9502 lines
1016 KiB
Plaintext
9502 lines
1016 KiB
Plaintext
2025-11-09T20:55:22Z INFO 373 [root]: /opt/conda/bin/neuronx-cc compile --framework=XLA /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/model.MODULE_e6b44ff520e6c4333666+e9aa1481.hlo_module.pb --output /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/model.MODULE_e6b44ff520e6c4333666+e9aa1481.neff --target=trn2 --auto-cast=none --model-type=transformer '--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma' --lnc=2 -O1 '--internal-hlo2tensorizer-options= --modular-flow-mac-threshold=10 --verify-hlo=true' --logfile=/models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/log-neuron-cc.txt --verbose=35
|
|
2025-11-09T20:55:27Z INFO 373 [root]: NeuronX Compiler version 2.21.33363.0+82129205 Python version 3.11.11 HWM version 2.21.0.33363+82129205 NumPy version 1.26.4
|
|
2025-11-09T20:55:27Z INFO 550 [root]: XLA detected
|
|
2025-11-09T20:55:27Z INFO 550 [root]: Pipeline: HLOToTensorizer Frontend StaticIOTranspose WalrusDriver BIRLinker Kelper NeffWrapper
|
|
2025-11-09T20:55:31Z INFO 550 [root]: Intermediate files stored in /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/neuronxcc-u_vl19it, output in /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4
|
|
2025-11-09T20:55:31Z INFO 550 [pipeline.Pipeline.0]: Job Pipeline len(in_states) 1
|
|
2025-11-09T20:55:31Z INFO 550 [pipeline.Pipeline.0]: Processing input #0
|
|
2025-11-09T20:55:31Z INFO 550 [pipeline.Pipeline.0]: Running pipeline Pipeline.0
|
|
2025-11-09T20:55:31Z INFO 550 [pipeline.Pipeline.0]: Starting job job.HLOToTensorizer.0
|
|
2025-11-09T20:55:31Z INFO 550 [job.HLOToTensorizer.0]: Job HLOToTensorizer len(in_states) 1
|
|
2025-11-09T20:55:31Z INFO 550 [job.HLOToTensorizer.0]: Processing input #0
|
|
2025-11-09T20:55:31Z INFO 550 [job.HLOToTensorizer.0]: Executing: /opt/conda/lib/python3.11/site-packages/neuronxcc/starfish/bin/hlo2penguin --input /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/model.MODULE_e6b44ff520e6c4333666+e9aa1481.hlo_module.pb --out-dir ./ --output penguin.py --remat --max-costly-ops=2 --max-live-in-size=5 --max-remat-chain-size=10 --max-mem-multiple=1.8 --min-def-use-distance=500 --remat-policy=transformer --allow-same-pass-remat=true --verbose=error --logfile=/models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/log-neuron-cc.txt --logfile-verbose=info --layers-per-module=1 --partition --emit-tensor-level-dropout-ops --modular-flow-mac-threshold=10 --verify-hlo=true --native-to-custom-softmax --partitioner-opts='--transformer'
|
|
2025-11-09T20:55:40Z INFO 550 [job.HLOToTensorizer.0]:
|
|
Pre-Partition Pre-Opt Histogram:
|
|
total HLO instructions: 8312
|
|
reshape 1912 23.00% ################################################################
|
|
broadcast 1123 13.51% #####################################
|
|
transpose 1072 12.90% ###################################
|
|
convert 945 11.37% ###############################
|
|
constant 636 7.65% #####################
|
|
parameter 371 4.46% ############
|
|
slice 347 4.17% ###########
|
|
add 284 3.42% #########
|
|
get-tuple-element 259 3.12% ########
|
|
multiply 255 3.07% ########
|
|
dot 198 2.38% ######
|
|
call 174 2.09% #####
|
|
compare 173 2.08% #####
|
|
select 170 2.05% #####
|
|
concatenate 116 1.40% ###
|
|
tuple 57 0.69% #
|
|
scatter 57 0.69% #
|
|
negate 56 0.67% #
|
|
all-reduce 56 0.67% #
|
|
divide 29 0.35%
|
|
gather 6 0.07%
|
|
iota 5 0.06%
|
|
all-gather 3 0.04%
|
|
reduce 3 0.04%
|
|
custom-call 2 0.02%
|
|
sine 1 0.01%
|
|
cosine 1 0.01%
|
|
maximum 1 0.01%
|
|
|
|
|
|
Pre-Partition Post-Op Histogram:
|
|
total HLO instructions: 5437
|
|
reshape 1421 26.14% ################################################################
|
|
transpose 817 15.03% ####################################
|
|
convert 720 13.24% ################################
|
|
constant 443 8.15% ###################
|
|
parameter 371 6.82% ################
|
|
broadcast 266 4.89% ###########
|
|
dot 197 3.62% ########
|
|
custom-call 175 3.22% #######
|
|
multiply 171 3.15% #######
|
|
add 171 3.15% #######
|
|
get-tuple-element 147 2.70% ######
|
|
slice 115 2.12% #####
|
|
concatenate 114 2.10% #####
|
|
compare 59 1.09% ##
|
|
select 58 1.07% ##
|
|
scatter 57 1.05% ##
|
|
negate 56 1.03% ##
|
|
all-reduce 56 1.03% ##
|
|
gather 6 0.11%
|
|
all-gather 3 0.06%
|
|
iota 3 0.06%
|
|
reduce 3 0.06%
|
|
pad 2 0.04%
|
|
sine 1 0.02%
|
|
divide 1 0.02%
|
|
tuple 1 0.02%
|
|
maximum 1 0.02%
|
|
rng 1 0.02%
|
|
cosine 1 0.02%
|
|
|
|
Potential split-points stats: #CC 59 #AR 56 #AG 3 #BN 0 nClamp 0
|
|
ModuleSplitter initial partitioning... #parts 59
|
|
ModuleSplitter initial partitioning... Done.
|
|
0 1 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 3 2 57 58
|
|
New disjoint wave: start 2 len 54 NumReps: 27 macs 753766760448
|
|
First non-zero-mac/used part from the end is 58
|
|
Not enough zero-mac parts. skip
|
|
ModuleSplitter initial partitioning... #parts 29
|
|
ModuleSplitter initial partitioning... Done.
|
|
Remat: gather-iota 0 matches, 0 ops rematted
|
|
Wrote HLO netlist to hlo_netlist.json
|
|
Wrote graph partitions in debug_info_hlo_partitions.json
|
|
Processing partition 0
|
|
Replaced 0 dropout sequences with OffloadedDropout
|
|
HLO Ops used in computation: add all-gather all-reduce broadcast compare concatenate constant convert cosine custom-call dot gather get-tuple-element multiply negate parameter reshape scatter select sine slice transpose tuple
|
|
Invoking RemoveOptimizationBarriers pass
|
|
Processing partition 1
|
|
Replaced 0 dropout sequences with OffloadedDropout
|
|
HLO Ops used in computation: add all-reduce broadcast compare concatenate constant convert custom-call dot get-tuple-element multiply negate parameter reshape scatter select slice transpose tuple
|
|
Invoking RemoveOptimizationBarriers pass
|
|
Processing partition 2
|
|
Replaced 0 dropout sequences with OffloadedDropout
|
|
HLO Ops used in computation: add all-gather all-reduce broadcast compare concatenate constant convert custom-call divide dot gather get-tuple-element iota maximum multiply pad parameter reduce reshape rng scatter select slice transpose tuple
|
|
Invoking RemoveOptimizationBarriers pass
|
|
|
|
2025-11-09T20:55:40Z INFO 550 [job.HLOToTensorizer.0]: IR signature: 4d83ebbf58c3d64d98146963cffcf9881dc66e3c32b00b8b6651a2fe4ffe9d12 for sg0000/HLOToTensorizer
|
|
2025-11-09T20:55:40Z INFO 550 [job.HLOToTensorizer.0]: IR signature: fcea4c0f2eed2b295c8f8107328f300dce88a00dffc1f9e5db97851eb5475c39 for sg0001/HLOToTensorizer
|
|
2025-11-09T20:55:40Z INFO 550 [job.HLOToTensorizer.0]: IR signature: c05e7950d7af07ded9e3a64f6bb14d692d6ba2cd09cc3ac9a6bbbd0a0514e315 for sg0002/HLOToTensorizer
|
|
2025-11-09T20:55:40Z INFO 550 [job.HLOToTensorizer.0]: Job #0 finished
|
|
2025-11-09T20:55:40Z INFO 550 [pipeline.Pipeline.0]: Finished job job.HLOToTensorizer.0
|
|
2025-11-09T20:55:40Z INFO 550 [pipeline.Pipeline.0]: Starting job job.Frontend.0
|
|
2025-11-09T20:55:40Z INFO 550 [job.Frontend.0]: Job Frontend len(in_states) 1
|
|
2025-11-09T20:55:40Z INFO 550 [job.Frontend.0]: Processing input #0
|
|
2025-11-09T20:55:40Z INFO 550 [job.Frontend.0]: Start model loading
|
|
2025-11-09T20:55:40Z INFO 550 [job.Frontend.0]: Start tensorization
|
|
2025-11-09T20:55:52Z INFO 550 [job.Frontend.0]: Num jobs: 12
|
|
2025-11-09T20:55:52Z USER 550 [root/Tensorizer/Tensorizer]: Running Tensorizer
|
|
2025-11-09T20:55:52Z INFO 550 [Tensorizer]: Max workers: 3
|
|
2025-11-09T20:55:53Z INFO 749 [Tensorizer]: Building model from Penguin script "penguin.py.000001"...
|
|
2025-11-09T20:55:53Z INFO 748 [Tensorizer]: Building model from Penguin script "penguin.py.000000"...
|
|
2025-11-09T20:55:53Z INFO 750 [Tensorizer]: Building model from Penguin script "penguin.py.000002"...
|
|
2025-11-09T20:55:54Z INFO 748 [Tensorizer]: Allocate SB of shape (128, 0) for CausalAttentionMMSoftmaxMMWithoutSwap
|
|
2025-11-09T20:55:54Z INFO 748 [Tensorizer]: Allocate PSUM of shape (8, 128, 0) for CausalAttentionMMSoftmaxMMWithoutSwap
|
|
2025-11-09T20:55:54Z INFO 748 [Tensorizer]: Tensorizer options: --enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma --run-pg-layout-and-tiling --enable-dse-after-mask-propagation --disable-concat-delinearizer --num-neuroncores-per-sengine=2 --num-neuroncores-per-sengine=2 --internal_dynamic_dma_scratch_size_per_partition=16384 --disable-bitcasted-transpose --dont-verify-after-all --fp32-cast=none --mm-transpose-type=fp32 --disable-expensive-checks --disable-max-stride-tiling --hbm-scratchpad-page-size-in-bytes=536870912 --enable-replication --max-local-tensor-tile-size-in-bytes=32768 --tensor-layout-p-order=0 --tensor-layout-b-order=1 --enable-advanced-delinearization --weight-coalescing-threshold=512 --enable-bir-converter=enable --enable-tritium-loopfusion --enable-softmax-kernel --model-type-transformer --enable-isl-in-injective-check --enable-dge-on-io-dma --enable-dge-on-spill-reload-dma --enable-dge-on-indirect-dma --enable-dge-on-vector-indirect-dma --keep-rng-tensor-op
|
|
2025-11-09T20:55:54Z INFO 748 [sg0000/Tensorizer/DoNothing]: Running DoNothing
|
|
2025-11-09T20:55:54Z INFO 748 [sg0000/Tensorizer/DoNothing]: Finished (changed=True)
|
|
2025-11-09T20:55:54Z INFO 748 [sg0000/Tensorizer/DoNothing]: DoNothing finished after 0.002 seconds
|
|
2025-11-09T20:55:54Z INFO 748 [sg0000/Tensorizer/LegalizeOpLevelAlias]: Running LegalizeOpLevelAlias
|
|
2025-11-09T20:55:54Z INFO 748 [sg0000/Tensorizer/LegalizeOpLevelAlias]: Finished (changed=False)
|
|
2025-11-09T20:55:54Z INFO 748 [sg0000/Tensorizer/LegalizeOpLevelAlias]: LegalizeOpLevelAlias finished after 0.021 seconds
|
|
2025-11-09T20:55:54Z INFO 748 [sg0000/Tensorizer/OptimizeAliasedCopyChain]: Running OptimizeAliasedCopyChain
|
|
2025-11-09T20:55:54Z INFO 748 [sg0000/Tensorizer/OptimizeAliasedCopyChain]: Finished (changed=False)
|
|
2025-11-09T20:55:54Z INFO 748 [sg0000/Tensorizer/OptimizeAliasedCopyChain]: OptimizeAliasedCopyChain finished after 0.017 seconds
|
|
2025-11-09T20:55:54Z INFO 748 [sg0000/Tensorizer/AliasDependencyInduction]: Running AliasDependencyInduction
|
|
2025-11-09T20:55:55Z INFO 748 [sg0000/Tensorizer/AliasDependencyInduction]: Finished (changed=False)
|
|
2025-11-09T20:55:55Z INFO 749 [Tensorizer]: Allocate SB of shape (128, 0) for CausalAttentionMMSoftmaxMMWithoutSwap
|
|
2025-11-09T20:55:55Z INFO 749 [Tensorizer]: Allocate PSUM of shape (8, 128, 0) for CausalAttentionMMSoftmaxMMWithoutSwap
|
|
2025-11-09T20:55:55Z INFO 748 [sg0000/Tensorizer/AliasDependencyInduction]: AliasDependencyInduction finished after 0.289 seconds
|
|
2025-11-09T20:55:55Z INFO 748 [sg0000/Tensorizer/TransformConvOp]: Running TransformConvOp
|
|
2025-11-09T20:55:55Z INFO 749 [Tensorizer]: Tensorizer options: --enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma --run-pg-layout-and-tiling --enable-dse-after-mask-propagation --disable-concat-delinearizer --num-neuroncores-per-sengine=2 --num-neuroncores-per-sengine=2 --internal_dynamic_dma_scratch_size_per_partition=16384 --disable-bitcasted-transpose --dont-verify-after-all --fp32-cast=none --mm-transpose-type=fp32 --disable-expensive-checks --disable-max-stride-tiling --hbm-scratchpad-page-size-in-bytes=536870912 --enable-replication --max-local-tensor-tile-size-in-bytes=32768 --tensor-layout-p-order=0 --tensor-layout-b-order=1 --enable-advanced-delinearization --weight-coalescing-threshold=512 --enable-bir-converter=enable --enable-tritium-loopfusion --enable-softmax-kernel --model-type-transformer --enable-isl-in-injective-check --enable-dge-on-io-dma --enable-dge-on-spill-reload-dma --enable-dge-on-indirect-dma --enable-dge-on-vector-indirect-dma --keep-rng-tensor-op
|
|
2025-11-09T20:55:55Z INFO 748 [sg0000/Tensorizer/TransformConvOp]: Finished (changed=False)
|
|
2025-11-09T20:55:55Z INFO 748 [sg0000/Tensorizer/TransformConvOp]: TransformConvOp finished after 0.176 seconds
|
|
2025-11-09T20:55:55Z INFO 748 [sg0000/Tensorizer/LowerTensorOp]: Running LowerTensorOp
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/DoNothing]: Running DoNothing
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/DoNothing]: Finished (changed=True)
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/DoNothing]: DoNothing finished after 0.003 seconds
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/LegalizeOpLevelAlias]: Running LegalizeOpLevelAlias
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/LegalizeOpLevelAlias]: Finished (changed=False)
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/LegalizeOpLevelAlias]: LegalizeOpLevelAlias finished after 0.024 seconds
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/OptimizeAliasedCopyChain]: Running OptimizeAliasedCopyChain
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/OptimizeAliasedCopyChain]: Finished (changed=False)
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/OptimizeAliasedCopyChain]: OptimizeAliasedCopyChain finished after 0.002 seconds
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/AliasDependencyInduction]: Running AliasDependencyInduction
|
|
2025-11-09T20:55:55Z INFO 748 [sg0000/Tensorizer/LowerTensorOp]: Finished (changed=True)
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/AliasDependencyInduction]: Finished (changed=False)
|
|
2025-11-09T20:55:55Z INFO 748 [sg0000/Tensorizer/LowerTensorOp]: LowerTensorOp finished after 0.226 seconds
|
|
2025-11-09T20:55:55Z INFO 748 [sg0000/Tensorizer/AliasDependencyReset]: Running AliasDependencyReset
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/AliasDependencyInduction]: AliasDependencyInduction finished after 0.117 seconds
|
|
2025-11-09T20:55:55Z INFO 748 [sg0000/Tensorizer/AliasDependencyElimination]: Running AliasDependencyElimination
|
|
2025-11-09T20:55:55Z INFO 748 [sg0000/Tensorizer/AliasDependencyElimination]: Finished (changed=False)
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/TransformConvOp]: Running TransformConvOp
|
|
2025-11-09T20:55:55Z INFO 748 [sg0000/Tensorizer/AliasDependencyElimination]: AliasDependencyElimination finished after 0.001 seconds
|
|
2025-11-09T20:55:55Z INFO 748 [sg0000/Tensorizer/AliasDependencyInduction]: Running AliasDependencyInduction
|
|
2025-11-09T20:55:55Z INFO 749 [sg0001/Tensorizer/TransformConvOp]: Finished (changed=False)
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/TransformConvOp]: TransformConvOp finished after 0.092 seconds
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/LowerTensorOp]: Running LowerTensorOp
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/AliasDependencyInduction]: Finished (changed=True)
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/AliasDependencyInduction]: AliasDependencyInduction finished after 0.292 seconds
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/AliasDependencyReset]: AliasDependencyReset finished after 0.392 seconds
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/LegalizeCCOpLayout]: Running LegalizeCCOpLayout
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/LowerTensorOp]: Finished (changed=True)
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/LowerTensorOp]: LowerTensorOp finished after 0.329 seconds
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/AliasDependencyReset]: Running AliasDependencyReset
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/AliasDependencyElimination]: Running AliasDependencyElimination
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/AliasDependencyElimination]: Finished (changed=False)
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/AliasDependencyElimination]: AliasDependencyElimination finished after 0.001 seconds
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/AliasDependencyInduction]: Running AliasDependencyInduction
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/LegalizeCCOpLayout]: Finished (changed=False)
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/LegalizeCCOpLayout]: LegalizeCCOpLayout finished after 0.110 seconds
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/TensorOpSimplifier]: Running TensorOpSimplifier
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/TensorOpSimplifier]: Finished (changed=True)
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/AliasDependencyInduction]: Finished (changed=True)
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/TensorOpSimplifier]: TensorOpSimplifier finished after 0.114 seconds
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/CanonicalizeIR]: Running CanonicalizeIR
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/CanonicalizeIR]: Finished (changed=True)
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/AliasDependencyInduction]: AliasDependencyInduction finished after 0.194 seconds
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/CanonicalizeIR]: CanonicalizeIR finished after 0.012 seconds
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/ResolveComplicatePredicates]: Running ResolveComplicatePredicates
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/ResolveComplicatePredicates]: Finished (changed=False)
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/AliasDependencyReset]: AliasDependencyReset finished after 0.225 seconds
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/LegalizeCCOpLayout]: Running LegalizeCCOpLayout
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/LegalizeCCOpLayout]: Finished (changed=False)
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/LegalizeCCOpLayout]: LegalizeCCOpLayout finished after 0.005 seconds
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/TensorOpSimplifier]: Running TensorOpSimplifier
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/ResolveComplicatePredicates]: ResolveComplicatePredicates finished after 0.002 seconds
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/AffinePredicateResolution]: Running AffinePredicateResolution
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/TensorOpSimplifier]: Finished (changed=True)
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/AffinePredicateResolution]: Finished (changed=False)
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/TensorOpSimplifier]: TensorOpSimplifier finished after 0.038 seconds
|
|
2025-11-09T20:55:56Z INFO 749 [sg0001/Tensorizer/CanonicalizeIR]: Running CanonicalizeIR
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/AffinePredicateResolution]: AffinePredicateResolution finished after 0.067 seconds
|
|
2025-11-09T20:55:56Z INFO 748 [sg0000/Tensorizer/EliminateDivs]: Running EliminateDivs
|
|
2025-11-09T20:55:57Z INFO 748 [sg0000/Tensorizer/EliminateDivs]: Finished (changed=False)
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/CanonicalizeIR]: Finished (changed=True)
|
|
2025-11-09T20:55:57Z INFO 748 [sg0000/Tensorizer/EliminateDivs]: EliminateDivs finished after 0.080 seconds
|
|
2025-11-09T20:55:57Z INFO 748 [sg0000/Tensorizer/PerfectLoopNest]: Running PerfectLoopNest
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/CanonicalizeIR]: CanonicalizeIR finished after 0.102 seconds
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/ResolveComplicatePredicates]: Running ResolveComplicatePredicates
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/ResolveComplicatePredicates]: Finished (changed=False)
|
|
2025-11-09T20:55:57Z INFO 748 [sg0000/Tensorizer/PerfectLoopNest]: Finished (changed=False)
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/ResolveComplicatePredicates]: ResolveComplicatePredicates finished after 0.003 seconds
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/AffinePredicateResolution]: Running AffinePredicateResolution
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/AffinePredicateResolution]: Finished (changed=False)
|
|
2025-11-09T20:55:57Z INFO 748 [sg0000/Tensorizer/PerfectLoopNest]: PerfectLoopNest finished after 0.078 seconds
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/AffinePredicateResolution]: AffinePredicateResolution finished after 0.003 seconds
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/EliminateDivs]: Running EliminateDivs
|
|
2025-11-09T20:55:57Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:55:57Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/EliminateDivs]: Finished (changed=False)
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/EliminateDivs]: EliminateDivs finished after 0.102 seconds
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/PerfectLoopNest]: Running PerfectLoopNest
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/PerfectLoopNest]: Finished (changed=False)
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/PerfectLoopNest]: PerfectLoopNest finished after 0.002 seconds
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.290 seconds
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier_iteration_1
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier_iteration_1 finished after 0.005 seconds
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier_iteration_2
|
|
2025-11-09T20:55:57Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.585 seconds
|
|
2025-11-09T20:55:57Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_1
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier_iteration_2 finished after 0.101 seconds
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/Simplifier]: Finished (changed=True)
|
|
2025-11-09T20:55:57Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_1 finished after 0.095 seconds
|
|
2025-11-09T20:55:57Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_2
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier finished after 0.487 seconds
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier
|
|
2025-11-09T20:55:57Z INFO 749 [sg0001/Tensorizer/GenericAccessSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:55:57Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_2 finished after 0.011 seconds
|
|
2025-11-09T20:55:57Z INFO 748 [sg0000/Tensorizer/Simplifier]: Finished (changed=True)
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.003 seconds
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/TCTransform]: Running TCTransform
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/TCTransform]: Finished (changed=False)
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/TCTransform]: TCTransform finished after 0.005 seconds
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/CommuteConcat]: Running CommuteConcat
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/CommuteConcat]: Running CommuteConcat_iteration_0
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/CommuteConcat]: CommuteConcat_iteration_0 finished after 0.069 seconds
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/CommuteConcat]: Finished (changed=False)
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier finished after 0.706 seconds
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/CommuteConcat]: CommuteConcat finished after 0.070 seconds
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/ExpandBatchNorm]: Running ExpandBatchNorm
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/ExpandBatchNorm]: Finished (changed=False)
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/GenericAccessSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/ExpandBatchNorm]: ExpandBatchNorm finished after 0.004 seconds
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/TCTransform]: Running TCTransform
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/TCTransform]: Finished (changed=False)
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/TCTransform]: TCTransform finished after 0.002 seconds
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.088 seconds
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/TCTransform]: Running TCTransform
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/GenericAccessSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/TCTransform]: Finished (changed=False)
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.013 seconds
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/TensorOpTransform]: Running TensorOpTransform
|
|
2025-11-09T20:55:58Z INFO 749 [sg0001/Tensorizer/TensorOpTransform]: Running TensorOpTransform_iteration_0
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/TCTransform]: TCTransform finished after 0.092 seconds
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/CommuteConcat]: Running CommuteConcat
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/CommuteConcat]: Running CommuteConcat_iteration_0
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/CommuteConcat]: CommuteConcat_iteration_0 finished after 0.003 seconds
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/CommuteConcat]: Finished (changed=False)
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/CommuteConcat]: CommuteConcat finished after 0.016 seconds
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/ExpandBatchNorm]: Running ExpandBatchNorm
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/ExpandBatchNorm]: Finished (changed=False)
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/ExpandBatchNorm]: ExpandBatchNorm finished after 0.011 seconds
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/TCTransform]: Running TCTransform
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/TCTransform]: Finished (changed=False)
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/TCTransform]: TCTransform finished after 0.001 seconds
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/GenericAccessSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.079 seconds
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/TensorOpTransform]: Running TensorOpTransform
|
|
2025-11-09T20:55:58Z INFO 748 [sg0000/Tensorizer/TensorOpTransform]: Running TensorOpTransform_iteration_0
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/TensorOpTransform]: TensorOpTransform_iteration_0 finished after 0.417 seconds
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/TensorOpTransform]: Running TensorOpTransform_iteration_1
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/TensorOpTransform]: TensorOpTransform_iteration_1 finished after 0.079 seconds
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/TensorOpTransform]: Finished (changed=True)
|
|
2025-11-09T20:55:59Z INFO 749 [sg0001/Tensorizer/TensorOpTransform]: TensorOpTransform_iteration_0 finished after 0.910 seconds
|
|
2025-11-09T20:55:59Z INFO 749 [sg0001/Tensorizer/TensorOpTransform]: Running TensorOpTransform_iteration_1
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/TensorOpTransform]: TensorOpTransform finished after 0.500 seconds
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/LateLowerTensorOp]: Running LateLowerTensorOp
|
|
2025-11-09T20:55:59Z INFO 749 [sg0001/Tensorizer/TensorOpTransform]: TensorOpTransform_iteration_1 finished after 0.269 seconds
|
|
2025-11-09T20:55:59Z INFO 749 [sg0001/Tensorizer/TensorOpTransform]: Finished (changed=True)
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/LateLowerTensorOp]: Finished (changed=True)
|
|
2025-11-09T20:55:59Z INFO 749 [sg0001/Tensorizer/TensorOpTransform]: TensorOpTransform finished after 1.189 seconds
|
|
2025-11-09T20:55:59Z INFO 749 [sg0001/Tensorizer/LateLowerTensorOp]: Running LateLowerTensorOp
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/LateLowerTensorOp]: LateLowerTensorOp finished after 0.204 seconds
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/AliasDependencyReset]: Running AliasDependencyReset
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/AliasDependencyElimination]: Running AliasDependencyElimination
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/AliasDependencyElimination]: Finished (changed=True)
|
|
2025-11-09T20:55:59Z INFO 749 [sg0001/Tensorizer/LateLowerTensorOp]: Finished (changed=True)
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/AliasDependencyElimination]: AliasDependencyElimination finished after 0.001 seconds
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/AliasDependencyInduction]: Running AliasDependencyInduction
|
|
2025-11-09T20:55:59Z INFO 749 [sg0001/Tensorizer/LateLowerTensorOp]: LateLowerTensorOp finished after 0.101 seconds
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/AliasDependencyInduction]: Finished (changed=False)
|
|
2025-11-09T20:55:59Z INFO 749 [sg0001/Tensorizer/AliasDependencyReset]: Running AliasDependencyReset
|
|
2025-11-09T20:55:59Z INFO 749 [sg0001/Tensorizer/AliasDependencyElimination]: Running AliasDependencyElimination
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/AliasDependencyInduction]: AliasDependencyInduction finished after 0.022 seconds
|
|
2025-11-09T20:55:59Z INFO 749 [sg0001/Tensorizer/AliasDependencyElimination]: Finished (changed=True)
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/AliasDependencyReset]: AliasDependencyReset finished after 0.198 seconds
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/MemcpyElimination]: Running MemcpyElimination
|
|
2025-11-09T20:55:59Z INFO 748 [sg0000/Tensorizer/MemcpyElimination]: Running MemcpyElimination_iteration_0
|
|
2025-11-09T20:56:00Z INFO 749 [sg0001/Tensorizer/AliasDependencyElimination]: AliasDependencyElimination finished after 0.001 seconds
|
|
2025-11-09T20:56:00Z INFO 749 [sg0001/Tensorizer/AliasDependencyInduction]: Running AliasDependencyInduction
|
|
2025-11-09T20:56:00Z INFO 749 [sg0001/Tensorizer/AliasDependencyInduction]: Finished (changed=False)
|
|
2025-11-09T20:56:00Z INFO 749 [sg0001/Tensorizer/AliasDependencyInduction]: AliasDependencyInduction finished after 0.218 seconds
|
|
2025-11-09T20:56:00Z INFO 749 [sg0001/Tensorizer/AliasDependencyReset]: AliasDependencyReset finished after 0.487 seconds
|
|
2025-11-09T20:56:00Z INFO 749 [sg0001/Tensorizer/MemcpyElimination]: Running MemcpyElimination
|
|
2025-11-09T20:56:00Z INFO 749 [sg0001/Tensorizer/MemcpyElimination]: Running MemcpyElimination_iteration_0
|
|
2025-11-09T20:56:00Z INFO 748 [sg0000/Tensorizer/MemcpyElimination]: MemcpyElimination_iteration_0 finished after 0.797 seconds
|
|
2025-11-09T20:56:00Z INFO 748 [sg0000/Tensorizer/MemcpyElimination]: Running MemcpyElimination_iteration_1
|
|
2025-11-09T20:56:00Z INFO 748 [sg0000/Tensorizer/MemcpyElimination]: MemcpyElimination_iteration_1 finished after 0.005 seconds
|
|
2025-11-09T20:56:00Z INFO 748 [sg0000/Tensorizer/MemcpyElimination]: Finished (changed=True)
|
|
2025-11-09T20:56:00Z INFO 748 [sg0000/Tensorizer/MemcpyElimination]: MemcpyElimination finished after 0.808 seconds
|
|
2025-11-09T20:56:00Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion
|
|
2025-11-09T20:56:00Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.190 seconds
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_1
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_1 finished after 0.114 seconds
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_2
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_2 finished after 0.003 seconds
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.084 seconds
|
|
2025-11-09T20:56:01Z INFO 749 [sg0001/Tensorizer/MemcpyElimination]: MemcpyElimination_iteration_0 finished after 0.638 seconds
|
|
2025-11-09T20:56:01Z INFO 749 [sg0001/Tensorizer/MemcpyElimination]: Running MemcpyElimination_iteration_1
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_1
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_1 finished after 0.006 seconds
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/LoopFusion]: LoopFusion finished after 0.491 seconds
|
|
2025-11-09T20:56:01Z INFO 749 [sg0001/Tensorizer/MemcpyElimination]: MemcpyElimination_iteration_1 finished after 0.077 seconds
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Rematerialization]: Running Rematerialization
|
|
2025-11-09T20:56:01Z INFO 749 [sg0001/Tensorizer/MemcpyElimination]: Finished (changed=True)
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Rematerialization]: Finished (changed=True)
|
|
2025-11-09T20:56:01Z INFO 749 [sg0001/Tensorizer/MemcpyElimination]: MemcpyElimination finished after 0.797 seconds
|
|
2025-11-09T20:56:01Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Running LoopFusion
|
|
2025-11-09T20:56:01Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Rematerialization]: Rematerialization finished after 0.091 seconds
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.111 seconds
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_1
|
|
2025-11-09T20:56:01Z INFO 749 [sg0001/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.199 seconds
|
|
2025-11-09T20:56:01Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Running LoopFusion_iteration_1
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_1 finished after 0.164 seconds
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_2
|
|
2025-11-09T20:56:01Z INFO 749 [sg0001/Tensorizer/LoopFusion]: LoopFusion_iteration_1 finished after 0.082 seconds
|
|
2025-11-09T20:56:01Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Running LoopFusion_iteration_2
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_2 finished after 0.032 seconds
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Simplifier]: Finished (changed=True)
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier finished after 0.309 seconds
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:01Z INFO 749 [sg0001/Tensorizer/LoopFusion]: LoopFusion_iteration_2 finished after 0.109 seconds
|
|
2025-11-09T20:56:01Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Delinearization]: Finished (changed=True)
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/Delinearization]: Delinearization finished after 0.028 seconds
|
|
2025-11-09T20:56:01Z INFO 748 [sg0000/Tensorizer/DeadStoreElimination]: Running DeadStoreElimination
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.183 seconds
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Running LoopFusion_iteration_1
|
|
2025-11-09T20:56:02Z INFO 750 [Tensorizer]: Tensorizer options: --enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma --run-pg-layout-and-tiling --enable-dse-after-mask-propagation --disable-concat-delinearizer --num-neuroncores-per-sengine=2 --num-neuroncores-per-sengine=2 --internal_dynamic_dma_scratch_size_per_partition=16384 --disable-bitcasted-transpose --dont-verify-after-all --fp32-cast=none --mm-transpose-type=fp32 --disable-expensive-checks --disable-max-stride-tiling --hbm-scratchpad-page-size-in-bytes=536870912 --enable-replication --max-local-tensor-tile-size-in-bytes=32768 --tensor-layout-p-order=0 --tensor-layout-b-order=1 --enable-advanced-delinearization --weight-coalescing-threshold=512 --enable-bir-converter=enable --enable-tritium-loopfusion --enable-softmax-kernel --model-type-transformer --enable-isl-in-injective-check --enable-dge-on-io-dma --enable-dge-on-spill-reload-dma --enable-dge-on-indirect-dma --enable-dge-on-vector-indirect-dma --keep-rng-tensor-op
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/LoopFusion]: LoopFusion_iteration_1 finished after 0.021 seconds
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/LoopFusion]: LoopFusion finished after 0.609 seconds
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Rematerialization]: Running Rematerialization
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/DoNothing]: Running DoNothing
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/DoNothing]: Finished (changed=True)
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Rematerialization]: Finished (changed=False)
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Rematerialization]: Rematerialization finished after 0.069 seconds
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.083 seconds
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier_iteration_1
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/DoNothing]: DoNothing finished after 0.001 seconds
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/LegalizeOpLevelAlias]: Running LegalizeOpLevelAlias
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier_iteration_1 finished after 0.021 seconds
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Simplifier]: Finished (changed=True)
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/LegalizeOpLevelAlias]: Finished (changed=False)
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier finished after 0.105 seconds
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/LegalizeOpLevelAlias]: LegalizeOpLevelAlias finished after 0.006 seconds
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/OptimizeAliasedCopyChain]: Running OptimizeAliasedCopyChain
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/OptimizeAliasedCopyChain]: Finished (changed=False)
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/DeadStoreElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/OptimizeAliasedCopyChain]: OptimizeAliasedCopyChain finished after 0.004 seconds
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/AliasDependencyInduction]: Running AliasDependencyInduction
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/DeadStoreElimination]: DeadStoreElimination finished after 0.397 seconds
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Delinearization]: Finished (changed=True)
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/AliasDependencyInduction]: Finished (changed=False)
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Delinearization]: Delinearization finished after 0.111 seconds
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/DeadStoreElimination]: Running DeadStoreElimination
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/AliasDependencyInduction]: AliasDependencyInduction finished after 0.086 seconds
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/TransformConvOp]: Running TransformConvOp
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/TransformConvOp]: Finished (changed=False)
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.101 seconds
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/Simplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/TransformConvOp]: TransformConvOp finished after 0.014 seconds
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/LowerTensorOp]: Running LowerTensorOp
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier finished after 0.103 seconds
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/LICM]: Finished (changed=True)
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/DeadStoreElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/LICM]: LICM finished after 0.107 seconds
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/Delinearization]: Delinearization finished after 0.006 seconds
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.008 seconds
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/DeadStoreElimination]: DeadStoreElimination finished after 0.383 seconds
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/LowerTensorOp]: Finished (changed=True)
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/LowerTensorOp]: LowerTensorOp finished after 0.402 seconds
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/AliasDependencyReset]: Running AliasDependencyReset
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/AliasDependencyElimination]: Running AliasDependencyElimination
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/AliasDependencyElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.082 seconds
|
|
2025-11-09T20:56:02Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Finished (changed=False)
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.024 seconds
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/AliasDependencyElimination]: AliasDependencyElimination finished after 0.001 seconds
|
|
2025-11-09T20:56:02Z INFO 749 [sg0001/Tensorizer/Simplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:02Z INFO 750 [sg0002/Tensorizer/AliasDependencyInduction]: Running AliasDependencyInduction
|
|
2025-11-09T20:56:03Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier finished after 0.092 seconds
|
|
2025-11-09T20:56:03Z INFO 749 [sg0001/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/AliasDependencyInduction]: Finished (changed=False)
|
|
2025-11-09T20:56:03Z INFO 749 [sg0001/Tensorizer/LICM]: Finished (changed=True)
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/LoopFusion]: LoopFusion finished after 0.095 seconds
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/SimplifySlice]: Running SimplifySlice
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/AliasDependencyInduction]: AliasDependencyInduction finished after 0.107 seconds
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/SimplifySlice]: Finished (changed=False)
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/AliasDependencyReset]: AliasDependencyReset finished after 0.206 seconds
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/LegalizeCCOpLayout]: Running LegalizeCCOpLayout
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/LegalizeCCOpLayout]: Finished (changed=False)
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/LegalizeCCOpLayout]: LegalizeCCOpLayout finished after 0.004 seconds
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/TensorOpSimplifier]: Running TensorOpSimplifier
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/SimplifySlice]: SimplifySlice finished after 0.015 seconds
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/TensorOpSimplifier]: Finished (changed=True)
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/LICM]: Finished (changed=False)
|
|
2025-11-09T20:56:03Z INFO 749 [sg0001/Tensorizer/LICM]: LICM finished after 0.080 seconds
|
|
2025-11-09T20:56:03Z INFO 749 [sg0001/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/TensorOpSimplifier]: TensorOpSimplifier finished after 0.027 seconds
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/CanonicalizeIR]: Running CanonicalizeIR
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/LICM]: LICM finished after 0.077 seconds
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/CanonicalizeIR]: Finished (changed=True)
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/CanonicalizeIR]: CanonicalizeIR finished after 0.017 seconds
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/ResolveComplicatePredicates]: Running ResolveComplicatePredicates
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/ResolveComplicatePredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/ResolveComplicatePredicates]: ResolveComplicatePredicates finished after 0.004 seconds
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/AffinePredicateResolution]: Running AffinePredicateResolution
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/AffinePredicateResolution]: Finished (changed=False)
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/AffinePredicateResolution]: AffinePredicateResolution finished after 0.001 seconds
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/EliminateDivs]: Running EliminateDivs
|
|
2025-11-09T20:56:03Z INFO 749 [sg0001/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.110 seconds
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_1
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/EliminateDivs]: Finished (changed=False)
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_1 finished after 0.015 seconds
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/Simplifier]: Finished (changed=True)
|
|
2025-11-09T20:56:03Z INFO 749 [sg0001/Tensorizer/Delinearization]: Delinearization finished after 0.286 seconds
|
|
2025-11-09T20:56:03Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Running LoopFusion
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier finished after 0.202 seconds
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/ValueNumbering]: Running ValueNumbering
|
|
2025-11-09T20:56:03Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/EliminateDivs]: EliminateDivs finished after 0.095 seconds
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/PerfectLoopNest]: Running PerfectLoopNest
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/ValueNumbering]: Finished (changed=True)
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/PerfectLoopNest]: Finished (changed=False)
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/ValueNumbering]: ValueNumbering finished after 0.074 seconds
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/LICM]: Finished (changed=False)
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/LICM]: LICM finished after 0.005 seconds
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/PadElimination]: Running PadElimination
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/PadElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/PadElimination]: PadElimination finished after 0.005 seconds
|
|
2025-11-09T20:56:03Z INFO 748 [sg0000/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/PerfectLoopNest]: PerfectLoopNest finished after 0.007 seconds
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:03Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:03Z INFO 749 [sg0001/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.204 seconds
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.018 seconds
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/Delinearization]: Delinearization finished after 0.181 seconds
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/LoopFusion]: LoopFusion finished after 0.302 seconds
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/SimplifySlice]: Running SimplifySlice
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/SimplifySlice]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.075 seconds
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/SimplifySlice]: SimplifySlice finished after 0.004 seconds
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/LICM]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.017 seconds
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/LoopFusion]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/LoopFusion]: LoopFusion finished after 0.097 seconds
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/GenericAccessSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.002 seconds
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/LICM]: LICM finished after 0.005 seconds
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.104 seconds
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/Simplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier finished after 0.106 seconds
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/LICM]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/LICM]: LICM finished after 0.006 seconds
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/ValueNumbering]: Running ValueNumbering
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/ValueNumbering]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.585 seconds
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/ValueNumbering]: ValueNumbering finished after 0.013 seconds
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier_iteration_1
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/TCTransform]: Running TCTransform
|
|
2025-11-09T20:56:04Z INFO 748 [sg0000/Tensorizer/TCTransform]: Finished (changed=True)
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier_iteration_1 finished after 0.015 seconds
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/Simplifier]: Finished (changed=True)
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier finished after 0.622 seconds
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/GenericAccessSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.292 seconds
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier_iteration_1
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.004 seconds
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/TCTransform]: Running TCTransform
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/TCTransform]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier_iteration_1 finished after 0.085 seconds
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/TCTransform]: TCTransform finished after 0.003 seconds
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/CommuteConcat]: Running CommuteConcat
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/Simplifier]: Finished (changed=True)
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/CommuteConcat]: Running CommuteConcat_iteration_0
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier finished after 0.380 seconds
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/ValueNumbering]: Running ValueNumbering
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/CommuteConcat]: CommuteConcat_iteration_0 finished after 0.003 seconds
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/CommuteConcat]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/CommuteConcat]: CommuteConcat finished after 0.005 seconds
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/ExpandBatchNorm]: Running ExpandBatchNorm
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/ValueNumbering]: Finished (changed=True)
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/ExpandBatchNorm]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/ValueNumbering]: ValueNumbering finished after 0.008 seconds
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/LICM]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/ExpandBatchNorm]: ExpandBatchNorm finished after 0.005 seconds
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/TCTransform]: Running TCTransform
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/TCTransform]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/TCTransform]: TCTransform finished after 0.004 seconds
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/GenericAccessSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.003 seconds
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/TensorOpTransform]: Running TensorOpTransform
|
|
2025-11-09T20:56:04Z INFO 750 [sg0002/Tensorizer/TensorOpTransform]: Running TensorOpTransform_iteration_0
|
|
2025-11-09T20:56:04Z INFO 749 [sg0001/Tensorizer/LICM]: LICM finished after 0.005 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/PadElimination]: Running PadElimination
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/PadElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/PadElimination]: PadElimination finished after 0.002 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/TCTransform]: TCTransform finished after 0.005 seconds
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/CommuteConcat]: Running CommuteConcat
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/CommuteConcat]: Running CommuteConcat_iteration_0
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/CommuteConcat]: CommuteConcat_iteration_0 finished after 0.003 seconds
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/CommuteConcat]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/CommuteConcat]: CommuteConcat finished after 0.005 seconds
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/RecognizeOpIdiom]: Running RecognizeOpIdiom
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/RecognizeOpIdiom]: Running RecognizeOpIdiom_iteration_0
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/RecognizeOpIdiom]: RecognizeOpIdiom_iteration_0 finished after 0.009 seconds
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/RecognizeOpIdiom]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/Delinearization]: Delinearization finished after 0.090 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Running LoopFusion
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/TensorOpTransform]: TensorOpTransform_iteration_0 finished after 0.229 seconds
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/TensorOpTransform]: Running TensorOpTransform_iteration_1
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/RecognizeOpIdiom]: RecognizeOpIdiom finished after 0.011 seconds
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/MaskPropagation]: Running MaskPropagation
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/TensorOpTransform]: TensorOpTransform_iteration_1 finished after 0.072 seconds
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/TensorOpTransform]: Finished (changed=True)
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.094 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/TensorOpTransform]: TensorOpTransform finished after 0.304 seconds
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/LateLowerTensorOp]: Running LateLowerTensorOp
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/LateLowerTensorOp]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/MaskPropagation]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.083 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/LoopFusion]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/LateLowerTensorOp]: LateLowerTensorOp finished after 0.006 seconds
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/AliasDependencyReset]: Running AliasDependencyReset
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/AliasDependencyElimination]: Running AliasDependencyElimination
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/AliasDependencyElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/MaskPropagation]: MaskPropagation finished after 0.095 seconds
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/DeadStoreElimination]: Running DeadStoreElimination
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/LoopFusion]: LoopFusion finished after 0.180 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/GenericAccessSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.002 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.075 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/Simplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/AliasDependencyElimination]: AliasDependencyElimination finished after 0.000 seconds
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/AliasDependencyInduction]: Running AliasDependencyInduction
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier finished after 0.075 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/LICM]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/DeadStoreElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/LICM]: LICM finished after 0.008 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/ValueNumbering]: Running ValueNumbering
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/AliasDependencyInduction]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/AliasDependencyInduction]: AliasDependencyInduction finished after 0.018 seconds
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/AliasDependencyReset]: AliasDependencyReset finished after 0.129 seconds
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/MemcpyElimination]: Running MemcpyElimination
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/MemcpyElimination]: Running MemcpyElimination_iteration_0
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/ValueNumbering]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/ValueNumbering]: ValueNumbering finished after 0.086 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/TCTransform]: Running TCTransform
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/TCTransform]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/TCTransform]: TCTransform finished after 0.002 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/CommuteConcat]: Running CommuteConcat
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/CommuteConcat]: Running CommuteConcat_iteration_0
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/CommuteConcat]: CommuteConcat_iteration_0 finished after 0.002 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/CommuteConcat]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/CommuteConcat]: CommuteConcat finished after 0.002 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/RecognizeOpIdiom]: Running RecognizeOpIdiom
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/RecognizeOpIdiom]: Running RecognizeOpIdiom_iteration_0
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/RecognizeOpIdiom]: RecognizeOpIdiom_iteration_0 finished after 0.008 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/RecognizeOpIdiom]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/RecognizeOpIdiom]: RecognizeOpIdiom finished after 0.009 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/MaskPropagation]: Running MaskPropagation
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/MemcpyElimination]: MemcpyElimination_iteration_0 finished after 0.214 seconds
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/MemcpyElimination]: Running MemcpyElimination_iteration_1
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/MemcpyElimination]: MemcpyElimination_iteration_1 finished after 0.005 seconds
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/MemcpyElimination]: Finished (changed=True)
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/MaskPropagation]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/DeadStoreElimination]: DeadStoreElimination finished after 0.109 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/MaskPropagation]: MaskPropagation finished after 0.014 seconds
|
|
2025-11-09T20:56:05Z INFO 749 [sg0001/Tensorizer/DeadStoreElimination]: Running DeadStoreElimination
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/MemcpyElimination]: MemcpyElimination finished after 0.221 seconds
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/LoopFusion]: Running LoopFusion
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/Recompute]: Running Recompute
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/Recompute]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/Recompute]: Recompute finished after 0.003 seconds
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/DeadCodeElimination]: DeadCodeElimination_iteration_0 finished after 0.003 seconds
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/DeadCodeElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/DeadCodeElimination]: DeadCodeElimination finished after 0.006 seconds
|
|
2025-11-09T20:56:05Z INFO 748 [Tensorizer]: After optimization: 32 statements
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/DoNothing]: Running DoNothing
|
|
2025-11-09T20:56:05Z INFO 748 [sg0000/Tensorizer/DoNothing]: Finished (changed=True)
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.126 seconds
|
|
2025-11-09T20:56:05Z INFO 750 [sg0002/Tensorizer/LoopFusion]: Running LoopFusion_iteration_1
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/LoopFusion]: LoopFusion_iteration_1 finished after 0.072 seconds
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/DeadStoreElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:06Z INFO 748 [sg0000/Tensorizer/DoNothing]: DoNothing finished after 0.000 seconds
|
|
2025-11-09T20:56:06Z INFO 748 [sg0000/Tensorizer/MutateDataType]: Running MutateDataType
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.004 seconds
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/LoopFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:06Z INFO 748 [sg0000/Tensorizer/MutateDataType]: Finished (changed=False)
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/LoopFusion]: LoopFusion finished after 0.205 seconds
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Rematerialization]: Running Rematerialization
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Rematerialization]: Finished (changed=False)
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/DeadStoreElimination]: DeadStoreElimination finished after 0.271 seconds
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/Recompute]: Running Recompute
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/Recompute]: Finished (changed=False)
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/Recompute]: Recompute finished after 0.002 seconds
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Rematerialization]: Rematerialization finished after 0.009 seconds
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/DeadCodeElimination]: DeadCodeElimination_iteration_0 finished after 0.003 seconds
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/DeadCodeElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:06Z INFO 748 [sg0000/Tensorizer/MutateDataType]: MutateDataType finished after 0.012 seconds
|
|
2025-11-09T20:56:06Z INFO 748 [sg0000/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier
|
|
2025-11-09T20:56:06Z INFO 748 [sg0000/Tensorizer/GenericAccessSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:06Z INFO 748 [sg0000/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.003 seconds
|
|
2025-11-09T20:56:06Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:06Z INFO 748 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.175 seconds
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/DeadCodeElimination]: DeadCodeElimination finished after 0.007 seconds
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier_iteration_1
|
|
2025-11-09T20:56:06Z INFO 749 [Tensorizer]: After optimization: 32 statements
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/DoNothing]: Running DoNothing
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/DoNothing]: Finished (changed=True)
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier_iteration_1 finished after 0.009 seconds
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier_iteration_2
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/DoNothing]: DoNothing finished after 0.000 seconds
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/MutateDataType]: Running MutateDataType
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier_iteration_2 finished after 0.006 seconds
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Simplifier]: Finished (changed=True)
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/MutateDataType]: Finished (changed=False)
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier finished after 0.192 seconds
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/MutateDataType]: MutateDataType finished after 0.014 seconds
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/GenericAccessSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.011 seconds
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:06Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.190 seconds
|
|
2025-11-09T20:56:06Z INFO 748 [sg0000/Tensorizer/Simplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Delinearization]: Finished (changed=True)
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.088 seconds
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/Simplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:06Z INFO 748 [sg0000/Tensorizer/Simplifier]: Simplifier finished after 0.194 seconds
|
|
2025-11-09T20:56:06Z INFO 748 [sg0000/Tensorizer/TileCCOps]: Running TileCCOps
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/Simplifier]: Simplifier finished after 0.090 seconds
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/TileCCOps]: Running TileCCOps
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/TileCCOps]: Finished (changed=False)
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Delinearization]: Delinearization finished after 0.101 seconds
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/DeadStoreElimination]: Running DeadStoreElimination
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/TileCCOps]: TileCCOps finished after 0.018 seconds
|
|
2025-11-09T20:56:06Z INFO 749 [sg0001/Tensorizer/DelinearIndices]: Running DelinearIndices
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/DeadStoreElimination]: Finished (changed=True)
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/DeadStoreElimination]: DeadStoreElimination finished after 0.231 seconds
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:06Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.097 seconds
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/Simplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:07Z INFO 748 [sg0000/Tensorizer/TileCCOps]: Finished (changed=True)
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier finished after 0.103 seconds
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/LICM]: Finished (changed=True)
|
|
2025-11-09T20:56:07Z INFO 749 [sg0001/Tensorizer/DelinearIndices]: Finished (changed=True)
|
|
2025-11-09T20:56:07Z INFO 748 [sg0000/Tensorizer/TileCCOps]: TileCCOps finished after 0.588 seconds
|
|
2025-11-09T20:56:07Z INFO 748 [sg0000/Tensorizer/DelinearIndices]: Running DelinearIndices
|
|
2025-11-09T20:56:07Z INFO 749 [sg0001/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.503 seconds
|
|
2025-11-09T20:56:07Z INFO 749 [sg0001/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/LICM]: LICM finished after 0.007 seconds
|
|
2025-11-09T20:56:07Z INFO 749 [sg0001/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:07Z INFO 749 [sg0001/Tensorizer/Delinearization]: Delinearization finished after 0.096 seconds
|
|
2025-11-09T20:56:07Z INFO 749 [sg0001/Tensorizer/DelinearIndices]: Running DelinearIndices
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/Delinearization]: Finished (changed=True)
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/Delinearization]: Delinearization finished after 0.097 seconds
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/LoopFusion]: Running LoopFusion
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.095 seconds
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.019 seconds
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/LoopFusion]: Finished (changed=False)
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/LoopFusion]: LoopFusion finished after 0.119 seconds
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/SimplifySlice]: Running SimplifySlice
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/SimplifySlice]: Finished (changed=False)
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/SimplifySlice]: SimplifySlice finished after 0.003 seconds
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:07Z INFO 749 [sg0001/Tensorizer/DelinearIndices]: Finished (changed=False)
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/LICM]: Finished (changed=True)
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/LICM]: LICM finished after 0.007 seconds
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:07Z INFO 748 [sg0000/Tensorizer/DelinearIndices]: Finished (changed=True)
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.025 seconds
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier_iteration_1
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier_iteration_1 finished after 0.068 seconds
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/Simplifier]: Finished (changed=True)
|
|
2025-11-09T20:56:07Z INFO 749 [sg0001/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.304 seconds
|
|
2025-11-09T20:56:07Z INFO 749 [sg0001/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination
|
|
2025-11-09T20:56:07Z INFO 749 [sg0001/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier finished after 0.093 seconds
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/ValueNumbering]: Running ValueNumbering
|
|
2025-11-09T20:56:07Z INFO 750 [sg0002/Tensorizer/ValueNumbering]: Finished (changed=False)
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/DeadCodeElimination]: DeadCodeElimination_iteration_0 finished after 0.016 seconds
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/DeadCodeElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.600 seconds
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/DeadCodeElimination]: DeadCodeElimination finished after 0.099 seconds
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/LateLowerReshapeOp]: Running LateLowerReshapeOp
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/LateLowerReshapeOp]: Finished (changed=False)
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/Delinearization]: Delinearization finished after 0.013 seconds
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/DelinearIndices]: Running DelinearIndices
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/LateLowerReshapeOp]: LateLowerReshapeOp finished after 0.003 seconds
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/InferIntrinsicOnCC]: Running InferIntrinsicOnCC
|
|
2025-11-09T20:56:08Z INFO 750 [sg0002/Tensorizer/ValueNumbering]: ValueNumbering finished after 0.005 seconds
|
|
2025-11-09T20:56:08Z INFO 750 [sg0002/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/DelinearIndices]: Finished (changed=False)
|
|
2025-11-09T20:56:08Z INFO 750 [sg0002/Tensorizer/LICM]: Finished (changed=False)
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.115 seconds
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/DeadCodeElimination]: DeadCodeElimination_iteration_0 finished after 0.003 seconds
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/DeadCodeElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/DeadCodeElimination]: DeadCodeElimination finished after 0.006 seconds
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/LateLowerReshapeOp]: Running LateLowerReshapeOp
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/LateLowerReshapeOp]: Finished (changed=False)
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/LateLowerReshapeOp]: LateLowerReshapeOp finished after 0.003 seconds
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/InferIntrinsicOnCC]: Running InferIntrinsicOnCC
|
|
2025-11-09T20:56:08Z INFO 750 [sg0002/Tensorizer/LICM]: LICM finished after 0.085 seconds
|
|
2025-11-09T20:56:08Z INFO 750 [sg0002/Tensorizer/PadElimination]: Running PadElimination
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/InferIntrinsicOnCC]: Finished (changed=True)
|
|
2025-11-09T20:56:08Z INFO 750 [sg0002/Tensorizer/PadElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/InferIntrinsicOnCC]: Finished (changed=False)
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/InferIntrinsicOnCC]: InferIntrinsicOnCC finished after 0.297 seconds
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/ResolveAccessConflict]: Running ResolveAccessConflict
|
|
2025-11-09T20:56:08Z INFO 750 [sg0002/Tensorizer/PadElimination]: PadElimination finished after 0.007 seconds
|
|
2025-11-09T20:56:08Z INFO 750 [sg0002/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/ResolveAccessConflict]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/ResolveAccessConflict]: DeadCodeElimination_iteration_0 finished after 0.002 seconds
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/ResolveAccessConflict]: Finished (changed=False)
|
|
2025-11-09T20:56:08Z INFO 750 [sg0002/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/ResolveAccessConflict]: ResolveAccessConflict finished after 0.024 seconds
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/LICM]: Finished (changed=True)
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/LICM]: LICM finished after 0.005 seconds
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/LocalLayoutOpt]: Running LocalLayoutOpt
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/InferIntrinsicOnCC]: InferIntrinsicOnCC finished after 0.092 seconds
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/ResolveAccessConflict]: Running ResolveAccessConflict
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/ResolveAccessConflict]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/ResolveAccessConflict]: DeadCodeElimination_iteration_0 finished after 0.002 seconds
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/ResolveAccessConflict]: Finished (changed=False)
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/ResolveAccessConflict]: ResolveAccessConflict finished after 0.011 seconds
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/LICM]: Finished (changed=True)
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/LICM]: LICM finished after 0.005 seconds
|
|
2025-11-09T20:56:08Z INFO 748 [sg0000/Tensorizer/LocalLayoutOpt]: Running LocalLayoutOpt
|
|
2025-11-09T20:56:08Z INFO 749 [sg0001/Tensorizer/LocalLayoutOpt]: Finished (changed=True)
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/LocalLayoutOpt]: LocalLayoutOpt finished after 0.231 seconds
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/DelinearIndices]: Running DelinearIndices
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/Delinearization]: Delinearization finished after 0.092 seconds
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/LoopFusion]: Running LoopFusion
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/LocalLayoutOpt]: Finished (changed=True)
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/DelinearIndices]: Finished (changed=False)
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/LocalLayoutOpt]: LocalLayoutOpt finished after 0.275 seconds
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/DelinearIndices]: Running DelinearIndices
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.107 seconds
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.187 seconds
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/PGLayoutTilingPipeline]: Running PGLayoutTilingPipeline
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/LowerCCOpBlockAxis]: Running LowerCCOpBlockAxis
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/DelinearIndices]: Finished (changed=False)
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/LowerCCOpBlockAxis]: Finished (changed=False)
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.101 seconds
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/LoopFusion]: Finished (changed=False)
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.108 seconds
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/PGLayoutTilingPipeline]: Running PGLayoutTilingPipeline
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/LowerCCOpBlockAxis]: Running LowerCCOpBlockAxis
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/LowerCCOpBlockAxis]: Finished (changed=True)
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/LowerCCOpBlockAxis]: LowerCCOpBlockAxis finished after 0.029 seconds
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/LayoutPreprocessingAndAnalysis]: Running LayoutPreprocessingAndAnalysis
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/LayoutPreprocessing]: Running LayoutPreprocessing
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/LowerCCOpBlockAxis]: LowerCCOpBlockAxis finished after 0.015 seconds
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/LayoutPreprocessingAndAnalysis]: Running LayoutPreprocessingAndAnalysis
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/LayoutPreprocessing]: Running LayoutPreprocessing
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/LoopFusion]: LoopFusion finished after 0.296 seconds
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/GenericAccessSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.003 seconds
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/Delinearization]: Delinearization finished after 0.087 seconds
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/Delinearization]: Delinearization finished after 0.009 seconds
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/LayoutPreprocessing]: Finished (changed=True)
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.103 seconds
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/Simplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/LayoutPreprocessing]: Finished (changed=True)
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/LayoutPreprocessing]: LayoutPreprocessing finished after 0.238 seconds
|
|
2025-11-09T20:56:09Z INFO 749 [sg0001/Tensorizer/LayoutRequirementAnalysis]: Running LayoutRequirementAnalysis
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/LayoutPreprocessing]: LayoutPreprocessing finished after 0.213 seconds
|
|
2025-11-09T20:56:09Z INFO 748 [sg0000/Tensorizer/LayoutRequirementAnalysis]: Running LayoutRequirementAnalysis
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier finished after 0.105 seconds
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:09Z INFO 750 [sg0002/Tensorizer/LICM]: Finished (changed=True)
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/LICM]: LICM finished after 0.007 seconds
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/ValueNumbering]: Running ValueNumbering
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/ValueNumbering]: Finished (changed=False)
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/ValueNumbering]: ValueNumbering finished after 0.007 seconds
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/TCTransform]: Running TCTransform
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/TCTransform]: Finished (changed=False)
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/TCTransform]: TCTransform finished after 0.011 seconds
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/CommuteConcat]: Running CommuteConcat
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/CommuteConcat]: Running CommuteConcat_iteration_0
|
|
2025-11-09T20:56:10Z INFO 749 [sg0001/Tensorizer/LayoutRequirementAnalysis]: LayoutRequirementAnalysis finished after 0.105 seconds
|
|
2025-11-09T20:56:10Z INFO 749 [sg0001/Tensorizer/LayoutPreprocessingAndAnalysis]: LayoutPreprocessingAndAnalysis finished after 0.712 seconds
|
|
2025-11-09T20:56:10Z INFO 749 [sg0001/Tensorizer/InferNonlocalTensors]: Running InferNonlocalTensors
|
|
2025-11-09T20:56:10Z INFO 749 [sg0001/Tensorizer/InferNonlocalTensors]: prefer_non_broadcast_par: True
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/CommuteConcat]: CommuteConcat_iteration_0 finished after 0.091 seconds
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/CommuteConcat]: Finished (changed=False)
|
|
2025-11-09T20:56:10Z INFO 748 [sg0000/Tensorizer/LayoutRequirementAnalysis]: LayoutRequirementAnalysis finished after 0.091 seconds
|
|
2025-11-09T20:56:10Z INFO 748 [sg0000/Tensorizer/LayoutPreprocessingAndAnalysis]: LayoutPreprocessingAndAnalysis finished after 0.628 seconds
|
|
2025-11-09T20:56:10Z INFO 748 [sg0000/Tensorizer/InferNonlocalTensors]: Running InferNonlocalTensors
|
|
2025-11-09T20:56:10Z INFO 748 [sg0000/Tensorizer/InferNonlocalTensors]: prefer_non_broadcast_par: True
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/CommuteConcat]: CommuteConcat finished after 0.095 seconds
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/RecognizeOpIdiom]: Running RecognizeOpIdiom
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/RecognizeOpIdiom]: Running RecognizeOpIdiom_iteration_0
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/RecognizeOpIdiom]: RecognizeOpIdiom_iteration_0 finished after 0.104 seconds
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/RecognizeOpIdiom]: Finished (changed=False)
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/RecognizeOpIdiom]: RecognizeOpIdiom finished after 0.105 seconds
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/MaskPropagation]: Running MaskPropagation
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/MaskPropagation]: Finished (changed=False)
|
|
2025-11-09T20:56:10Z INFO 749 [sg0001/Tensorizer/InferNonlocalTensors]: prefer_non_broadcast_par: True
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/MaskPropagation]: MaskPropagation finished after 0.204 seconds
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/DeadStoreElimination]: Running DeadStoreElimination
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/DeadStoreElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/DeadStoreElimination]: DeadStoreElimination finished after 0.008 seconds
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/Recompute]: Running Recompute
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/Recompute]: Finished (changed=False)
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/Recompute]: Recompute finished after 0.083 seconds
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:10Z INFO 750 [sg0002/Tensorizer/DeadCodeElimination]: DeadCodeElimination_iteration_0 finished after 0.011 seconds
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DeadCodeElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DeadCodeElimination]: DeadCodeElimination finished after 0.084 seconds
|
|
2025-11-09T20:56:11Z INFO 750 [Tensorizer]: After optimization: 39 statements
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DoNothing]: Running DoNothing
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DoNothing]: Finished (changed=True)
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DoNothing]: DoNothing finished after 0.001 seconds
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/MutateDataType]: Running MutateDataType
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/MutateDataType]: Finished (changed=False)
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/MutateDataType]: MutateDataType finished after 0.084 seconds
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/GenericAccessSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.005 seconds
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/Simplifier]: Running Simplifier_iteration_0
|
|
2025-11-09T20:56:11Z INFO 749 [sg0001/Tensorizer/InferNonlocalTensors]: Finished (changed=False)
|
|
2025-11-09T20:56:11Z INFO 749 [sg0001/Tensorizer/InferNonlocalTensors]: InferNonlocalTensors finished after 0.996 seconds
|
|
2025-11-09T20:56:11Z INFO 749 [sg0001/Tensorizer/PAGLayoutOpt]: Running PAGLayoutOpt
|
|
2025-11-09T20:56:11Z INFO 749 [sg0001/Tensorizer/ParAxesAnnotation]: Running ParAxesAnnotation
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.117 seconds
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/Simplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/Simplifier]: Simplifier finished after 0.128 seconds
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/TileCCOps]: Running TileCCOps
|
|
2025-11-09T20:56:11Z INFO 749 [sg0001/Tensorizer/LayoutSearchAlgorithm]: prefer_non_broadcast_par: True
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/TileCCOps]: pass did not tile CC tensor due to `All gather output tensor check failed`
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/TileCCOps]: in float32 (1024,) %'all_gather.2' = AllGatherOp-162 AllGather_add(float32 (256,) %'add.11', replica_groups = [[0, 1, 2, 3]],all_gather_dim = DimensionSet((1024,), {0}),stream_id = -1) # dl = tensor_op_name: _all-gather.6459 | hlo_id: 108 | , id = 162
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/TileCCOps]: pass did not tile CC tensor due to `multi_rank_size=4096 is not above min_allgather_tile_size_in_bytes=8388608`
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/TileCCOps]: in uint32 (1024,) %'all_gather.3' = AllGatherOp-178 AllGather_add(uint32 (256,) %'add.12', replica_groups = [[0, 1, 2, 3]],all_gather_dim = DimensionSet((1024,), {0}),stream_id = -1) # dl = tensor_op_name: _all-gather.6596 | hlo_id: 117 | , id = 178
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/TileCCOps]: Finished (changed=False)
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/TileCCOps]: TileCCOps finished after 0.132 seconds
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DelinearIndices]: Running DelinearIndices
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DelinearIndices]: Finished (changed=True)
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.195 seconds
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/Delinearization]: Delinearization finished after 0.011 seconds
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DelinearIndices]: Running DelinearIndices
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DelinearIndices]: Finished (changed=False)
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.085 seconds
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DeadCodeElimination]: DeadCodeElimination_iteration_0 finished after 0.008 seconds
|
|
2025-11-09T20:56:11Z INFO 750 [sg0002/Tensorizer/DeadCodeElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/DeadCodeElimination]: DeadCodeElimination finished after 0.012 seconds
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/LateLowerReshapeOp]: Running LateLowerReshapeOp
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/LateLowerReshapeOp]: Finished (changed=False)
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/LateLowerReshapeOp]: LateLowerReshapeOp finished after 0.004 seconds
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/InferIntrinsicOnCC]: Running InferIntrinsicOnCC
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/InferIntrinsicOnCC]: Finished (changed=True)
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/InferIntrinsicOnCC]: InferIntrinsicOnCC finished after 0.170 seconds
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/ResolveAccessConflict]: Running ResolveAccessConflict
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/ResolveAccessConflict]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:12Z INFO 748 [sg0000/Tensorizer/InferNonlocalTensors]: prefer_non_broadcast_par: True
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/ResolveAccessConflict]: DeadCodeElimination_iteration_0 finished after 0.006 seconds
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/ResolveAccessConflict]: Finished (changed=False)
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/ResolveAccessConflict]: ResolveAccessConflict finished after 0.101 seconds
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/LICM]: Finished (changed=True)
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/LICM]: LICM finished after 0.008 seconds
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/LocalLayoutOpt]: Running LocalLayoutOpt
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/LocalLayoutOpt]: Finished (changed=True)
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/LocalLayoutOpt]: LocalLayoutOpt finished after 0.304 seconds
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/DelinearIndices]: Running DelinearIndices
|
|
2025-11-09T20:56:12Z INFO 750 [sg0002/Tensorizer/DelinearIndices]: Finished (changed=False)
|
|
2025-11-09T20:56:13Z INFO 750 [sg0002/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.115 seconds
|
|
2025-11-09T20:56:13Z INFO 750 [sg0002/Tensorizer/PGLayoutTilingPipeline]: Running PGLayoutTilingPipeline
|
|
2025-11-09T20:56:13Z INFO 750 [sg0002/Tensorizer/LowerCCOpBlockAxis]: Running LowerCCOpBlockAxis
|
|
2025-11-09T20:56:13Z INFO 750 [sg0002/Tensorizer/LowerCCOpBlockAxis]: Finished (changed=False)
|
|
2025-11-09T20:56:13Z INFO 750 [sg0002/Tensorizer/LowerCCOpBlockAxis]: LowerCCOpBlockAxis finished after 0.212 seconds
|
|
2025-11-09T20:56:13Z INFO 750 [sg0002/Tensorizer/LayoutPreprocessingAndAnalysis]: Running LayoutPreprocessingAndAnalysis
|
|
2025-11-09T20:56:13Z INFO 750 [sg0002/Tensorizer/LayoutPreprocessing]: Running LayoutPreprocessing
|
|
2025-11-09T20:56:13Z INFO 748 [sg0000/Tensorizer/InferNonlocalTensors]: Finished (changed=False)
|
|
2025-11-09T20:56:13Z INFO 748 [sg0000/Tensorizer/InferNonlocalTensors]: InferNonlocalTensors finished after 3.224 seconds
|
|
2025-11-09T20:56:13Z INFO 748 [sg0000/Tensorizer/PAGLayoutOpt]: Running PAGLayoutOpt
|
|
2025-11-09T20:56:13Z INFO 748 [sg0000/Tensorizer/ParAxesAnnotation]: Running ParAxesAnnotation
|
|
2025-11-09T20:56:13Z INFO 750 [sg0002/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:13Z INFO 748 [sg0000/Tensorizer/LayoutSearchAlgorithm]: prefer_non_broadcast_par: True
|
|
2025-11-09T20:56:13Z INFO 750 [sg0002/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:14Z INFO 750 [sg0002/Tensorizer/Delinearization]: Delinearization finished after 0.198 seconds
|
|
2025-11-09T20:56:14Z INFO 750 [sg0002/Tensorizer/LayoutPreprocessing]: Finished (changed=True)
|
|
2025-11-09T20:56:14Z INFO 750 [sg0002/Tensorizer/LayoutPreprocessing]: LayoutPreprocessing finished after 0.777 seconds
|
|
2025-11-09T20:56:14Z INFO 750 [sg0002/Tensorizer/LayoutRequirementAnalysis]: Running LayoutRequirementAnalysis
|
|
2025-11-09T20:56:14Z INFO 750 [sg0002/Tensorizer/LayoutRequirementAnalysis]: LayoutRequirementAnalysis finished after 0.187 seconds
|
|
2025-11-09T20:56:14Z INFO 750 [sg0002/Tensorizer/LayoutPreprocessingAndAnalysis]: LayoutPreprocessingAndAnalysis finished after 1.180 seconds
|
|
2025-11-09T20:56:14Z INFO 750 [sg0002/Tensorizer/InferNonlocalTensors]: Running InferNonlocalTensors
|
|
2025-11-09T20:56:14Z INFO 750 [sg0002/Tensorizer/InferNonlocalTensors]: prefer_non_broadcast_par: True
|
|
2025-11-09T20:56:14Z INFO 750 [sg0002/Tensorizer/InferNonlocalTensors]: prefer_non_broadcast_par: True
|
|
2025-11-09T20:56:15Z INFO 750 [sg0002/Tensorizer/InferNonlocalTensors]: Finished (changed=False)
|
|
2025-11-09T20:56:15Z INFO 750 [sg0002/Tensorizer/InferNonlocalTensors]: InferNonlocalTensors finished after 0.500 seconds
|
|
2025-11-09T20:56:15Z INFO 750 [sg0002/Tensorizer/PAGLayoutOpt]: Running PAGLayoutOpt
|
|
2025-11-09T20:56:15Z INFO 750 [sg0002/Tensorizer/ParAxesAnnotation]: Running ParAxesAnnotation
|
|
2025-11-09T20:56:15Z INFO 750 [sg0002/Tensorizer/LayoutSearchAlgorithm]: prefer_non_broadcast_par: True
|
|
2025-11-09T20:56:16Z INFO 749 [sg0001/Tensorizer/ParAxesAnnotation]: Finished (changed=True)
|
|
2025-11-09T20:56:16Z INFO 749 [sg0001/Tensorizer/ParAxesAnnotation]: ParAxesAnnotation finished after 5.510 seconds
|
|
2025-11-09T20:56:16Z INFO 749 [sg0001/Tensorizer/InsertLocalTransposes]: Running InsertLocalTransposes
|
|
2025-11-09T20:56:16Z INFO 749 [sg0001/Tensorizer/InsertLocalTransposes]: Finished (changed=True)
|
|
2025-11-09T20:56:16Z INFO 749 [sg0001/Tensorizer/InsertLocalTransposes]: InsertLocalTransposes finished after 0.092 seconds
|
|
2025-11-09T20:56:16Z INFO 749 [sg0001/Tensorizer/PAGLayoutOpt]: PAGLayoutOpt finished after 5.627 seconds
|
|
2025-11-09T20:56:16Z INFO 749 [sg0001/Tensorizer/DelinearizeSPMD]: Running DelinearizeSPMD
|
|
2025-11-09T20:56:16Z INFO 749 [sg0001/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:16Z INFO 749 [sg0001/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:17Z INFO 749 [sg0001/Tensorizer/Delinearization]: Delinearization finished after 0.004 seconds
|
|
2025-11-09T20:56:17Z INFO 749 [sg0001/Tensorizer/DelinearizeSPMD]: Finished (changed=False)
|
|
2025-11-09T20:56:17Z INFO 749 [sg0001/Tensorizer/DelinearizeSPMD]: DelinearizeSPMD finished after 0.089 seconds
|
|
2025-11-09T20:56:17Z INFO 749 [sg0001/Tensorizer/ShardingPropagationAnalysis]: Running ShardingPropagationAnalysis
|
|
2025-11-09T20:56:17Z INFO 749 [sg0001/Tensorizer/ShardingPropagationAnalysis]: ShardingPropagationAnalysis finished after 0.200 seconds
|
|
2025-11-09T20:56:17Z INFO 749 [sg0001/Tensorizer/InferShardAxis]: Running InferShardAxis
|
|
2025-11-09T20:56:18Z INFO 750 [sg0002/Tensorizer/ParAxesAnnotation]: Finished (changed=True)
|
|
2025-11-09T20:56:18Z INFO 750 [sg0002/Tensorizer/ParAxesAnnotation]: ParAxesAnnotation finished after 3.381 seconds
|
|
2025-11-09T20:56:18Z INFO 750 [sg0002/Tensorizer/InsertLocalTransposes]: Running InsertLocalTransposes
|
|
2025-11-09T20:56:18Z INFO 750 [sg0002/Tensorizer/InsertLocalTransposes]: Finished (changed=True)
|
|
2025-11-09T20:56:18Z INFO 750 [sg0002/Tensorizer/InsertLocalTransposes]: InsertLocalTransposes finished after 0.090 seconds
|
|
2025-11-09T20:56:18Z INFO 750 [sg0002/Tensorizer/PAGLayoutOpt]: PAGLayoutOpt finished after 3.499 seconds
|
|
2025-11-09T20:56:18Z INFO 750 [sg0002/Tensorizer/DelinearizeSPMD]: Running DelinearizeSPMD
|
|
2025-11-09T20:56:18Z INFO 750 [sg0002/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:18Z INFO 750 [sg0002/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:18Z INFO 750 [sg0002/Tensorizer/Delinearization]: Delinearization finished after 0.012 seconds
|
|
2025-11-09T20:56:18Z INFO 750 [sg0002/Tensorizer/DelinearizeSPMD]: Finished (changed=False)
|
|
2025-11-09T20:56:18Z INFO 750 [sg0002/Tensorizer/DelinearizeSPMD]: DelinearizeSPMD finished after 0.020 seconds
|
|
2025-11-09T20:56:18Z INFO 750 [sg0002/Tensorizer/ShardingPropagationAnalysis]: Running ShardingPropagationAnalysis
|
|
2025-11-09T20:56:19Z INFO 749 [sg0001/Tensorizer/ShardResult]: =================== Dumping Debug Info =====================
|
|
2025-11-09T20:56:19Z INFO 749 [sg0001/Tensorizer/ShardResult]: ------------------ Sharding summary ------------------
|
|
total number of dags: 32
|
|
total number of sharded dags: 25
|
|
|
|
total bytes transferred from input, output, non local tensors: 85992452
|
|
total bytes transferred from input, output, non local tensors with 2x bandwidths: 69210112
|
|
% bytes transferred with 2x bandwidths: 80.48
|
|
|
|
NC0 FLOPs: 92233720359985741827
|
|
NC1 FLOPs: 92233720359985741824
|
|
% FLOPs sharded: 100.00
|
|
|
|
|
|
Shard dim: 2048, Number of dags: 24
|
|
Matmuls sharded with this dim:
|
|
[2048(s),2,3,2,128] @ [2,3,2,128,4,4,128] = [2048(s),4,4,128] (stationary-streaming swapped) Number of occurrences: 1
|
|
[2048(s),2,8,128] @ [2,8,128,2,128] = [2048(s),2,128] Number of occurrences: 1
|
|
[2048(s),2,8,128] @ [2,8,128,2,2,2,64] = [2048(s),2,2,2,64] Number of occurrences: 1
|
|
[2048(s),2,8,128] @ [2,8,128,2,2,64] = [2048(s),2,2,64] Number of occurrences: 1
|
|
[2048(s),2,8,128] @ [2,8,128,2,3,2,128] = [2048(s),2,3,2,128] Number of occurrences: 2
|
|
|
|
|
|
Shard dim: 2, Number of dags: 1
|
|
Matmuls sharded with this dim:
|
|
[2048,2,2,128] @ [2,2,128,2(s),8,128] = [2048,2(s),8,128] (stationary-streaming swapped) Number of occurrences: 1
|
|
|
|
|
|
|
|
2025-11-09T20:56:19Z INFO 749 [sg0001/Tensorizer/DelinearIndices]: Running DelinearIndices
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/DelinearIndices]: Finished (changed=False)
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.098 seconds
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/RemoveShardedPartitionAxes]: Running RemoveShardedPartitionAxes
|
|
2025-11-09T20:56:20Z INFO 750 [sg0002/Tensorizer/ShardingPropagationAnalysis]: ShardingPropagationAnalysis finished after 1.705 seconds
|
|
2025-11-09T20:56:20Z INFO 750 [sg0002/Tensorizer/InferShardAxis]: Running InferShardAxis
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/RemoveShardedPartitionAxes]: Finished (changed=True)
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/RemoveShardedPartitionAxes]: RemoveShardedPartitionAxes finished after 0.403 seconds
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/InferShardAxis]: Finished (changed=True)
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/InferShardAxis]: InferShardAxis finished after 3.227 seconds
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/MaskPropagation]: Running MaskPropagation
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/MaskPropagation]: Finished (changed=False)
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/MaskPropagation]: MaskPropagation finished after 0.003 seconds
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/CanonicalizeDAGForPGTiling]: Running CanonicalizeDAGForPGTiling
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/CanonicalizeDAGForPGTiling]: Finished (changed=True)
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/CanonicalizeDAGForPGTiling]: CanonicalizeDAGForPGTiling finished after 0.184 seconds
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/LowerCCOpBlockAxis]: Running LowerCCOpBlockAxis
|
|
2025-11-09T20:56:20Z INFO 749 [sg0001/Tensorizer/LowerCCOpBlockAxis]: Finished (changed=False)
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/LowerCCOpBlockAxis]: LowerCCOpBlockAxis finished after 0.119 seconds
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/PGTiling]: Running PGTiling
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: Running AGOrderingAnalysisPass
|
|
2025-11-09T20:56:21Z INFO 748 [sg0000/Tensorizer/ParAxesAnnotation]: Finished (changed=True)
|
|
2025-11-09T20:56:21Z INFO 748 [sg0000/Tensorizer/ParAxesAnnotation]: ParAxesAnnotation finished after 7.722 seconds
|
|
2025-11-09T20:56:21Z INFO 748 [sg0000/Tensorizer/InsertLocalTransposes]: Running InsertLocalTransposes
|
|
2025-11-09T20:56:21Z INFO 748 [sg0000/Tensorizer/InsertLocalTransposes]: Finished (changed=True)
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 655 of IO tensor {'CrossPassTensor': ''}bfloat16 %input70|N|(128, 2, 8) is not sorted, index list (w/ AG ids): [(29, 'AG106'), (25, 'AG108'), (27, 'AG107')]
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 656 of IO tensor {'CrossPassTensor': ''}bfloat16 %input71|NC|(2, 3, 128, 2, 8, 2, 128) is not sorted, index list (w/ AG ids): [(29, 'AG106'), (25, 'AG108'), (27, 'AG107')]
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 657 of IO tensor {'CrossPassTensor': ''}bfloat16 %input69|NC|(2, 3, 128, 2, 8, 2, 128) is not sorted, index list (w/ AG ids): [(29, 'AG106'), (25, 'AG108'), (27, 'AG107')]
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 658 of IO tensor {'CrossPassTensor': ''}bfloat16 %input68|NC|(4, 2, 128, 3, 2, 4, 128) is not sorted, index list (w/ AG ids): [(22, 'AG114'), (28, 'AG111'), (23, 'AG113'), (26, 'AG112')]
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 659 of IO tensor {'CrossPassTensor': ''}bfloat16 %input74|N|(128, 2, 8) is not sorted, index list (w/ AG ids): [(29, 'AG106'), (25, 'AG108'), (27, 'AG107')]
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 660 of IO tensor {'CrossPassTensor': ''}bfloat16 %input78|NC|(2, 128, 8, 2, 2, 2, 64) is not sorted, index list (w/ AG ids): [(25, 'AG108'), (29, 'AG106'), (27, 'AG107')]
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 661 of IO tensor {'CrossPassTensor': ''}bfloat16 %input77|N|(64, 2) is not sorted, index list (w/ AG ids): [(11, 'AG118'), (7, 'AG119')]
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 662 of IO tensor {'CrossPassTensor': ''}bfloat16 %input76|NC|(2, 128, 8, 2, 2, 64) is not sorted, index list (w/ AG ids): [(25, 'AG108'), (29, 'AG106'), (27, 'AG107')]
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 663 of IO tensor {'CrossPassTensor': ''}bfloat16 %input75|N|(64, 2) is not sorted, index list (w/ AG ids): [(16, 'AG122'), (12, 'AG123')]
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 664 of IO tensor {'CrossPassTensor': ''}bfloat16 %input73|NC|(2, 128, 8, 2, 128) is not sorted, index list (w/ AG ids): [(25, 'AG108'), (29, 'AG106'), (27, 'AG107')]
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 444 of IO tensor {'CrossPassTensor': ''}bfloat16 %input72|NC|(2, 128, 2, 2, 8, 128) is not sorted, index list (w/ AG ids): [(18, 'AG129'), (10, 'AG131'), (15, 'AG130')]
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 694 of IO tensor non_local bfloat16 %reshape.68(2, 2, 2, 64, 2, 1024) is not sorted, index list (w/ AG ids): [(8, 'AG124'), (13, 'AG125'), (5, 'AG110'), (24, 'AG109')]
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 644 of IO tensor non_local bfloat16 %reshape.73(2, 2, 2, 1024, 128) is not sorted, index list (w/ AG ids): [(9, 'AG127'), (14, 'AG128'), (5, 'AG110'), (17, 'AG126')]
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/AGOrderingAnalysisPass]: AGOrderingAnalysisPass finished after 0.492 seconds
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/StaticTransposeLocalTensor]: Running StaticTransposeLocalTensor
|
|
2025-11-09T20:56:21Z INFO 748 [sg0000/Tensorizer/InsertLocalTransposes]: InsertLocalTransposes finished after 0.039 seconds
|
|
2025-11-09T20:56:21Z INFO 748 [sg0000/Tensorizer/PAGLayoutOpt]: PAGLayoutOpt finished after 7.920 seconds
|
|
2025-11-09T20:56:21Z INFO 748 [sg0000/Tensorizer/DelinearizeSPMD]: Running DelinearizeSPMD
|
|
2025-11-09T20:56:21Z INFO 748 [sg0000/Tensorizer/Delinearization]: Running Delinearization
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/StaticTransposeLocalTensor]: Finished (changed=True)
|
|
2025-11-09T20:56:21Z INFO 748 [sg0000/Tensorizer/Delinearization]: Finished (changed=False)
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/StaticTransposeLocalTensor]: StaticTransposeLocalTensor finished after 0.104 seconds
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/PComputeCutting]: Running PComputeCutting
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/PComputeCutting]: Finished (changed=True)
|
|
2025-11-09T20:56:21Z INFO 748 [sg0000/Tensorizer/Delinearization]: Delinearization finished after 0.013 seconds
|
|
2025-11-09T20:56:21Z INFO 748 [sg0000/Tensorizer/DelinearizeSPMD]: Finished (changed=False)
|
|
2025-11-09T20:56:21Z INFO 748 [sg0000/Tensorizer/DelinearizeSPMD]: DelinearizeSPMD finished after 0.202 seconds
|
|
2025-11-09T20:56:21Z INFO 748 [sg0000/Tensorizer/ShardingPropagationAnalysis]: Running ShardingPropagationAnalysis
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/PComputeCutting]: PComputeCutting finished after 0.087 seconds
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/BFComputeCutting]: Running BFComputeCutting
|
|
2025-11-09T20:56:21Z INFO 749 [sg0001/Tensorizer/BFComputeCutting]: Finished (changed=True)
|
|
2025-11-09T20:56:22Z INFO 749 [sg0001/Tensorizer/BFComputeCutting]: BFComputeCutting finished after 0.097 seconds
|
|
2025-11-09T20:56:22Z INFO 749 [sg0001/Tensorizer/LoopSplitting]: Running LoopSplitting
|
|
2025-11-09T20:56:22Z INFO 749 [sg0001/Tensorizer/LoopSplitting]: Finished (changed=False)
|
|
2025-11-09T20:56:22Z INFO 749 [sg0001/Tensorizer/LoopSplitting]: LoopSplitting finished after 0.001 seconds
|
|
2025-11-09T20:56:22Z INFO 749 [sg0001/Tensorizer/MacroGeneration]: Running MacroGeneration
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/ShardResult]: =================== Dumping Debug Info =====================
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/ShardResult]: ------------------ Sharding summary ------------------
|
|
total number of dags: 36
|
|
total number of sharded dags: 13
|
|
|
|
total bytes transferred from input, output, non local tensors: 216600994
|
|
total bytes transferred from input, output, non local tensors with 2x bandwidths: 203991440
|
|
% bytes transferred with 2x bandwidths: 94.18
|
|
|
|
NC0 FLOPs: 55340232214782380594
|
|
NC1 FLOPs: 55340232214782371376
|
|
% FLOPs sharded: 100.00
|
|
|
|
|
|
Shard dim: 2048, Number of dags: 7
|
|
Matmuls sharded with this dim:
|
|
[2048(s),2,3,2,128] @ [2,3,2,128,4,4,128] = [2048(s),4,4,128] (stationary-streaming swapped) Number of occurrences: 1
|
|
[2048(s),2,8,128] @ [2,8,128,2,3,2,128] = [2048(s),2,3,2,128] Number of occurrences: 2
|
|
|
|
|
|
Shard dim: 256, Number of dags: 5
|
|
Matmuls sharded with this dim:
|
|
|
|
|
|
Shard dim: 37984, Number of dags: 1
|
|
Matmuls sharded with this dim:
|
|
[2,8,128] @ [2,8,128,37984(s)] = [37984(s)] Number of occurrences: 1
|
|
|
|
|
|
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/DelinearIndices]: Running DelinearIndices
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/DelinearIndices]: Finished (changed=True)
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.088 seconds
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/RemoveShardedPartitionAxes]: Running RemoveShardedPartitionAxes
|
|
2025-11-09T20:56:22Z INFO 748 [sg0000/Tensorizer/ShardingPropagationAnalysis]: ShardingPropagationAnalysis finished after 0.402 seconds
|
|
2025-11-09T20:56:22Z INFO 748 [sg0000/Tensorizer/InferShardAxis]: Running InferShardAxis
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/RemoveShardedPartitionAxes]: Finished (changed=True)
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/RemoveShardedPartitionAxes]: RemoveShardedPartitionAxes finished after 0.111 seconds
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/InferShardAxis]: Finished (changed=True)
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/InferShardAxis]: InferShardAxis finished after 1.973 seconds
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/MaskPropagation]: Running MaskPropagation
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/MaskPropagation]: Finished (changed=False)
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/MaskPropagation]: MaskPropagation finished after 0.019 seconds
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/CanonicalizeDAGForPGTiling]: Running CanonicalizeDAGForPGTiling
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/CanonicalizeDAGForPGTiling]: Finished (changed=True)
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/CanonicalizeDAGForPGTiling]: CanonicalizeDAGForPGTiling finished after 0.017 seconds
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/LowerCCOpBlockAxis]: Running LowerCCOpBlockAxis
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/LowerCCOpBlockAxis]: Finished (changed=False)
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/LowerCCOpBlockAxis]: LowerCCOpBlockAxis finished after 0.006 seconds
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/PGTiling]: Running PGTiling
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/AGOrderingAnalysisPass]: Running AGOrderingAnalysisPass
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 598 of IO tensor {'CrossPassTensor': ''}bfloat16 %input367|N|(128, 2, 8) is not sorted, index list (w/ AG ids): [(26, 'AG77'), (21, 'AG79'), (22, 'AG78')]
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 599 of IO tensor {'CrossPassTensor': ''}bfloat16 %input368|NC|(2, 3, 128, 2, 8, 2, 128) is not sorted, index list (w/ AG ids): [(26, 'AG77'), (21, 'AG79'), (22, 'AG78')]
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 600 of IO tensor {'CrossPassTensor': ''}bfloat16 %input366|NC|(2, 3, 128, 2, 8, 2, 128) is not sorted, index list (w/ AG ids): [(26, 'AG77'), (21, 'AG79'), (22, 'AG78')]
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 601 of IO tensor {'CrossPassTensor': ''}bfloat16 %input365|NC|(4, 2, 128, 3, 2, 4, 128) is not sorted, index list (w/ AG ids): [(18, 'AG85'), (25, 'AG82'), (19, 'AG84'), (24, 'AG83')]
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 602 of IO tensor {'CrossPassTensor': ''}bfloat16 %input370|N|(128, 2, 8) is not sorted, index list (w/ AG ids): [(26, 'AG77'), (21, 'AG79'), (22, 'AG78')]
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 553 of IO tensor {'CrossPassTensor': ''}bfloat16 %input369|NC|(2, 18992, 2, 8, 128) is not sorted, index list (w/ AG ids): [(3, 'AG94'), (23, 'AG93'), (21, 'AG79'), (22, 'AG78')]
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/AGOrderingAnalysisPass]: AGOrderingAnalysisPass finished after 0.289 seconds
|
|
2025-11-09T20:56:22Z INFO 750 [sg0002/Tensorizer/StaticTransposeLocalTensor]: Running StaticTransposeLocalTensor
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/StaticTransposeLocalTensor]: Finished (changed=True)
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/StaticTransposeLocalTensor]: StaticTransposeLocalTensor finished after 0.087 seconds
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/PComputeCutting]: Running PComputeCutting
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/PComputeCutting]: Finished (changed=True)
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/PComputeCutting]: PComputeCutting finished after 0.102 seconds
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/BFComputeCutting]: Running BFComputeCutting
|
|
2025-11-09T20:56:23Z INFO 749 [sg0001/Tensorizer/MacroGeneration]: Finished (changed=True)
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/BFComputeCutting]: Finished (changed=True)
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/BFComputeCutting]: BFComputeCutting finished after 0.004 seconds
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/LoopSplitting]: Running LoopSplitting
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/LoopSplitting]: Finished (changed=False)
|
|
2025-11-09T20:56:23Z INFO 749 [sg0001/Tensorizer/MacroGeneration]: MacroGeneration finished after 1.186 seconds
|
|
2025-11-09T20:56:23Z INFO 749 [sg0001/Tensorizer/PGTiling]: PGTiling finished after 2.223 seconds
|
|
2025-11-09T20:56:23Z INFO 749 [sg0001/Tensorizer/InsertIOTransposes]: Running InsertIOTransposes
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/LoopSplitting]: LoopSplitting finished after 0.001 seconds
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/MacroGeneration]: Running MacroGeneration
|
|
2025-11-09T20:56:23Z INFO 749 [sg0001/Tensorizer/InsertIOTransposes]: Finished (changed=True)
|
|
2025-11-09T20:56:23Z INFO 749 [sg0001/Tensorizer/InsertIOTransposes]: InsertIOTransposes finished after 0.304 seconds
|
|
2025-11-09T20:56:23Z INFO 749 [sg0001/Tensorizer/InsertOffloadedTransposes]: Running InsertOffloadedTransposes
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/MacroGeneration]: Finished (changed=True)
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/MacroGeneration]: MacroGeneration finished after 0.401 seconds
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/PGTiling]: PGTiling finished after 1.204 seconds
|
|
2025-11-09T20:56:23Z INFO 750 [sg0002/Tensorizer/InsertIOTransposes]: Running InsertIOTransposes
|
|
2025-11-09T20:56:23Z INFO 749 [sg0001/Tensorizer/InsertOffloadedTransposes]: OffloadedTranspose inserted: 0
|
|
2025-11-09T20:56:23Z INFO 749 [sg0001/Tensorizer/InsertOffloadedTransposes]: Finished (changed=False)
|
|
2025-11-09T20:56:23Z INFO 749 [sg0001/Tensorizer/InsertOffloadedTransposes]: InsertOffloadedTransposes finished after 0.206 seconds
|
|
2025-11-09T20:56:23Z INFO 749 [sg0001/Tensorizer/DramToDramTranspose]: Running DramToDramTranspose
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/DramToDramTranspose]: Finished (changed=False)
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/DramToDramTranspose]: DramToDramTranspose finished after 0.101 seconds
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/PGLayoutTilingPipeline]: PGLayoutTilingPipeline finished after 14.707 seconds
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingProfiler]: Running TilingProfiler
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/InsertIOTransposes]: Finished (changed=True)
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/InsertIOTransposes]: InsertIOTransposes finished after 0.211 seconds
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/InsertOffloadedTransposes]: Running InsertOffloadedTransposes
|
|
2025-11-09T20:56:24Z INFO 748 [sg0000/Tensorizer/ShardResult]: =================== Dumping Debug Info =====================
|
|
2025-11-09T20:56:24Z INFO 748 [sg0000/Tensorizer/ShardResult]: ------------------ Sharding summary ------------------
|
|
total number of dags: 32
|
|
total number of sharded dags: 25
|
|
|
|
total bytes transferred from input, output, non local tensors: 51402758
|
|
total bytes transferred from input, output, non local tensors with 2x bandwidths: 47207424
|
|
% bytes transferred with 2x bandwidths: 91.84
|
|
|
|
NC0 FLOPs: 36893488145287151619
|
|
NC1 FLOPs: 36893488145287151616
|
|
% FLOPs sharded: 100.00
|
|
|
|
|
|
Shard dim: 2048, Number of dags: 23
|
|
Matmuls sharded with this dim:
|
|
[2048(s),2,2,2,2,128] @ [2,2,2,2,128,2,128] = [2048(s),2,128] Number of occurrences: 1
|
|
[2048(s),2,2,2,2,128] @ [2,2,2,2,128,2,2,2,64] = [2048(s),2,2,2,64] Number of occurrences: 1
|
|
[2048(s),2,2,2,2,128] @ [2,2,2,2,128,2,2,64] = [2048(s),2,2,64] Number of occurrences: 1
|
|
[64] @ [2048(s)] = [64,2048(s)] Number of occurrences: 1
|
|
|
|
|
|
Shard dim: 2, Number of dags: 1
|
|
Matmuls sharded with this dim:
|
|
[2048,2,2,128] @ [2,2,128,2(s),8,128] = [2048,2(s),8,128] (stationary-streaming swapped) Number of occurrences: 1
|
|
|
|
|
|
Shard dim: 256, Number of dags: 1
|
|
Matmuls sharded with this dim:
|
|
|
|
|
|
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]:
|
|
20 MACROS WITH LARGEST INSTRUCTION COUNTS:
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 768: matmul_128x128x512
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 768: matmul_128x128x512
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 768: matmul_128x128x512
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 256: matmul_128x128x512
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 256: matmul_128x128x512
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 128: matmul_128x128x512
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 128: matmul_128x128x512
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 64: rmsnorm128x512x128
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 64: simd128x512
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 64: rmsnorm128x512x128
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 48: simd128x512
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 32: transpose_128x128
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 32: transpose_128x128
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 32: transpose_128x128
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 32: generic_store128x128
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 32: generic_store128x128
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingBottleneck]: 16: rmsnorm128x512x128
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/InsertOffloadedTransposes]: OffloadedTranspose inserted: 0
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/InsertOffloadedTransposes]: Finished (changed=False)
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/InsertOffloadedTransposes]: InsertOffloadedTransposes finished after 0.100 seconds
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/DramToDramTranspose]: Running DramToDramTranspose
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/TilingProfiler]: TilingProfiler finished after 0.207 seconds
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/DramToDramTranspose]: Finished (changed=False)
|
|
2025-11-09T20:56:24Z INFO 748 [sg0000/Tensorizer/DelinearIndices]: Running DelinearIndices
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/DramToDramTranspose]: DramToDramTranspose finished after 0.100 seconds
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/PGLayoutTilingPipeline]: PGLayoutTilingPipeline finished after 11.393 seconds
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingProfiler]: Running TilingProfiler
|
|
2025-11-09T20:56:24Z INFO 748 [sg0000/Tensorizer/DelinearIndices]: Finished (changed=False)
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/FlattenMacroLoop]: Finished (changed=True)
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]:
|
|
20 MACROS WITH LARGEST INSTRUCTION COUNTS:
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 4768: transpose_128x128
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 4768: matmul_128x128x1
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 768: matmul_128x128x512
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 768: matmul_128x128x512
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 768: matmul_128x128x512
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 64: rmsnorm128x512x128
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 64: simd128x512
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 64: rmsnorm128x512x128
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 48: simd128x512
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 4: reduce512x1x1
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 4: simd1x512
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 4: reduce512x1x1
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 2: simd1x128
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 2: simd1x128
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 2: indirect_load128x1
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 2: simd1x128
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingBottleneck]: 2: simd1x128
|
|
2025-11-09T20:56:24Z INFO 748 [sg0000/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.024 seconds
|
|
2025-11-09T20:56:24Z INFO 748 [sg0000/Tensorizer/RemoveShardedPartitionAxes]: Running RemoveShardedPartitionAxes
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/TilingProfiler]: TilingProfiler finished after 0.115 seconds
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop
|
|
2025-11-09T20:56:24Z INFO 748 [sg0000/Tensorizer/RemoveShardedPartitionAxes]: Finished (changed=True)
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/FlattenMacroLoop]: Finished (changed=True)
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.115 seconds
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/InferNeuronTensor]: Running InferNeuronTensor
|
|
2025-11-09T20:56:24Z INFO 749 [sg0001/Tensorizer/InferNeuronTensor]: Running InferNeuronTensor_iteration_0
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.091 seconds
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/InferNeuronTensor]: Running InferNeuronTensor
|
|
2025-11-09T20:56:24Z INFO 750 [sg0002/Tensorizer/InferNeuronTensor]: Running InferNeuronTensor_iteration_0
|
|
2025-11-09T20:56:24Z INFO 748 [sg0000/Tensorizer/RemoveShardedPartitionAxes]: RemoveShardedPartitionAxes finished after 0.180 seconds
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/InferShardAxis]: Finished (changed=True)
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/InferShardAxis]: InferShardAxis finished after 2.713 seconds
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/MaskPropagation]: Running MaskPropagation
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/InferNeuronTensor]: InferNeuronTensor_iteration_0 finished after 0.378 seconds
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/InferNeuronTensor]: Running InferNeuronTensor_iteration_1
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/InferNeuronTensor]: InferNeuronTensor_iteration_1 finished after 0.003 seconds
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/InferNeuronTensor]: Finished (changed=True)
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/MaskPropagation]: Finished (changed=False)
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/InferNeuronTensor]: InferNeuronTensor finished after 0.384 seconds
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/MaskPropagation]: MaskPropagation finished after 0.014 seconds
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/CanonicalizeDAGForPGTiling]: Running CanonicalizeDAGForPGTiling
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/CanonicalizeDAGForPGTiling]: Finished (changed=False)
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/InferNeuronTensor]: InferNeuronTensor_iteration_0 finished after 0.316 seconds
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/InferNeuronTensor]: Running InferNeuronTensor_iteration_1
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/InferNeuronTensor]: InferNeuronTensor_iteration_1 finished after 0.002 seconds
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/InferNeuronTensor]: Finished (changed=True)
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.086 seconds
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/CanonicalizeDAGForPGTiling]: CanonicalizeDAGForPGTiling finished after 0.004 seconds
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/LowerCCOpBlockAxis]: Running LowerCCOpBlockAxis
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.098 seconds
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/LICM]: Finished (changed=True)
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/InferNeuronTensor]: InferNeuronTensor finished after 0.321 seconds
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/LowerCCOpBlockAxis]: Finished (changed=False)
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/LowerCCOpBlockAxis]: LowerCCOpBlockAxis finished after 0.018 seconds
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/PGTiling]: Running PGTiling
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: Running AGOrderingAnalysisPass
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.079 seconds
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.080 seconds
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/LICM]: LICM finished after 0.006 seconds
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/RewriteReplicationMatmul]: Running RewriteReplicationMatmul
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/RewriteReplicationMatmul]: Finished (changed=False)
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/RewriteReplicationMatmul]: RewriteReplicationMatmul finished after 0.004 seconds
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/LICM]: Finished (changed=True)
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/LICM]: LICM finished after 0.017 seconds
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/RewriteReplicationMatmul]: Running RewriteReplicationMatmul
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/RewriteReplicationMatmul]: Finished (changed=False)
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/RewriteReplicationMatmul]: RewriteReplicationMatmul finished after 0.067 seconds
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/FlattenMacroLoop]: Finished (changed=True)
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.082 seconds
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/SimplifyMacroPredicates]: Running SimplifyMacroPredicates
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/FlattenMacroLoop]: Finished (changed=True)
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/SimplifyMacroPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.013 seconds
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/SimplifyMacroPredicates]: Running SimplifyMacroPredicates
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/SimplifyMacroPredicates]: Finished (changed=True)
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/SimplifyMacroPredicates]: SimplifyMacroPredicates finished after 0.010 seconds
|
|
2025-11-09T20:56:25Z INFO 749 [sg0001/Tensorizer/DataLocalityOpt]: Running DataLocalityOpt
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 633 of IO tensor {'CrossPassTensor': ''}bfloat16 %input63|N|(128, 2, 2, 2, 2) is not sorted, index list (w/ AG ids): [(29, 'AG95'), (22, 'AG99'), (25, 'AG98'), (17, 'AG97'), (27, 'AG96')]
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 634 of IO tensor {'CrossPassTensor': ''}bfloat16 %input67|NC|(2, 128, 2, 2, 2, 2, 2, 2, 64) is not sorted, index list (w/ AG ids): [(22, 'AG99'), (29, 'AG95'), (25, 'AG98'), (17, 'AG97'), (27, 'AG96')]
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 635 of IO tensor {'CrossPassTensor': ''}bfloat16 %input66|N|(64, 2) is not sorted, index list (w/ AG ids): [(23, 'AG102'), (18, 'AG105')]
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 636 of IO tensor {'CrossPassTensor': ''}bfloat16 %input65|NC|(2, 128, 2, 2, 2, 2, 2, 64) is not sorted, index list (w/ AG ids): [(22, 'AG99'), (29, 'AG95'), (25, 'AG98'), (17, 'AG97'), (27, 'AG96')]
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 637 of IO tensor {'CrossPassTensor': ''}bfloat16 %input64|N|(64, 2) is not sorted, index list (w/ AG ids): [(23, 'AG102'), (19, 'AG108')]
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 638 of IO tensor {'CrossPassTensor': ''}bfloat16 %input62|NC|(2, 128, 2, 2, 2, 2, 128) is not sorted, index list (w/ AG ids): [(22, 'AG99'), (29, 'AG95'), (25, 'AG98'), (17, 'AG97'), (27, 'AG96')]
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: P dims of loadstore 419 of IO tensor {'CrossPassTensor': ''}bfloat16 %input61|NC|(2, 128, 2, 2, 8, 128) is not sorted, index list (w/ AG ids): [(26, 'AG114'), (21, 'AG116'), (24, 'AG115')]
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 631 of IO tensor non_local bfloat16 %all_gather.1(2, 2, 2, 2, 128, 2, 1024) is not sorted, index list (w/ AG ids): [(17, 'AG97'), (22, 'AG99'), (25, 'AG98'), (27, 'AG96'), (1, 'AG101'), (28, 'AG100')]
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 520 of IO tensor {'IntermediateTensor': ''}bfloat16 %intermediate0(2, 1024, 2, 2, 2, 2, 128) is not sorted, index list (w/ AG ids): [(1, 'AG101'), (28, 'AG100'), (22, 'AG99'), (25, 'AG98'), (17, 'AG97'), (27, 'AG96')]
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 582 of IO tensor non_local bfloat16 %reshape.16(2, 2, 2, 64, 2, 1024) is not sorted, index list (w/ AG ids): [(6, 'AG107'), (13, 'AG106'), (18, 'AG105'), (23, 'AG102'), (1, 'AG101')]
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 676 of IO tensor non_local bfloat16 %reshape.24(2, 2, 2, 64, 2, 1024) is not sorted, index list (w/ AG ids): [(7, 'AG109'), (14, 'AG110'), (19, 'AG108'), (23, 'AG102'), (1, 'AG101')]
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 614 of IO tensor non_local bfloat16 %reshape.29(2, 2, 2, 1024, 128) is not sorted, index list (w/ AG ids): [(8, 'AG112'), (15, 'AG113'), (1, 'AG101'), (20, 'AG111')]
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/SimplifyMacroPredicates]: SimplifyMacroPredicates finished after 0.072 seconds
|
|
2025-11-09T20:56:25Z INFO 750 [sg0002/Tensorizer/DataLocalityOpt]: Running DataLocalityOpt
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/AGOrderingAnalysisPass]: AGOrderingAnalysisPass finished after 0.205 seconds
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/StaticTransposeLocalTensor]: Running StaticTransposeLocalTensor
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/StaticTransposeLocalTensor]: Finished (changed=True)
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/StaticTransposeLocalTensor]: StaticTransposeLocalTensor finished after 0.078 seconds
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/PComputeCutting]: Running PComputeCutting
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/PComputeCutting]: Finished (changed=True)
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/PComputeCutting]: PComputeCutting finished after 0.011 seconds
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/BFComputeCutting]: Running BFComputeCutting
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/BFComputeCutting]: Finished (changed=True)
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/BFComputeCutting]: BFComputeCutting finished after 0.005 seconds
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/LoopSplitting]: Running LoopSplitting
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/LoopSplitting]: Finished (changed=False)
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/LoopSplitting]: LoopSplitting finished after 0.001 seconds
|
|
2025-11-09T20:56:25Z INFO 748 [sg0000/Tensorizer/MacroGeneration]: Running MacroGeneration
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/MacroGeneration]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/MacroGeneration]: MacroGeneration finished after 0.383 seconds
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/PGTiling]: PGTiling finished after 0.713 seconds
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InsertIOTransposes]: Running InsertIOTransposes
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/DataLocalityOpt]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/DataLocalityOpt]: DataLocalityOpt finished after 0.611 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/DMATilingProfiler]: Running DMATilingProfiler
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InsertIOTransposes]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]:
|
|
20 MACROS WITH LARGEST INSTRUCTION COUNTS:
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 4768: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 4768: matmul_128x128x1
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 768: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 768: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 768: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 298: transpose_128x1
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 64: rmsnorm128x512x128
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 64: simd128x512
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 64: rmsnorm128x512x128
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 48: simd128x512
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 32: dma128x1024
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 24: dma128x1024
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 12: dma128x2048
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 12: dma128x2048
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 4: reduce512x1x1
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 4: simd1x512
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PostDLOTilingBottleneck]: 4: reduce512x1x1
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/DMATilingProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InsertIOTransposes]: InsertIOTransposes finished after 0.115 seconds
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InsertOffloadedTransposes]: Running InsertOffloadedTransposes
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/DMATilingProfiler]: DMATilingProfiler finished after 0.007 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InsertOffloadedTransposes]: OffloadedTranspose inserted: 0
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InsertOffloadedTransposes]: Finished (changed=False)
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.081 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InsertOffloadedTransposes]: InsertOffloadedTransposes finished after 0.102 seconds
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/DramToDramTranspose]: Running DramToDramTranspose
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.083 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/LegalizeSundaMacro]: Running LegalizeSundaMacro
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/DramToDramTranspose]: Finished (changed=False)
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/DramToDramTranspose]: DramToDramTranspose finished after 0.018 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/LegalizeSundaMacro]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/PGLayoutTilingPipeline]: PGLayoutTilingPipeline finished after 16.909 seconds
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingProfiler]: Running TilingProfiler
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]:
|
|
20 MACROS WITH LARGEST INSTRUCTION COUNTS:
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 256: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 256: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 128: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 128: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 64: indirect_load128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 64: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 64: simd128x512
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 64: rmsnorm128x512x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 64: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 64: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 64: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 32: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 32: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 32: generic_store128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 32: generic_store128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 16: matmul_1x128x64
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 16: simd128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 16: simd128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingBottleneck]: 16: rmsnorm128x512x128
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/LegalizeSundaMacro]: LegalizeSundaMacro finished after 0.030 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/InsertImplicitShardAxisBeforeISel]: Running InsertImplicitShardAxisBeforeISel
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/TilingProfiler]: TilingProfiler finished after 0.020 seconds
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/DataLocalityOpt]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/FlattenMacroLoop]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/DataLocalityOpt]: DataLocalityOpt finished after 0.928 seconds
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/DMATilingProfiler]: Running DMATilingProfiler
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/InsertImplicitShardAxisBeforeISel]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]:
|
|
20 MACROS WITH LARGEST INSTRUCTION COUNTS:
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 768: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 768: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 768: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.087 seconds
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 256: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InferNeuronTensor]: Running InferNeuronTensor
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 256: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 128: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 128: matmul_128x128x512
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 64: rmsnorm128x512x128
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 64: simd128x512
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 64: rmsnorm128x512x128
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 64: dma128x128
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 48: simd128x512
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 32: dma128x1024
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 32: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 32: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 32: transpose_128x128
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InferNeuronTensor]: Running InferNeuronTensor_iteration_0
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/PostDLOTilingBottleneck]: 32: dma128x1024
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/DMATilingProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/DMATilingProfiler]: DMATilingProfiler finished after 0.013 seconds
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/InsertImplicitShardAxisBeforeISel]: InsertImplicitShardAxisBeforeISel finished after 0.102 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.021 seconds
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.034 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_1
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_1 finished after 0.074 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.035 seconds
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/LegalizeSundaMacro]: Running LegalizeSundaMacro
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.097 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PerfectLoopNest]: Running PerfectLoopNest
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PerfectLoopNest]: Finished (changed=False)
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/PerfectLoopNest]: PerfectLoopNest finished after 0.004 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InferNeuronTensor]: InferNeuronTensor_iteration_0 finished after 0.286 seconds
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InferNeuronTensor]: Running InferNeuronTensor_iteration_1
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InferNeuronTensor]: InferNeuronTensor_iteration_1 finished after 0.003 seconds
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InferNeuronTensor]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/FlattenMacroLoop]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/InferNeuronTensor]: InferNeuronTensor finished after 0.291 seconds
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/LegalizeSundaMacro]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.089 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/RewriteWeights]: Running RewriteWeights
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/LegalizeSundaMacro]: LegalizeSundaMacro finished after 0.123 seconds
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/InsertImplicitShardAxisBeforeISel]: Running InsertImplicitShardAxisBeforeISel
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.091 seconds
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/RewriteWeights]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.092 seconds
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:26Z INFO 748 [sg0000/Tensorizer/LICM]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 749 [sg0001/Tensorizer/InsertImplicitShardAxisBeforeISel]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/RewriteWeights]: RewriteWeights finished after 0.018 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/ReshapeWeights]: Running ReshapeWeights
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/ReshapeWeights]: Finished (changed=True)
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/ReshapeWeights]: ReshapeWeights finished after 0.002 seconds
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop
|
|
2025-11-09T20:56:26Z INFO 750 [sg0002/Tensorizer/FlattenMacroLoop]: Finished (changed=False)
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/InsertImplicitShardAxisBeforeISel]: InsertImplicitShardAxisBeforeISel finished after 0.022 seconds
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/LICM]: LICM finished after 0.005 seconds
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/RewriteReplicationMatmul]: Running RewriteReplicationMatmul
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/RewriteReplicationMatmul]: Finished (changed=False)
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/RewriteReplicationMatmul]: RewriteReplicationMatmul finished after 0.003 seconds
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/FlattenMacroLoop]: Finished (changed=True)
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.005 seconds
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/SimplifyMacroPredicates]: Running SimplifyMacroPredicates
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.113 seconds
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.011 seconds
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/SimplifyMacroPredicates]: Running SimplifyMacroPredicates
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.115 seconds
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/PerfectLoopNest]: Running PerfectLoopNest
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/PerfectLoopNest]: Finished (changed=False)
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/SimplifyMacroPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/SimplifyMacroPredicates]: Finished (changed=True)
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/PerfectLoopNest]: PerfectLoopNest finished after 0.005 seconds
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/SimplifyMacroPredicates]: SimplifyMacroPredicates finished after 0.008 seconds
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/DataLocalityOpt]: Running DataLocalityOpt
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/SimplifyMacroPredicates]: SimplifyMacroPredicates finished after 0.025 seconds
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/InferInitValue]: Running InferInitValue
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/FlattenMacroLoop]: Finished (changed=True)
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.100 seconds
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/RewriteWeights]: Running RewriteWeights
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/RewriteWeights]: Finished (changed=True)
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/RewriteWeights]: RewriteWeights finished after 0.008 seconds
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/ReshapeWeights]: Running ReshapeWeights
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/ReshapeWeights]: Finished (changed=True)
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/ReshapeWeights]: ReshapeWeights finished after 0.001 seconds
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/FlattenMacroLoop]: Finished (changed=True)
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/InferInitValue]: Finished (changed=True)
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.016 seconds
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/SimplifyMacroPredicates]: Running SimplifyMacroPredicates
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/InferInitValue]: InferInitValue finished after 0.131 seconds
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/SimplifyMacroPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/SimplifyMacroPredicates]: SimplifyMacroPredicates finished after 0.018 seconds
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/InferInitValue]: Running InferInitValue
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.021 seconds
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.022 seconds
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/SimplifyTensor]: Running SimplifyTensor
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/SimplifyTensor]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/SimplifyTensor]: DeadCodeElimination_iteration_0 finished after 0.006 seconds
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/SimplifyTensor]: Finished (changed=True)
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/SimplifyTensor]: SimplifyTensor finished after 0.091 seconds
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/LICM]: Finished (changed=True)
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/LICM]: LICM finished after 0.007 seconds
|
|
2025-11-09T20:56:27Z INFO 750 [sg0002/Tensorizer/SundaISel]: Running SundaISel
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/InferInitValue]: Finished (changed=True)
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/InferInitValue]: InferInitValue finished after 0.289 seconds
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/DataLocalityOpt]: Finished (changed=True)
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.107 seconds
|
|
2025-11-09T20:56:27Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/DataLocalityOpt]: DataLocalityOpt finished after 0.699 seconds
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/DMATilingProfiler]: Running DMATilingProfiler
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]:
|
|
20 MACROS WITH LARGEST INSTRUCTION COUNTS:
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 256: transpose_128x128
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 256: matmul_128x128x512
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 256: matmul_128x128x512
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 128: matmul_128x128x512
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 128: matmul_128x128x512
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 64: indirect_load128x128
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 64: transpose_128x128
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 64: dma128x512
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 64: dma128x512
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 64: rmsnorm128x512x128
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 64: transpose_128x128
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 64: transpose_128x128
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 64: transpose_128x128
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 64: dma128x128
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 32: transpose_128x128
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 32: transpose_128x128
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 32: dma128x1024
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 32: generic_store128x128
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 32: generic_store128x128
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 16: dma128x1
|
|
2025-11-09T20:56:27Z INFO 748 [sg0000/Tensorizer/DMATilingProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/DMATilingProfiler]: DMATilingProfiler finished after 0.016 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/SundaISel]: Finished (changed=True)
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/SundaISel]: SundaISel finished after 0.369 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronAliasDependencyReset]: Running NeuronAliasDependencyReset
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/AliasDependencyElimination]: Running AliasDependencyElimination
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/AliasDependencyElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/AliasDependencyElimination]: AliasDependencyElimination finished after 0.000 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronAliasDependencyInduction]: Running NeuronAliasDependencyInduction
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronAliasDependencyInduction]: Finished (changed=False)
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronAliasDependencyInduction]: NeuronAliasDependencyInduction finished after 0.001 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronAliasDependencyReset]: NeuronAliasDependencyReset finished after 0.011 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/LowerComplexBroadcast]: Running LowerComplexBroadcast
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.109 seconds
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/SimplifyTensor]: Running SimplifyTensor
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/LowerComplexBroadcast]: Finished (changed=False)
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/LowerComplexBroadcast]: LowerComplexBroadcast finished after 0.082 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopInterchange]: Running NeuronLoopInterchange
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopInterchange]: Finished (changed=True)
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.112 seconds
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopInterchange]: NeuronLoopInterchange finished after 0.007 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/SimplifyTensor]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/SimplifyTensor]: DeadCodeElimination_iteration_0 finished after 0.005 seconds
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.122 seconds
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/LegalizeSundaMacro]: Running LegalizeSundaMacro
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/SimplifyTensor]: Finished (changed=True)
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/SimplifyTensor]: SimplifyTensor finished after 0.182 seconds
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.087 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion_iteration_0
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/LICM]: Finished (changed=False)
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/LICM]: LICM finished after 0.017 seconds
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/SundaISel]: Running SundaISel
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/LegalizeSundaMacro]: Finished (changed=True)
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion_iteration_0 finished after 0.182 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion_iteration_1
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/LegalizeSundaMacro]: LegalizeSundaMacro finished after 0.122 seconds
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/InsertImplicitShardAxisBeforeISel]: Running InsertImplicitShardAxisBeforeISel
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion_iteration_1 finished after 0.012 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion_iteration_2
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion_iteration_2 finished after 0.010 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion_iteration_3
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/InsertImplicitShardAxisBeforeISel]: Finished (changed=True)
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion_iteration_3 finished after 0.072 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/InsertImplicitShardAxisBeforeISel]: InsertImplicitShardAxisBeforeISel finished after 0.024 seconds
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion finished after 0.281 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopInterchange]: Running NeuronLoopInterchange
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopInterchange]: Finished (changed=False)
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.094 seconds
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLoopInterchange]: NeuronLoopInterchange finished after 0.006 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.098 seconds
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/PerfectLoopNest]: Running PerfectLoopNest
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/PerfectLoopNest]: Finished (changed=False)
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/PerfectLoopNest]: PerfectLoopNest finished after 0.010 seconds
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLICM]: Finished (changed=True)
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.108 seconds
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/FlattenMacroLoop]: Finished (changed=True)
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.094 seconds
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/RewriteWeights]: Running RewriteWeights
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/SundaISel]: Finished (changed=True)
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/FactorizeBlkDims]: Finished (changed=True)
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/SundaISel]: SundaISel finished after 0.533 seconds
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/NeuronAliasDependencyReset]: Running NeuronAliasDependencyReset
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/AliasDependencyElimination]: Running AliasDependencyElimination
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/AliasDependencyElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.113 seconds
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/RewriteWeights]: Finished (changed=True)
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:28Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/AliasDependencyElimination]: AliasDependencyElimination finished after 0.001 seconds
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/NeuronAliasDependencyInduction]: Running NeuronAliasDependencyInduction
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/RewriteWeights]: RewriteWeights finished after 0.109 seconds
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/ReshapeWeights]: Running ReshapeWeights
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/ReshapeWeights]: Finished (changed=True)
|
|
2025-11-09T20:56:28Z INFO 749 [sg0001/Tensorizer/NeuronAliasDependencyInduction]: Finished (changed=False)
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/ReshapeWeights]: ReshapeWeights finished after 0.003 seconds
|
|
2025-11-09T20:56:28Z INFO 748 [sg0000/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronAliasDependencyInduction]: NeuronAliasDependencyInduction finished after 0.010 seconds
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronAliasDependencyReset]: NeuronAliasDependencyReset finished after 0.097 seconds
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/LowerComplexBroadcast]: Running LowerComplexBroadcast
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/FlattenMacroLoop]: Finished (changed=True)
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.081 seconds
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/SimplifyMacroPredicates]: Running SimplifyMacroPredicates
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/LowerComplexBroadcast]: Finished (changed=False)
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/LowerComplexBroadcast]: LowerComplexBroadcast finished after 0.012 seconds
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopInterchange]: Running NeuronLoopInterchange
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopInterchange]: Finished (changed=True)
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopInterchange]: NeuronLoopInterchange finished after 0.008 seconds
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/SimplifyMacroPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/SimplifyMacroPredicates]: SimplifyMacroPredicates finished after 0.091 seconds
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/InferInitValue]: Running InferInitValue
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.219 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_1
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_1 finished after 0.005 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: Finished (changed=True)
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.034 seconds
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion_iteration_0
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.228 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronValueNumbering]: Finished (changed=False)
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.009 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.022 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_1
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_1 finished after 0.004 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: Finished (changed=True)
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.027 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/InferInitValue]: Finished (changed=True)
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/InferInitValue]: InferInitValue finished after 0.305 seconds
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion_iteration_0 finished after 0.290 seconds
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion_iteration_1
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.097 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/VectorizeDMA]: Running VectorizeDMA
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/VectorizeDMA]: Running VectorizeDMA_iteration_0
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion_iteration_1 finished after 0.027 seconds
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion_iteration_2
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.111 seconds
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: Finished (changed=False)
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/VectorizeDMA]: VectorizeDMA_iteration_0 finished after 0.086 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/VectorizeDMA]: Finished (changed=False)
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.114 seconds
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/SimplifyTensor]: Running SimplifyTensor
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion_iteration_2 finished after 0.083 seconds
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/VectorizeDMA]: VectorizeDMA finished after 0.087 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/SimplifyTensor]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.006 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/LegalizePartitionReduce]: Running LegalizePartitionReduce
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/LegalizePartitionReduce]: Finished (changed=False)
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/SimplifyTensor]: DeadCodeElimination_iteration_0 finished after 0.005 seconds
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/SimplifyTensor]: Finished (changed=True)
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/LegalizePartitionReduce]: LegalizePartitionReduce finished after 0.003 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/DeConcat]: Running DeConcat
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/DeConcat]: Running DeConcat_iteration_0
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion finished after 0.408 seconds
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopInterchange]: Running NeuronLoopInterchange
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/SimplifyTensor]: SimplifyTensor finished after 0.095 seconds
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopInterchange]: Finished (changed=False)
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/LICM]: Running LICM
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/DeConcat]: DeConcat_iteration_0 finished after 0.012 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/DeConcat]: Finished (changed=False)
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/LICM]: Finished (changed=False)
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/DeConcat]: DeConcat finished after 0.013 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/FactorizeThreadAxesInFreeDims]: Running FactorizeThreadAxesInFreeDims
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/FactorizeThreadAxesInFreeDims]: Finished (changed=False)
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/LICM]: LICM finished after 0.086 seconds
|
|
2025-11-09T20:56:29Z INFO 748 [sg0000/Tensorizer/SundaISel]: Running SundaISel
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/FactorizeThreadAxesInFreeDims]: FactorizeThreadAxesInFreeDims finished after 0.007 seconds
|
|
2025-11-09T20:56:29Z INFO 750 [sg0002/Tensorizer/PartialSimdFusion]: Running PartialSimdFusion
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLoopInterchange]: NeuronLoopInterchange finished after 0.005 seconds
|
|
2025-11-09T20:56:29Z INFO 749 [sg0001/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:30Z INFO 750 [sg0002/Tensorizer/PartialSimdFusion]: Running PartialSimdFusion_iteration_0
|
|
2025-11-09T20:56:30Z INFO 749 [sg0001/Tensorizer/NeuronLICM]: Finished (changed=True)
|
|
2025-11-09T20:56:30Z INFO 749 [sg0001/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.104 seconds
|
|
2025-11-09T20:56:30Z INFO 749 [sg0001/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims
|
|
2025-11-09T20:56:30Z INFO 750 [sg0002/Tensorizer/PartialSimdFusion]: PartialSimdFusion_iteration_0 finished after 0.107 seconds
|
|
2025-11-09T20:56:30Z INFO 750 [sg0002/Tensorizer/PartialSimdFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:30Z INFO 750 [sg0002/Tensorizer/PartialSimdFusion]: PartialSimdFusion finished after 0.183 seconds
|
|
2025-11-09T20:56:30Z INFO 750 [sg0002/Tensorizer/TritiumFusion]: Running TritiumFusion
|
|
2025-11-09T20:56:30Z INFO 749 [sg0001/Tensorizer/FactorizeBlkDims]: Finished (changed=True)
|
|
2025-11-09T20:56:30Z INFO 749 [sg0001/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.237 seconds
|
|
2025-11-09T20:56:30Z INFO 749 [sg0001/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/SundaISel]: Finished (changed=True)
|
|
2025-11-09T20:56:30Z INFO 749 [sg0001/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:30Z INFO 750 [sg0002/Tensorizer/TritiumFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/SundaISel]: SundaISel finished after 0.612 seconds
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/NeuronAliasDependencyReset]: Running NeuronAliasDependencyReset
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/AliasDependencyElimination]: Running AliasDependencyElimination
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/AliasDependencyElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/AliasDependencyElimination]: AliasDependencyElimination finished after 0.001 seconds
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/NeuronAliasDependencyInduction]: Running NeuronAliasDependencyInduction
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/NeuronAliasDependencyInduction]: Finished (changed=False)
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/NeuronAliasDependencyInduction]: NeuronAliasDependencyInduction finished after 0.003 seconds
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/NeuronAliasDependencyReset]: NeuronAliasDependencyReset finished after 0.105 seconds
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/LowerComplexBroadcast]: Running LowerComplexBroadcast
|
|
2025-11-09T20:56:30Z INFO 750 [sg0002/Tensorizer/TritiumFusion]: TritiumFusion finished after 0.409 seconds
|
|
2025-11-09T20:56:30Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: Running CCOpFusion
|
|
2025-11-09T20:56:30Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: Running CCOpFusion_iteration_0
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/LowerComplexBroadcast]: Finished (changed=False)
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/LowerComplexBroadcast]: LowerComplexBroadcast finished after 0.105 seconds
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/NeuronLoopInterchange]: Running NeuronLoopInterchange
|
|
2025-11-09T20:56:30Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: CCOpFusion_iteration_0 finished after 0.161 seconds
|
|
2025-11-09T20:56:30Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: Finished (changed=False)
|
|
2025-11-09T20:56:30Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: CCOpFusion finished after 0.163 seconds
|
|
2025-11-09T20:56:30Z INFO 750 [sg0002/Tensorizer/VectorizeMatMult]: Running VectorizeMatMult
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/NeuronLoopInterchange]: Finished (changed=True)
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/NeuronLoopInterchange]: NeuronLoopInterchange finished after 0.029 seconds
|
|
2025-11-09T20:56:30Z INFO 748 [sg0000/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/VectorizeMatMult]: Finished (changed=False)
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/VectorizeMatMult]: VectorizeMatMult finished after 0.091 seconds
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/PartialLoopFusion]: Running PartialLoopFusion
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/PartialLoopFusion]: Running PartialLoopFusion_iteration_0
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.521 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_1
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.081 seconds
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion_iteration_0
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_1 finished after 0.077 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronInstComb]: Finished (changed=True)
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.700 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/PartialLoopFusion]: PartialLoopFusion_iteration_0 finished after 0.189 seconds
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/PartialLoopFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronValueNumbering]: Finished (changed=True)
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/PartialLoopFusion]: PartialLoopFusion finished after 0.191 seconds
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.090 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion_iteration_0 finished after 0.123 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion_iteration_1
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.010 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/NeuronLICM]: Finished (changed=True)
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion_iteration_1 finished after 0.078 seconds
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronLoopFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.012 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion finished after 0.204 seconds
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronLoopInterchange]: Running NeuronLoopInterchange
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronLoopInterchange]: Finished (changed=False)
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.015 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/VectorizeDMA]: Running VectorizeDMA
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/VectorizeDMA]: Running VectorizeDMA_iteration_0
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/VectorizeDMA]: VectorizeDMA_iteration_0 finished after 0.003 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/VectorizeDMA]: Finished (changed=False)
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronLoopInterchange]: NeuronLoopInterchange finished after 0.005 seconds
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/VectorizeDMA]: VectorizeDMA finished after 0.004 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronLICM]: Finished (changed=True)
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.010 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/LegalizePartitionReduce]: Running LegalizePartitionReduce
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/LegalizePartitionReduce]: Finished (changed=False)
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.079 seconds
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/LegalizePartitionReduce]: LegalizePartitionReduce finished after 0.003 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/DeConcat]: Running DeConcat
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/DeConcat]: Running DeConcat_iteration_0
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/DeConcat]: DeConcat_iteration_0 finished after 0.004 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/DeConcat]: Finished (changed=False)
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/DeConcat]: DeConcat finished after 0.005 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/FactorizeThreadAxesInFreeDims]: Running FactorizeThreadAxesInFreeDims
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.077 seconds
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/LowerTranspose]: Running LowerTranspose
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/FactorizeThreadAxesInFreeDims]: Finished (changed=False)
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/FactorizeThreadAxesInFreeDims]: FactorizeThreadAxesInFreeDims finished after 0.013 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/PartialSimdFusion]: Running PartialSimdFusion
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/PartialSimdFusion]: Running PartialSimdFusion_iteration_0
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/FactorizeBlkDims]: Finished (changed=True)
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.185 seconds
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/LowerTranspose]: Finished (changed=True)
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.101 seconds
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/LowerBroadcast]: Running LowerBroadcast
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/LowerBroadcast]: Finished (changed=False)
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.081 seconds
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.019 seconds
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_1
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_1 finished after 0.062 seconds
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/LateNeuronInstComb]: Finished (changed=True)
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.084 seconds
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/SplitAccGrp]: Running SplitAccGrp
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/SplitAccGrp]: Finished (changed=False)
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.216 seconds
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_1
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/SplitAccGrp]: SplitAccGrp finished after 0.011 seconds
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/SpillPSum]: Running SpillPSum
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_1 finished after 0.017 seconds
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronInstComb]: Finished (changed=True)
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/PartialSimdFusion]: PartialSimdFusion_iteration_0 finished after 0.391 seconds
|
|
2025-11-09T20:56:31Z INFO 749 [sg0001/Tensorizer/PartialSimdFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.306 seconds
|
|
2025-11-09T20:56:31Z INFO 748 [sg0000/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering
|
|
2025-11-09T20:56:31Z INFO 750 [sg0002/Tensorizer/SpillPSum]: Finished (changed=True)
|
|
2025-11-09T20:56:32Z INFO 749 [sg0001/Tensorizer/PartialSimdFusion]: PartialSimdFusion finished after 0.394 seconds
|
|
2025-11-09T20:56:32Z INFO 749 [sg0001/Tensorizer/TritiumFusion]: Running TritiumFusion
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/NeuronValueNumbering]: Finished (changed=True)
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.075 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.010 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/NeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/SpillPSum]: SpillPSum finished after 0.038 seconds
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.011 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.009 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/VectorizeDMA]: Running VectorizeDMA
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/VectorizeDMA]: Running VectorizeDMA_iteration_0
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/VectorizeDMA]: VectorizeDMA_iteration_0 finished after 0.012 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/VectorizeDMA]: Running VectorizeDMA_iteration_1
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/VectorizeDMA]: VectorizeDMA_iteration_1 finished after 0.003 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/VectorizeDMA]: Finished (changed=True)
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/VectorizeDMA]: VectorizeDMA finished after 0.016 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/LowerIntrinsics]: Finished (changed=True)
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.006 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/LegalizePartitionReduce]: Running LegalizePartitionReduce
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.206 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/LegalizePartitionReduce]: Finished (changed=False)
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/InlineNativeKernels]: Running InlineNativeKernels
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/LegalizePartitionReduce]: LegalizePartitionReduce finished after 0.003 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/DeConcat]: Running DeConcat
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/DeConcat]: Running DeConcat_iteration_0
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/DeConcat]: DeConcat_iteration_0 finished after 0.009 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/DeConcat]: Finished (changed=False)
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/InlineNativeKernels]: Finished (changed=False)
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/DeConcat]: DeConcat finished after 0.010 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/FactorizeThreadAxesInFreeDims]: Running FactorizeThreadAxesInFreeDims
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/InlineNativeKernels]: InlineNativeKernels finished after 0.018 seconds
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/LegalizeType]: Running LegalizeType
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/FactorizeThreadAxesInFreeDims]: Finished (changed=False)
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/LegalizeType]: Finished (changed=True)
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/FactorizeThreadAxesInFreeDims]: FactorizeThreadAxesInFreeDims finished after 0.099 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/PartialSimdFusion]: Running PartialSimdFusion
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/PartialSimdFusion]: Running PartialSimdFusion_iteration_0
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/LegalizeType]: LegalizeType finished after 0.097 seconds
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/NeuronLICM]: Finished (changed=True)
|
|
2025-11-09T20:56:32Z INFO 749 [sg0001/Tensorizer/TritiumFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.099 seconds
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/InferPSumTensor]: Running InferPSumTensor
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0
|
|
2025-11-09T20:56:32Z INFO 749 [sg0001/Tensorizer/TritiumFusion]: TritiumFusion finished after 0.624 seconds
|
|
2025-11-09T20:56:32Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: Running CCOpFusion
|
|
2025-11-09T20:56:32Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: Running CCOpFusion_iteration_0
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 0.108 seconds
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_1
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/PartialSimdFusion]: PartialSimdFusion_iteration_0 finished after 0.314 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/PartialSimdFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/PartialSimdFusion]: PartialSimdFusion finished after 0.316 seconds
|
|
2025-11-09T20:56:32Z INFO 748 [sg0000/Tensorizer/TritiumFusion]: Running TritiumFusion
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_1 finished after 0.091 seconds
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/InferPSumTensor]: Finished (changed=True)
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 0.201 seconds
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/WeightCoalescing]: Running WeightCoalescing
|
|
2025-11-09T20:56:32Z INFO 750 [sg0002/Tensorizer/WeightCoalescing]: Finished (changed=False)
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.005 seconds
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess
|
|
2025-11-09T20:56:33Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: CCOpFusion_iteration_0 finished after 0.299 seconds
|
|
2025-11-09T20:56:33Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:33Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: CCOpFusion finished after 0.303 seconds
|
|
2025-11-09T20:56:33Z INFO 749 [sg0001/Tensorizer/VectorizeMatMult]: Running VectorizeMatMult
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/LegalizeSundaAccess]: Finished (changed=False)
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.211 seconds
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/TritiumFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/RelaxPredicates]: Running RelaxPredicates
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/TritiumFusion]: TritiumFusion finished after 0.396 seconds
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: Running CCOpFusion
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: Running CCOpFusion_iteration_0
|
|
2025-11-09T20:56:33Z INFO 749 [sg0001/Tensorizer/VectorizeMatMult]: Finished (changed=False)
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/RelaxPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/RelaxPredicates]: RelaxPredicates finished after 0.186 seconds
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/TensorInitialization]: Running TensorInitialization
|
|
2025-11-09T20:56:33Z INFO 749 [sg0001/Tensorizer/VectorizeMatMult]: VectorizeMatMult finished after 0.291 seconds
|
|
2025-11-09T20:56:33Z INFO 749 [sg0001/Tensorizer/PartialLoopFusion]: Running PartialLoopFusion
|
|
2025-11-09T20:56:33Z INFO 749 [sg0001/Tensorizer/PartialLoopFusion]: Running PartialLoopFusion_iteration_0
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: CCOpFusion_iteration_0 finished after 0.117 seconds
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: CCOpFusion finished after 0.121 seconds
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/VectorizeMatMult]: Running VectorizeMatMult
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/TensorInitialization]: Finished (changed=True)
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/TensorInitialization]: TensorInitialization finished after 0.107 seconds
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/VectorizeMatMult]: Finished (changed=False)
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/VectorizeMatMult]: VectorizeMatMult finished after 0.195 seconds
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/PartialLoopFusion]: Running PartialLoopFusion
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/PartialLoopFusion]: Running PartialLoopFusion_iteration_0
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.101 seconds
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro
|
|
2025-11-09T20:56:33Z INFO 749 [sg0001/Tensorizer/PartialLoopFusion]: PartialLoopFusion_iteration_0 finished after 0.300 seconds
|
|
2025-11-09T20:56:33Z INFO 749 [sg0001/Tensorizer/PartialLoopFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:33Z INFO 749 [sg0001/Tensorizer/PartialLoopFusion]: PartialLoopFusion finished after 0.305 seconds
|
|
2025-11-09T20:56:33Z INFO 749 [sg0001/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/ExpandISAMacro]: Finished (changed=False)
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.090 seconds
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/PartialLoopFusion]: PartialLoopFusion_iteration_0 finished after 0.209 seconds
|
|
2025-11-09T20:56:33Z INFO 749 [sg0001/Tensorizer/NeuronLICM]: Finished (changed=False)
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/PartialLoopFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/PartialLoopFusion]: PartialLoopFusion finished after 0.211 seconds
|
|
2025-11-09T20:56:33Z INFO 748 [sg0000/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:33Z INFO 750 [sg0002/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.005 seconds
|
|
2025-11-09T20:56:34Z INFO 750 [sg0002/Tensorizer/SimplifyNeuronTensor]: Finished (changed=True)
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/NeuronLICM]: Finished (changed=False)
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.112 seconds
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/LowerTranspose]: Running LowerTranspose
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.078 seconds
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LowerTranspose]: Running LowerTranspose
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LowerTranspose]: Finished (changed=True)
|
|
2025-11-09T20:56:34Z INFO 750 [sg0002/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.188 seconds
|
|
2025-11-09T20:56:34Z INFO 750 [sg0002/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/LowerTranspose]: Finished (changed=True)
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.104 seconds
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/LowerBroadcast]: Running LowerBroadcast
|
|
2025-11-09T20:56:34Z INFO 750 [sg0002/Tensorizer/DMALocalityOpt]: Finished (changed=True)
|
|
2025-11-09T20:56:34Z INFO 750 [sg0002/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.004 seconds
|
|
2025-11-09T20:56:34Z INFO 750 [sg0002/Tensorizer/DataStreaming]: Running DataStreaming
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/LowerBroadcast]: Finished (changed=False)
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.006 seconds
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb
|
|
2025-11-09T20:56:34Z INFO 750 [sg0002/Tensorizer/DataStreaming]: Finished (changed=True)
|
|
2025-11-09T20:56:34Z INFO 750 [sg0002/Tensorizer/DataStreaming]: DataStreaming finished after 0.011 seconds
|
|
2025-11-09T20:56:34Z INFO 750 [sg0002/Tensorizer/SFKVectorizer]: Running SFKVectorizer
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.089 seconds
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LowerBroadcast]: Running LowerBroadcast
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.026 seconds
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/LateNeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.097 seconds
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/SplitAccGrp]: Running SplitAccGrp
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LowerBroadcast]: Finished (changed=False)
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.010 seconds
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/SplitAccGrp]: Finished (changed=False)
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/SplitAccGrp]: SplitAccGrp finished after 0.084 seconds
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/SpillPSum]: Running SpillPSum
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.027 seconds
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_1
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_1 finished after 0.005 seconds
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LateNeuronInstComb]: Finished (changed=True)
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.035 seconds
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/SplitAccGrp]: Running SplitAccGrp
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/SplitAccGrp]: Finished (changed=False)
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/SplitAccGrp]: SplitAccGrp finished after 0.013 seconds
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/SpillPSum]: Running SpillPSum
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/SpillPSum]: Finished (changed=True)
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/SpillPSum]: SpillPSum finished after 0.198 seconds
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/SpillPSum]: Finished (changed=True)
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/SpillPSum]: SpillPSum finished after 0.118 seconds
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics
|
|
2025-11-09T20:56:34Z INFO 750 [sg0002/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0
|
|
2025-11-09T20:56:34Z INFO 749 [sg0001/Tensorizer/LowerIntrinsics]: Finished (changed=True)
|
|
2025-11-09T20:56:34Z INFO 748 [sg0000/Tensorizer/LowerIntrinsics]: Finished (changed=True)
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.399 seconds
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/InlineNativeKernels]: Running InlineNativeKernels
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.328 seconds
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/InlineNativeKernels]: Running InlineNativeKernels
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/InlineNativeKernels]: Finished (changed=False)
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/InlineNativeKernels]: Finished (changed=False)
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/InlineNativeKernels]: InlineNativeKernels finished after 0.013 seconds
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/LegalizeType]: Running LegalizeType
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 0.279 seconds
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_1
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_1 finished after 0.011 seconds
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/InlineNativeKernels]: InlineNativeKernels finished after 0.005 seconds
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/LegalizeType]: Running LegalizeType
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/SFKVectorizer]: Finished (changed=True)
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/LegalizeType]: Finished (changed=True)
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/LegalizeType]: Finished (changed=True)
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/LegalizeType]: LegalizeType finished after 0.027 seconds
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/LegalizeType]: LegalizeType finished after 0.017 seconds
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/NeuronLICM]: Finished (changed=True)
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 0.993 seconds
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.089 seconds
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/InferPSumTensor]: Running InferPSumTensor
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/LateLegalizeInst]: Finished (changed=False)
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.092 seconds
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/NeuronLICM]: Finished (changed=True)
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.123 seconds
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/InferPSumTensor]: Running InferPSumTensor
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/CoalesceCCOp]: Finished (changed=True)
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.085 seconds
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/SimpleAllReduceTiling]: Finished (changed=True)
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.008 seconds
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/InsertCoreBarrier]: Finished (changed=True)
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.021 seconds
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: Running DMAProfiler
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 0.218 seconds
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_1
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs:
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: Est. DMA time: 772.293us (152.000MiB, est bw: 206.377GB/s, 52.057% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[2] bfloat16 (2, 149, 128, 2048) %'986.1572'[i31_0,4i31_1_0_0+i31_1_0_1,i0.128,i1.128+128i2.16] = load bfloat16<128 x 2048> {'CrossPassTensor': ''}bfloat16 (2, 18992, 16, 128) %'input369'[i31_0,i0.128+512i31_1_0_0+128i31_1_0_1,i2.16,i1.128] # id=1571, src_id=None, , instances=304 # dl = tensor_op_name: input369_pftranspose_986 | hlo_id: 95 | if -i0.128-512i31_1_0_0-128i31_1_0_1+18991 >= 0 and -4i31_1_0_0-i31_1_0_1+148 >= 0 [[i0.128];[i1.128, i2.16]] -> [[i0.128];[i1.128, i2.16]]
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: Est. DMA time: 148.113us (24.000MiB, est bw: 169.910GB/s, 9.984% of tot. time) for bfloat16<128 x 1024> TongaSB partitions[6] bfloat16 (2, 2, 2, 2, 2, 3, 128, 1024) %1513[i16_0_1068,i16_1_0_0_1068,i15_0_0_1,i15_0_0_0_2012,c1_1056_2012,c2_1057_2012,i0.128,i1.1024] = load bfloat16<128 x 1024> {'CrossPassTensor': ''}bfloat16 (4, 2, 128, 3, 1024) %'input365'[i15_0_0_1+2i15_0_0_0_2012,c1_1056_2012,i0.128,c2_1057_2012,i1.1024] # id=1368, src_id=None, , instances=96 # dl = tensor_op_name: _dot.199 | hlo_id: 63 | [[i0.128];[i1.1024]] -> [[i0.128];[i1.1024]]
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: Est. DMA time: 123.036us (24.000MiB, est bw: 204.541GB/s, 8.293% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[5] bfloat16 (2, 2, 3, 2, 2, 128, 2048) %1510[i16_0_1068,i16_1_0_0_1068,i10_0_0_1,i10_0_0_0,c2_1035,i0.128,i1.2048] = load bfloat16<128 x 2048> {'CrossPassTensor': ''}bfloat16 (2, 3, 128, 2, 2048) %'input366'[i10_0_0_0,i10_0_0_1,i0.128,c2_1035,i1.2048] # id=1359, src_id=None, , instances=48 # dl = tensor_op_name: _dot.197 | hlo_id: 52 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: Est. DMA time: 123.036us (24.000MiB, est bw: 204.541GB/s, 8.293% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[5] bfloat16 (2, 2, 3, 2, 2, 128, 2048) %1511[i16_0_1068,i16_1_0_0_1068,i12_0_0_1,i12_0_0_0,c2_1046,i0.128,i1.2048] = load bfloat16<128 x 2048> {'CrossPassTensor': ''}bfloat16 (2, 3, 128, 2, 2048) %'input368'[i12_0_0_0,i12_0_0_1,i0.128,c2_1046,i1.2048] # id=1362, src_id=None, , instances=48 # dl = tensor_op_name: _dot.198 | hlo_id: 42 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: Est. DMA time: 98.799us (152.000KiB, est bw: 1.575GB/s, 6.660% of tot. time) for float32<1 x 128> non_local float32 (1, 2, 18992) %'convert.55'[0,i31_0,i0.128+512i31_1_0_0+128i31_1_0_1] = store float32<1 x 128> TongaSB partitions[2] float32 (2, 149, 1, 128) %'dot.200.1582'[i31_0,4i31_1_0_0+i31_1_0_1,0,i0.128] # id=1580, src_id=None, , instances=304 # dl = tensor_op_name: _dot.200 | hlo_id: 95 | if -i0.128-512i31_1_0_0-128i31_1_0_1+18991 >= 0 and -4i31_1_0_0-i31_1_0_1+148 >= 0 [[];[i0.128]] -> [[];[i0.128]]
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: Est. DMA time: 41.879us (8.000MiB, est bw: 200.308GB/s, 2.823% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[3] bfloat16 (2, 2, 4, 128, 2048) %'990.1656'[i16_0_1068,i16_1_0_0_1068,T_i2_0_2013,i0.128,i1.2048] = load bfloat16<128 x 2048> non_local bfloat16 (2, 2, 512, 2048) %'add.9'[i16_0_1068,i16_1_0_0_1068,i0.128+128T_i2_0_2013,i1.2048] # id=1546, src_id=None, , instances=16 # dl = tensor_op_name: add.9_pftranspose_990 | hlo_id: 27 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: Est. DMA time: 41.879us (8.000MiB, est bw: 200.308GB/s, 2.823% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[3] bfloat16 (2, 2, 4, 128, 2048) %'994.1661'[T_i20_0_1002,T_i20_1_0_1002,T_i2_0_2014,i0.128,i1.2048] = load bfloat16<128 x 2048> non_local bfloat16 (4194304,) %'all_reduce.3-buffer-2029'[2097152T_i20_0_1002+2048i0.128+1048576T_i20_1_0_1002+i1.2048+262144T_i2_0_2014] # id=1555, src_id=None, , instances=16 # dl = tensor_op_name: all_reduce.3_pftranspose_994 | hlo_id: 66 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: Est. DMA time: 25.532us (8.000MiB, est bw: 328.547GB/s, 1.721% of tot. time) for bfloat16<128 x 2048> non_local bfloat16 (4194304,) %'dot.14-buffer-2027'[2097152i16_0_1068+2048i0.128+1048576i16_1_0_0_1068+i1.2048+262144i16_1_0_1_1068_1512] = store bfloat16<128 x 2048> TongaSB partitions[3] bfloat16 (2, 2, 4, 128, 2048) %1069[i16_0_1068,i16_1_0_0_1068,i16_1_0_1_1068_1512,i0.128,i1.2048] # id=1371, src_id=None, , instances=16 # dl = tensor_op_name: _dot.199 | hlo_id: 63 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: Est. DMA time: 25.532us (8.000MiB, est bw: 328.547GB/s, 1.721% of tot. time) for bfloat16<128 x 2048> non_local bfloat16 (2048, 16, 128) %'convert.53'[1024T_i20_0_1002+i0.128+512T_i20_1_0_1002+128T_i20_1_1_1002_0,i2.8+8i3.2,i1.128] = store bfloat16<128 x 2048> TongaSB partitions[3] bfloat16 (2, 2, 4, 128, 2, 1024) %'998.1561'[T_i20_0_1002,T_i20_1_0_1002,T_i20_1_1_1002_0,i0.128,i3.2,i1.128+128i2.8] # id=1559, src_id=None, , instances=16 # dl = tensor_op_name: convert.53_pftranspose_998 | hlo_id: 75 | [[i0.128];[i1.128, i2.8, i3.2]] -> [[i0.128];[i1.128, i2.8, i3.2]]
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: Est. DMA time: 4.336us (16.000KiB, est bw: 3.779GB/s, 0.292% of tot. time) for int32<1 x 1024> TongaSB partitions[2] int32 (2, 2, 1, 1024) %'input1_local_1077'[i31_0,i21_0,0,i0.1024] = load int32<1 x 1024> {'CrossPassTensor': ''}int32 (1, 2, 1024) %'input1'[0,i21_0,i0.1024] # id=1384, src_id=None, , instances=4 # dl = tensor_op_name: _reduce | hlo_id: 185 | [[];[i0.1024]] -> [[];[i0.1024]]
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.009 seconds
|
|
2025-11-09T20:56:35Z INFO 750 [sg0002/Tensorizer/OptimizeNKIKernels]: Running OptimizeNKIKernels
|
|
2025-11-09T20:56:35Z INFO 750 [topk/Tensorizer/DoNothing]: Running DoNothing
|
|
2025-11-09T20:56:35Z INFO 750 [topk/Tensorizer/DoNothing]: Finished (changed=True)
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 0.218 seconds
|
|
2025-11-09T20:56:35Z INFO 750 [topk/Tensorizer/DoNothing]: DoNothing finished after 0.000 seconds
|
|
2025-11-09T20:56:35Z INFO 750 [topk/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_1
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_1 finished after 0.113 seconds
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/InferPSumTensor]: Finished (changed=True)
|
|
2025-11-09T20:56:35Z INFO 750 [topk/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 0.334 seconds
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/WeightCoalescing]: Running WeightCoalescing
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/WeightCoalescing]: Finished (changed=False)
|
|
2025-11-09T20:56:35Z INFO 750 [topk/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.077 seconds
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.007 seconds
|
|
2025-11-09T20:56:35Z INFO 750 [topk/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_1 finished after 0.185 seconds
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/InferPSumTensor]: Finished (changed=True)
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 0.406 seconds
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/WeightCoalescing]: Running WeightCoalescing
|
|
2025-11-09T20:56:35Z INFO 750 [topk/Tensorizer/FactorizeBlkDims]: Finished (changed=False)
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/WeightCoalescing]: Finished (changed=False)
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/LegalizeSundaAccess]: Finished (changed=False)
|
|
2025-11-09T20:56:35Z INFO 750 [topk/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.108 seconds
|
|
2025-11-09T20:56:35Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:35Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.187 seconds
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/RelaxPredicates]: Running RelaxPredicates
|
|
2025-11-09T20:56:35Z INFO 749 [sg0001/Tensorizer/RelaxPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.005 seconds
|
|
2025-11-09T20:56:35Z INFO 748 [sg0000/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/RelaxPredicates]: RelaxPredicates finished after 0.007 seconds
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/TensorInitialization]: Running TensorInitialization
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/TensorInitialization]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/TensorInitialization]: TensorInitialization finished after 0.008 seconds
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.193 seconds
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.004 seconds
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_1
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/ExpandISAMacro]: Finished (changed=True)
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.018 seconds
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_1 finished after 0.092 seconds
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Finished (changed=True)
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.290 seconds
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.003 seconds
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronValueNumbering]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/SimplifyNeuronTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.010 seconds
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.022 seconds
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/DMALocalityOpt]: Finished (changed=True)
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.002 seconds
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/DataStreaming]: Running DataStreaming
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.083 seconds
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/DataStreaming]: Finished (changed=True)
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.085 seconds
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LowerTranspose]: Running LowerTranspose
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/DataStreaming]: DataStreaming finished after 0.013 seconds
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/SFKVectorizer]: Running SFKVectorizer
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/LegalizeSundaAccess]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LowerTranspose]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.402 seconds
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/RelaxPredicates]: Running RelaxPredicates
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/RelaxPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/RelaxPredicates]: RelaxPredicates finished after 0.004 seconds
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/TensorInitialization]: Running TensorInitialization
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.079 seconds
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LowerBroadcast]: Running LowerBroadcast
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LowerBroadcast]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/TensorInitialization]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.006 seconds
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/TensorInitialization]: TensorInitialization finished after 0.011 seconds
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.003 seconds
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/ExpandISAMacro]: Finished (changed=True)
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.004 seconds
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.088 seconds
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LateNeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.090 seconds
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/SpillPSum]: Running SpillPSum
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.009 seconds
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/SimplifyNeuronTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.113 seconds
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/DMALocalityOpt]: Finished (changed=True)
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.003 seconds
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/DataStreaming]: Running DataStreaming
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/DataStreaming]: Finished (changed=True)
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/DataStreaming]: DataStreaming finished after 0.010 seconds
|
|
2025-11-09T20:56:36Z INFO 748 [sg0000/Tensorizer/SFKVectorizer]: Running SFKVectorizer
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/SpillPSum]: Finished (changed=True)
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/SpillPSum]: SpillPSum finished after 0.212 seconds
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LowerIntrinsics]: Finished (changed=False)
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.010 seconds
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LegalizeType]: Running LegalizeType
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LegalizeType]: Finished (changed=True)
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/LegalizeType]: LegalizeType finished after 0.090 seconds
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:36Z INFO 749 [sg0001/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0
|
|
2025-11-09T20:56:36Z INFO 750 [topk/Tensorizer/NeuronLICM]: Finished (changed=False)
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.029 seconds
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/InferPSumTensor]: Running InferPSumTensor
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 0.115 seconds
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/InferPSumTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 0.117 seconds
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/WeightCoalescing]: Running WeightCoalescing
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/WeightCoalescing]: Finished (changed=False)
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.011 seconds
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/LegalizeSundaAccess]: Finished (changed=False)
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.112 seconds
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.016 seconds
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/ExpandISAMacro]: Finished (changed=False)
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.013 seconds
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 0.506 seconds
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_1
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_1 finished after 0.019 seconds
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/SFKVectorizer]: Finished (changed=True)
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 1.280 seconds
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst
|
|
2025-11-09T20:56:37Z INFO 748 [sg0000/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/LateLegalizeInst]: Finished (changed=True)
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.004 seconds
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.033 seconds
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/SimplifyNeuronTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.401 seconds
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/CoalesceCCOp]: Finished (changed=True)
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.024 seconds
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/DMALocalityOpt]: Finished (changed=False)
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.088 seconds
|
|
2025-11-09T20:56:37Z INFO 750 [topk/Tensorizer/DataStreaming]: Running DataStreaming
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/SimpleAllReduceTiling]: Finished (changed=True)
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.011 seconds
|
|
2025-11-09T20:56:37Z INFO 749 [sg0001/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/InsertCoreBarrier]: Finished (changed=True)
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DataStreaming]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.081 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: Running DMAProfiler
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DataStreaming]: DataStreaming finished after 0.094 seconds
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/SFKVectorizer]: Running SFKVectorizer
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs:
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: Est. DMA time: 148.113us (24.000MiB, est bw: 169.910GB/s, 20.219% of tot. time) for bfloat16<128 x 1024> TongaSB partitions[6] bfloat16 (2, 2, 2, 2, 2, 3, 128, 1024) %1738[i16_0_1406,i16_1_0_0_1406,i15_0_0_1,i15_0_0_0_2369,c1_1394_2369,c2_1395_2369,i0.128,i1.1024] = load bfloat16<128 x 1024> {'CrossPassTensor': ''}bfloat16 (4, 2, 128, 3, 1024) %'input68'[i15_0_0_1+2i15_0_0_0_2369,c1_1394_2369,i0.128,c2_1395_2369,i1.1024] # id=1628, src_id=None, , instances=96 # dl = tensor_op_name: _dot.6 | hlo_id: 51 | [[i0.128];[i1.1024]] -> [[i0.128];[i1.1024]]
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: Est. DMA time: 123.036us (24.000MiB, est bw: 204.541GB/s, 16.795% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[5] bfloat16 (2, 2, 3, 2, 2, 128, 2048) %1735[i16_0_1406,i16_1_0_0_1406,i10_0_0_1,i10_0_0_0,c2_1373,i0.128,i1.2048] = load bfloat16<128 x 2048> {'CrossPassTensor': ''}bfloat16 (2, 3, 128, 2, 2048) %'input69'[i10_0_0_0,i10_0_0_1,i0.128,c2_1373,i1.2048] # id=1619, src_id=None, , instances=48 # dl = tensor_op_name: _dot.4 | hlo_id: 40 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: Est. DMA time: 123.036us (24.000MiB, est bw: 204.541GB/s, 16.795% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[5] bfloat16 (2, 2, 3, 2, 2, 128, 2048) %1736[i16_0_1406,i16_1_0_0_1406,i12_0_0_1,i12_0_0_0,c2_1384,i0.128,i1.2048] = load bfloat16<128 x 2048> {'CrossPassTensor': ''}bfloat16 (2, 3, 128, 2, 2048) %'input71'[i12_0_0_0,i12_0_0_1,i0.128,c2_1384,i1.2048] # id=1622, src_id=None, , instances=48 # dl = tensor_op_name: _dot.5 | hlo_id: 30 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: Est. DMA time: 41.879us (8.000MiB, est bw: 200.308GB/s, 5.717% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[3] bfloat16 (2, 2, 4, 128, 2048) %'1326.1866'[i16_0_1406,i16_1_0_0_1406,T_i2_0_2370,i0.128,i1.2048] = load bfloat16<128 x 2048> non_local bfloat16 (2, 2, 512, 2048) %'add.4'[i16_0_1406,i16_1_0_0_1406,i0.128+128T_i2_0_2370,i1.2048] # id=1739, src_id=None, , instances=16 # dl = tensor_op_name: add.4_pftranspose_1326 | hlo_id: 15 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: Est. DMA time: 41.879us (8.000MiB, est bw: 200.308GB/s, 5.717% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[3] bfloat16 (2, 2, 4, 128, 2048) %'1330.1871'[i37_0,i37_1_0,T_i2_0_2371,i0.128,i1.2048] = load bfloat16<128 x 2048> non_local bfloat16 (4194304,) %'all_reduce.1-buffer-2423'[2097152i37_0+2048i0.128+1048576i37_1_0+i1.2048+262144T_i2_0_2371] # id=1748, src_id=None, , instances=16 # dl = tensor_op_name: all_reduce.1_pftranspose_1330 | hlo_id: 54 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: Est. DMA time: 30.524us (8.000MiB, est bw: 274.819GB/s, 4.167% of tot. time) for bfloat16<128 x 1024> non_local bfloat16 (4194304,) %'dot.11-buffer-2426'[1024i98_0_0_1514+2048i0.128+262144i99_0_1514+i1.1024] = store bfloat16<128 x 1024> TongaSB partitions[2] bfloat16 (2, 16, 128, 1024) %1515[i98_0_0_1514,i99_0_1514,i0.128,i1.1024] # id=1698, src_id=None, , instances=32 # dl = tensor_op_name: _dot.10 | hlo_id: 173 | [[i0.128];[i1.1024]] -> [[i0.128];[i1.1024]]
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: Est. DMA time: 25.532us (8.000MiB, est bw: 328.547GB/s, 3.485% of tot. time) for bfloat16<128 x 2048> non_local bfloat16 (4194304,) %'dot.7-buffer-2421'[2097152i16_0_1406+2048i0.128+1048576i16_1_0_0_1406+i1.2048+262144i16_1_0_1_1406_1737] = store bfloat16<128 x 2048> TongaSB partitions[3] bfloat16 (2, 2, 4, 128, 2048) %1407[i16_0_1406,i16_1_0_0_1406,i16_1_0_1_1406_1737,i0.128,i1.2048] # id=1631, src_id=None, , instances=16 # dl = tensor_op_name: _dot.6 | hlo_id: 51 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: Est. DMA time: 25.532us (8.000MiB, est bw: 328.547GB/s, 3.485% of tot. time) for bfloat16<128 x 2048> {'IntermediateTensor': ''}bfloat16 (1, 2, 2, 512, 2048) %'intermediate5'(init=0.0)[0,i37_0,i37_1_0,i0.128+128T_i18_1_1_0_1338,i1.2048] = store bfloat16<128 x 2048> TongaSB partitions[3] bfloat16 (2, 2, 4, 128, 2048) %'1334.1754'[i37_0,i37_1_0,T_i18_1_1_0_1338,i0.128,i1.2048] # id=1752, src_id=None, , instances=16 # dl = tensor_op_name: intermediate5_pftranspose_1334 | hlo_id: 2 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: Est. DMA time: 21.589us (4.000MiB, est bw: 194.277GB/s, 2.947% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[3] bfloat16 (2, 2, 2, 128, 2048) %'input78_local_1423'[i37_0,c0_1415,c1_1416,i0.128,i1.2048] = load bfloat16<128 x 2048> {'CrossPassTensor': ''}bfloat16 (2, 128, 4096) %'input78'[c0_1415,i0.128,i1.2048+2048c1_1416] # id=1642, src_id=None, , instances=8 # dl = tensor_op_name: _dot.9 | hlo_id: 71 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: Est. DMA time: 21.589us (4.000MiB, est bw: 194.277GB/s, 2.947% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[3] bfloat16 (2, 2, 2, 128, 16, 128) %'get_tuple_element.2_local_1497'[i98_0_0,c0_1491,c1_1492,i0.128,i1.16,i2.128] = load bfloat16<128 x 2048> non_local bfloat16 (2, 2, 128, 16, 128) %'get_tuple_element.2'[c0_1491,c1_1492,i0.128,i1.16,i2.128] # id=1694, src_id=None, , instances=8 # dl = tensor_op_name: _dot.10 | hlo_id: 173 | [[i0.128];[i2.128, i1.16]] -> [[i0.128];[i2.128, i1.16]]
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.016 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/OptimizeNKIKernels]: Running OptimizeNKIKernels
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/DoNothing]: Running DoNothing
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/DoNothing]: Finished (changed=True)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/DoNothing]: DoNothing finished after 0.007 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.002 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/FactorizeBlkDims]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.001 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.003 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronValueNumbering]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.001 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.001 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LowerTranspose]: Running LowerTranspose
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LowerTranspose]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LowerBroadcast]: Running LowerBroadcast
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LowerBroadcast]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LateNeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SpillPSum]: Running SpillPSum
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SpillPSum]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 0.001 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SpillPSum]: SpillPSum finished after 0.003 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LowerIntrinsics]: Finished (changed=True)
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/SFKVectorizer]: Finished (changed=True)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LegalizeType]: Running LegalizeType
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LegalizeType]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LegalizeType]: LegalizeType finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronLICM]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 0.288 seconds
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InferPSumTensor]: Running InferPSumTensor
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 0.001 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InferPSumTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 0.001 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/WeightCoalescing]: Running WeightCoalescing
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/WeightCoalescing]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/LateLegalizeInst]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LegalizeSundaAccess]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.021 seconds
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/CoalesceCCOp]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.001 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/ExpandISAMacro]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SimplifyNeuronTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.002 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/DMALocalityOpt]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/DataStreaming]: Running DataStreaming
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/DataStreaming]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/DataStreaming]: DataStreaming finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SFKVectorizer]: Running SFKVectorizer
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.006 seconds
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SFKVectorizer]: Finished (changed=True)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 0.082 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LateLegalizeInst]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/CoalesceCCOp]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/SimpleAllReduceTiling]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SimpleAllReduceTiling]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.000 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InsertCoreBarrier]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.001 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/DMAProfiler]: Running DMAProfiler
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs:
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/DMAProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.021 seconds
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.001 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/InsertCoreBarrier]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.008 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DMAProfiler]: Running DMAProfiler
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs:
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 3.006us (148.375KiB, est bw: 50.546GB/s, 16.410% of tot. time) for float32<32 x 1187> TongaSB partitions[0] float32 (32, 1443) %4(init=0.0)[i0.32,i1.1187] = load float32<32 x 1187> float32 (32, 1187) %6[i0.32,i1.1187] # id=7, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[i0.32];[i1.1187]] -> [[i0.32];[i1.1187]]
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 3.006us (148.375KiB, est bw: 50.546GB/s, 16.410% of tot. time) for float32<32 x 1187> TongaSB partitions[0] float32 (32, 1187) %10[i0.32,i1.1187] = load float32<32 x 1187> float32 (1, 37984) %'inp'[i0.32,i1.1187] # id=9, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[i0.32];[i1.1187]] -> [[i0.32];[i1.1187]]
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.965us (4.000KiB, est bw: 2.085GB/s, 10.725% of tot. time) for float32<32 x 32> TongaSB partitions[0] float32 (32, 32) %485[i0.32,i1.32] = load float32<32 x 32> float32 (32, 32) %3[i0.32,i1.32] # id=13, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[i0.32];[i1.32]] -> [[i0.32];[i1.32]]
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.922us (1.000KiB, est bw: 0.533GB/s, 10.491% of tot. time) for float32<1 x 256> TongaSB partitions[0] float32 (1, 256) %316[0,i0.256] = load float32<1 x 256> float32 (32, 8) %304[0,i0.256] # id=306, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[];[i0.256]] -> [[];[i0.256]]
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.922us (1.000KiB, est bw: 0.533GB/s, 10.491% of tot. time) for uint32<1 x 256> TongaSB partitions[0] uint32 (1, 256) %319[0,i0.256] = load float32<1 x 256> float32 (32, 8) %307[0,i0.256] # id=309, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[];[i0.256]] -> [[];[i0.256]]
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.640us (1.000KiB, est bw: 0.625GB/s, 8.951% of tot. time) for uint32<1 x 256> uint32 (1, 256) %'topk_indices'[0,i0.256] = store uint32<1 x 256> TongaSB partitions[0] uint32 (1, 256) %'global_id_buf'(init=0.0)[0,i0.256] # id=322, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[];[i0.256]] -> [[];[i0.256]]
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.640us (1.000KiB, est bw: 0.625GB/s, 8.951% of tot. time) for float32<1 x 256> float32 (1, 256) %'topk_values'[0,i0.256] = store float32<1 x 256> TongaSB partitions[0] float32 (1, 256) %'val_buf'(init=0.0)[0,i0.256] # id=324, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[];[i0.256]] -> [[];[i0.256]]
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.609us (1.000KiB, est bw: 0.636GB/s, 8.785% of tot. time) for float32<32 x 8> float32 (32, 8) %304[i0.32,i1.8] = store float32<32 x 8> TongaSB partitions[0] float32 (32, 8) %296[i0.32,i1.8] # id=305, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[i0.32];[i1.8]] -> [[i0.32];[i1.8]]
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.609us (1.000KiB, est bw: 0.636GB/s, 8.785% of tot. time) for float32<32 x 8> float32 (32, 8) %307[i0.32,i1.8] = store float32<32 x 8> TongaSB partitions[0] float32 (32, 8) %517[i0.32,i1.8] # id=308, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[i0.32];[i1.8]] -> [[i0.32];[i1.8]]
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DMAProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:38Z INFO 749 [attention_isa_kernel/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.068 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/OptimizeNKIKernels]: Allocate SB of shape (128, 60284) for CausalAttentionMMSoftmaxMMWithoutSwap
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/OptimizeNKIKernels]: Allocate PSUM of shape (8, 128, 2048) for CausalAttentionMMSoftmaxMMWithoutSwap
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/OptimizeNKIKernels]: Finished (changed=True)
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.018 seconds
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/OptimizeNKIKernels]: OptimizeNKIKernels finished after 0.531 seconds
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: Running CCOpFusion
|
|
2025-11-09T20:56:38Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: Running CCOpFusion_iteration_0
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:38Z INFO 750 [topk/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.012 seconds
|
|
2025-11-09T20:56:38Z INFO 748 [sg0000/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 0.993 seconds
|
|
2025-11-09T20:56:38Z INFO 748 [sg0000/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_1
|
|
2025-11-09T20:56:38Z INFO 748 [sg0000/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_1 finished after 0.099 seconds
|
|
2025-11-09T20:56:38Z INFO 748 [sg0000/Tensorizer/SFKVectorizer]: Finished (changed=True)
|
|
2025-11-09T20:56:38Z INFO 748 [sg0000/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 2.123 seconds
|
|
2025-11-09T20:56:38Z INFO 748 [sg0000/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/LateLegalizeInst]: Finished (changed=True)
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.102 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: CCOpFusion_iteration_0 finished after 0.316 seconds
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/CoalesceCCOp]: Finished (changed=True)
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: CCOpFusion finished after 0.317 seconds
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/StaticProfiler]: Running StaticProfiler
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.086 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/StaticProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/SimpleAllReduceTiling]: Finished (changed=True)
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/StaticProfiler]: StaticProfiler finished after 0.014 seconds
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/SplitAPUnionSets]: Running SplitAPUnionSets
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.011 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/InsertCoreBarrier]: Finished (changed=True)
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.021 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: Running DMAProfiler
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs:
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 44.622us (2.000MiB, est bw: 46.999GB/s, 12.206% of tot. time) for bfloat16<128 x 128> TongaSB partitions[3] bfloat16 (2, 2, 16, 128, 128) %'gather.41.1994'[i2_1_0_1996,i2_0_1996,i3_0,i0.128,i1.128] = indirect_load bfloat16<128 x 128> {'CrossPassTensor': ''}bfloat16 (151936, 2, 2, 128) %'input60'[i0.128,i2_0_1996,i2_1_0_1996,i1.128] generic generic_dims:[0] generic_addrs: int32<128 x 1> TongaSB partitions[1] int32 (2, 128, 16, 1) %'input0_local_1610'[i2_1_0_1996,i0.128,i3_0,0] # id=1814, src_id=None, , attrs={'mode': OOBMode.ERROR}, instances=64 # dl = tensor_op_name: _gather.41 | hlo_id: 12 | [[i0.128];[i1.128]] -> [[i0.128];[i1.128]]
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 41.879us (8.000MiB, est bw: 200.308GB/s, 11.456% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[4] bfloat16 (2, 2, 2, 2, 128, 2, 2, 512) %'intermediate0_pftranspose_1572'[i0_0,i1_1_0,i1_0_0,i1_0_1,i0.128,i3.2,i2.2,i1.512] = load bfloat16<128 x 2048> DRAM2DBlk partitions[1] bfloat16 (2, 1, 2, 2, 2, 128, 2, 2, 512) %'all_gather.1'[i1_1_0,0,i1_0_0,i1_0_1,i3.2,i0.128,i0_0,i2.2,i1.512] # id=1817, src_id=None, , instances=16 # dl = tensor_op_name: UnnamedModule | hlo_id: 1 | [[i0.128];[i1.512, i2.2, i3.2]] -> [[i0.128];[i1.512, i2.2, i3.2]]
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 41.879us (8.000MiB, est bw: 200.308GB/s, 11.456% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[4] bfloat16 (2, 2, 2, 2, 128, 2, 2, 512) %'custom-call.177.1997'[i17_0_1638_1999,i16_0_1_1_0_1638_1999,i16_0_0_1638_1999,i16_0_1_0_1638_1999,i0.128,i3.2,i2.2,i1.512] = load bfloat16<128 x 2048> DRAM2DBlk partitions[1] bfloat16 (2, 1, 2, 2, 2, 128, 2, 2, 512) %'all_gather.1'[i16_0_1_1_0_1638_1999,0,i16_0_0_1638_1999,i16_0_1_0_1638_1999,i3.2,i0.128,i17_0_1638_1999,i2.2,i1.512] # id=1853, src_id=None, , instances=16 # dl = tensor_op_name: _custom-call.177 | hlo_id: 24 | [[i0.128];[i1.512, i2.2, i3.2]] -> [[i0.128];[i1.512, i2.2, i3.2]]
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 30.524us (8.000MiB, est bw: 274.819GB/s, 8.350% of tot. time) for bfloat16<128 x 1024> {'IntermediateTensor': ''}bfloat16 (2, 2, 512, 4, 2, 256) %'intermediate0'(init=0.0)[T_i0_0_1576,T_i0_1_0_1576,i0.128+128T_i0_1_1_1576_0,i2.4,T_i1_1_0_1576,i1.256] = store bfloat16<128 x 1024> TongaSB partitions[4] bfloat16 (2, 2, 2, 4, 128, 1024) %'1572.2030'[T_i0_0_1576,T_i1_1_0_1576,T_i0_1_0_1576,T_i0_1_1_1576_0,i0.128,i1.256+256i2.4] # id=2028, src_id=None, , instances=32 # dl = tensor_op_name: intermediate0_pftranspose_1572 | hlo_id: 1 | [[i0.128];[i1.256, i2.4]] -> [[i0.128];[i1.256, i2.4]]
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 30.524us (8.000MiB, est bw: 274.819GB/s, 8.350% of tot. time) for bfloat16<128 x 1024> non_local bfloat16 (4194304,) %'dot.4-buffer-2729'[1024i95_0_0_1723+2048i0.128+262144i96_0_1723+i1.1024] = store bfloat16<128 x 1024> TongaSB partitions[2] bfloat16 (2, 16, 128, 1024) %1724[i95_0_0_1723,i96_0_1723,i0.128,i1.1024] # id=1962, src_id=None, , instances=32 # dl = tensor_op_name: _dot.3 | hlo_id: 147 | [[i0.128];[i1.1024]] -> [[i0.128];[i1.1024]]
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 21.589us (4.000MiB, est bw: 194.277GB/s, 5.906% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[3] bfloat16 (2, 2, 2, 128, 2048) %'input67_local_1658'[i34_0,c0_1649,c1_1650,i0.128,i1.2048] = load bfloat16<128 x 2048> {'CrossPassTensor': ''}bfloat16 (2, 128, 2, 2048) %'input67'[c0_1649,i0.128,c1_1650,i1.2048] # id=1858, src_id=None, , instances=8 # dl = tensor_op_name: _dot.2 | hlo_id: 32 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 21.589us (4.000MiB, est bw: 194.277GB/s, 5.906% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[3] bfloat16 (2, 2, 2, 128, 16, 128) %'get_tuple_element.1_local_1706'[i95_0_0,c0_1700,c1_1701,i0.128,i1.16,i2.128] = load bfloat16<128 x 2048> non_local bfloat16 (2, 2, 128, 16, 128) %'get_tuple_element.1'[c0_1700,c1_1701,i0.128,i1.16,i2.128] # id=1958, src_id=None, , instances=8 # dl = tensor_op_name: _dot.3 | hlo_id: 147 | [[i0.128];[i2.128, i1.16]] -> [[i0.128];[i2.128, i1.16]]
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 13.768us (1.000MiB, est bw: 76.160GB/s, 3.766% of tot. time) for bfloat16<128 x 128> bfloat16 (4, 2, 2048, 128) %'output2'[i0.128,i1.128] generic, generic_dims:[0] generic_addrs: int32<128 x 1> TongaSB partitions[4] int32 (2, 2, 2, 4, 128, 1) %'scatter.6719.2293'[i111_0,i105,i104_1_0_0,i104_1_0_1,i0.128,0] = indirect_save bfloat16<128 x 128> TongaSB partitions[2] bfloat16 (2, 2, 128, 4, 2, 128) %'transpose.19'[i111_0,i104_1_0_0,i0.128,i104_1_0_1,i105,i1.128] # id=1976, src_id=None, , attrs={'mode': OOBMode.ERROR}, instances=32 # dl = tensor_op_name: _scatter.6719 | hlo_id: 187 | [[i0.128];[i1.128]] -> [[i0.128];[i1.128]]
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 13.768us (1.000MiB, est bw: 76.160GB/s, 3.766% of tot. time) for bfloat16<128 x 128> bfloat16 (4, 2, 2048, 128) %'output1'[i0.128,i1.128] generic, generic_dims:[0] generic_addrs: int32<128 x 1> TongaSB partitions[4] int32 (2, 2, 2, 4, 128, 1) %'scatter.6667.2297'[i111_0,i112,i111_1_0_0,2i111_1_0_1_0+i111_1_0_1_1,i0.128,0] = indirect_save bfloat16<128 x 128> TongaSB partitions[3] bfloat16 (2, 2, 2, 128, 512) %'add.2'[i111_0,i111_1_0_0,i111_1_0_1_0,i0.128,128i112+i1.128+256i111_1_0_1_1] # id=1982, src_id=None, , attrs={'mode': OOBMode.ERROR}, instances=32 # dl = tensor_op_name: _scatter.6667 | hlo_id: 172 | [[i0.128];[i1.128]] -> [[i0.128];[i1.128]]
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 11.445us (2.000MiB, est bw: 183.243GB/s, 3.131% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[2] bfloat16 (2, 2, 128, 2048) %'input65_local_1675'[i64_0,c0_1667,i0.128,i1.2048] = load bfloat16<128 x 2048> {'CrossPassTensor': ''}bfloat16 (2, 128, 2048) %'input65'[c0_1667,i0.128,i1.2048] # id=1905, src_id=None, , instances=4 # dl = tensor_op_name: _dot.1 | hlo_id: 88 | [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.024 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [sg0000/Tensorizer/OptimizeNKIKernels]: Running OptimizeNKIKernels
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/DoNothing]: Running DoNothing
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/DoNothing]: Finished (changed=True)
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/SplitAPUnionSets]: Finished (changed=True)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/DoNothing]: DoNothing finished after 0.000 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/SplitAPUnionSets]: SplitAPUnionSets finished after 0.224 seconds
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/LateLegalizePostSplit]: Running LateLegalizePostSplit
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.004 seconds
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/LateLegalizePostSplit]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/LateLegalizePostSplit]: LateLegalizePostSplit finished after 0.076 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/FactorizeBlkDims]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.001 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.000 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.003 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronValueNumbering]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.085 seconds
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/LowerShardAxis]: Running LowerShardAxis
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.001 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.000 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.001 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LowerTranspose]: Running LowerTranspose
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LowerTranspose]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.001 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LowerBroadcast]: Running LowerBroadcast
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LowerBroadcast]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.000 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.007 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LateNeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/LowerShardAxis]: Finished (changed=True)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.008 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/SpillPSum]: Running SpillPSum
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/LowerShardAxis]: LowerShardAxis finished after 0.105 seconds
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: Running CCOpFusion
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/SpillPSum]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: Running CCOpFusion_iteration_0
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/SpillPSum]: SpillPSum finished after 0.003 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LowerIntrinsics]: Finished (changed=True)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.001 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LegalizeType]: Running LegalizeType
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LegalizeType]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LegalizeType]: LegalizeType finished after 0.000 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronLICM]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.000 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/InferPSumTensor]: Running InferPSumTensor
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 0.001 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/InferPSumTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 0.001 seconds
|
|
2025-11-09T20:56:39Z INFO 750 [topk/Tensorizer/DoNothing]: Running DoNothing
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/WeightCoalescing]: Running WeightCoalescing
|
|
2025-11-09T20:56:39Z INFO 750 [topk/Tensorizer/DoNothing]: Finished (changed=True)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/WeightCoalescing]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.000 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LegalizeSundaAccess]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.001 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.000 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/ExpandISAMacro]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.000 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.000 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/SimplifyNeuronTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: CCOpFusion_iteration_0 finished after 0.188 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.001 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/DMALocalityOpt]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.000 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/DataStreaming]: Running DataStreaming
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/DataStreaming]: Finished (changed=False)
|
|
2025-11-09T20:56:39Z INFO 749 [sg0001/Tensorizer/CCOpFusion]: CCOpFusion finished after 0.191 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/DataStreaming]: DataStreaming finished after 0.000 seconds
|
|
2025-11-09T20:56:39Z INFO 748 [attention_isa_kernel/Tensorizer/SFKVectorizer]: Running SFKVectorizer
|
|
2025-11-09T20:56:39Z INFO 750 [topk/Tensorizer/DoNothing]: DoNothing finished after 0.001 seconds
|
|
2025-11-09T20:56:39Z INFO 750 [topk/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 0.000 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/SFKVectorizer]: Finished (changed=True)
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 0.082 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/LateLegalizeInst]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.000 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/CoalesceCCOp]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.086 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.001 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/SimpleAllReduceTiling]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.000 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/InsertCoreBarrier]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims
|
|
2025-11-09T20:56:40Z INFO 749 [sg0001/Tensorizer/DumpGraphAndMetadata]: Running DumpGraphAndMetadata
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.001 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/DMAProfiler]: Running DMAProfiler
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs:
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/DMAProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.001 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:40Z INFO 748 [attention_isa_kernel/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.002 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/OptimizeNKIKernels]: Allocate SB of shape (128, 60284) for CausalAttentionMMSoftmaxMMWithoutSwap
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/OptimizeNKIKernels]: Allocate PSUM of shape (8, 128, 2048) for CausalAttentionMMSoftmaxMMWithoutSwap
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/OptimizeNKIKernels]: Finished (changed=True)
|
|
2025-11-09T20:56:40Z INFO 749 [sg0001/Tensorizer/DumpGraphAndMetadata]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/OptimizeNKIKernels]: OptimizeNKIKernels finished after 0.792 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: Running CCOpFusion
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: Running CCOpFusion_iteration_0
|
|
2025-11-09T20:56:40Z INFO 749 [sg0001/Tensorizer/DumpGraphAndMetadata]: DumpGraphAndMetadata finished after 0.172 seconds
|
|
2025-11-09T20:56:40Z INFO 749 [sg0001/Tensorizer/ZeroSizeTensorElimination]: Running ZeroSizeTensorElimination
|
|
2025-11-09T20:56:40Z INFO 749 [sg0001/Tensorizer/ZeroSizeTensorElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 749 [sg0001/Tensorizer/ZeroSizeTensorElimination]: ZeroSizeTensorElimination finished after 0.001 seconds
|
|
2025-11-09T20:56:40Z INFO 749 [sg0001/Tensorizer/LowerToSendRecv]: Running LowerToSendRecv
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/FactorizeBlkDims]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 749 [sg0001/Tensorizer/LowerToSendRecv]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.205 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:40Z INFO 749 [sg0001/Tensorizer/LowerToSendRecv]: LowerToSendRecv finished after 0.082 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.087 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_1
|
|
2025-11-09T20:56:40Z INFO 749 [sg0001/Tensorizer/BirCodeGenLoop]: Running BirCodeGenLoop
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: CCOpFusion_iteration_0 finished after 0.198 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: CCOpFusion finished after 0.199 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/StaticProfiler]: Running StaticProfiler
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_1 finished after 0.023 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/StaticProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Finished (changed=True)
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/StaticProfiler]: StaticProfiler finished after 0.014 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/SplitAPUnionSets]: Running SplitAPUnionSets
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.116 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronValueNumbering]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.075 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.018 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.020 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LowerTranspose]: Running LowerTranspose
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LowerTranspose]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.074 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LowerBroadcast]: Running LowerBroadcast
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/SplitAPUnionSets]: Finished (changed=True)
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/SplitAPUnionSets]: SplitAPUnionSets finished after 0.185 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/LateLegalizePostSplit]: Running LateLegalizePostSplit
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LowerBroadcast]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.008 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/LateLegalizePostSplit]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/LateLegalizePostSplit]: LateLegalizePostSplit finished after 0.007 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.016 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LateNeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.009 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/LowerShardAxis]: Running LowerShardAxis
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.017 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/SpillPSum]: Running SpillPSum
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/LowerShardAxis]: Finished (changed=True)
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/LowerShardAxis]: LowerShardAxis finished after 0.029 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: Running CCOpFusion
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: Running CCOpFusion_iteration_0
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/SpillPSum]: Finished (changed=True)
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/SpillPSum]: SpillPSum finished after 0.199 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LowerIntrinsics]: Finished (changed=False)
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.008 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LegalizeType]: Running LegalizeType
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: CCOpFusion_iteration_0 finished after 0.183 seconds
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: Finished (changed=True)
|
|
2025-11-09T20:56:40Z INFO 748 [sg0000/Tensorizer/CCOpFusion]: CCOpFusion finished after 0.184 seconds
|
|
2025-11-09T20:56:40Z INFO 750 [topk/Tensorizer/LegalizeType]: Finished (changed=True)
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/LegalizeType]: LegalizeType finished after 0.023 seconds
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/NeuronLICM]: Finished (changed=False)
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.106 seconds
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/InferPSumTensor]: Running InferPSumTensor
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0
|
|
2025-11-09T20:56:41Z INFO 748 [sg0000/Tensorizer/DumpGraphAndMetadata]: Running DumpGraphAndMetadata
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 0.092 seconds
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/InferPSumTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 0.094 seconds
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/WeightCoalescing]: Running WeightCoalescing
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/WeightCoalescing]: Finished (changed=False)
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.004 seconds
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess
|
|
2025-11-09T20:56:41Z INFO 748 [sg0000/Tensorizer/DumpGraphAndMetadata]: Finished (changed=False)
|
|
2025-11-09T20:56:41Z INFO 748 [sg0000/Tensorizer/DumpGraphAndMetadata]: DumpGraphAndMetadata finished after 0.103 seconds
|
|
2025-11-09T20:56:41Z INFO 748 [sg0000/Tensorizer/ZeroSizeTensorElimination]: Running ZeroSizeTensorElimination
|
|
2025-11-09T20:56:41Z INFO 748 [sg0000/Tensorizer/ZeroSizeTensorElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:41Z INFO 748 [sg0000/Tensorizer/ZeroSizeTensorElimination]: ZeroSizeTensorElimination finished after 0.001 seconds
|
|
2025-11-09T20:56:41Z INFO 748 [sg0000/Tensorizer/LowerToSendRecv]: Running LowerToSendRecv
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/LegalizeSundaAccess]: Finished (changed=False)
|
|
2025-11-09T20:56:41Z INFO 748 [sg0000/Tensorizer/LowerToSendRecv]: Finished (changed=False)
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.086 seconds
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:41Z INFO 748 [sg0000/Tensorizer/LowerToSendRecv]: LowerToSendRecv finished after 0.083 seconds
|
|
2025-11-09T20:56:41Z INFO 748 [sg0000/Tensorizer/BirCodeGenLoop]: Running BirCodeGenLoop
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.012 seconds
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/ExpandISAMacro]: Finished (changed=False)
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.081 seconds
|
|
2025-11-09T20:56:41Z INFO 750 [topk/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor
|
|
2025-11-09T20:56:42Z INFO 750 [topk/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:42Z INFO 750 [topk/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.012 seconds
|
|
2025-11-09T20:56:42Z INFO 750 [topk/Tensorizer/SimplifyNeuronTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:42Z INFO 750 [topk/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.710 seconds
|
|
2025-11-09T20:56:42Z INFO 750 [topk/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt
|
|
2025-11-09T20:56:42Z INFO 750 [topk/Tensorizer/DMALocalityOpt]: Finished (changed=False)
|
|
2025-11-09T20:56:42Z INFO 750 [topk/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.077 seconds
|
|
2025-11-09T20:56:42Z INFO 750 [topk/Tensorizer/DataStreaming]: Running DataStreaming
|
|
2025-11-09T20:56:42Z INFO 750 [topk/Tensorizer/DataStreaming]: Finished (changed=False)
|
|
2025-11-09T20:56:42Z INFO 750 [topk/Tensorizer/DataStreaming]: DataStreaming finished after 0.089 seconds
|
|
2025-11-09T20:56:42Z INFO 750 [topk/Tensorizer/SFKVectorizer]: Running SFKVectorizer
|
|
2025-11-09T20:56:44Z INFO 749 [sg0001/Tensorizer/BirCodeGenLoop]: Finished (changed=False)
|
|
2025-11-09T20:56:44Z INFO 749 [sg0001/Tensorizer/BirCodeGenLoop]: BirCodeGenLoop finished after 4.011 seconds
|
|
2025-11-09T20:56:44Z INFO 749 [Tensorizer]: BirCodeGen estimate #instances=2930 in sg0001
|
|
2025-11-09T20:56:44Z INFO 749 [Tensorizer]: IR signature: 0fef77ca7dec2441b8572e545234dfc807b31fa72c2159d8c20b6b0c8e1890ab for nc00/sg0001/TensorizerBIR
|
|
2025-11-09T20:56:44Z INFO 748 [sg0000/Tensorizer/BirCodeGenLoop]: Finished (changed=False)
|
|
2025-11-09T20:56:44Z INFO 749 [sg0001/Tensorizer/BirCodeGenLoop]: Running BirCodeGenLoop
|
|
2025-11-09T20:56:44Z INFO 748 [sg0000/Tensorizer/BirCodeGenLoop]: BirCodeGenLoop finished after 3.579 seconds
|
|
2025-11-09T20:56:45Z INFO 749 [sg0001/Tensorizer/BirCodeGenLoop]: Finished (changed=False)
|
|
2025-11-09T20:56:45Z INFO 749 [sg0001/Tensorizer/BirCodeGenLoop]: BirCodeGenLoop finished after 0.237 seconds
|
|
2025-11-09T20:56:45Z INFO 748 [Tensorizer]: BirCodeGen estimate #instances=1629 in sg0000
|
|
2025-11-09T20:56:45Z INFO 748 [Tensorizer]: IR signature: 2678462232feeaa642d1a36f13004f20e5a667f57e088862a93e9e2608f7a7b5 for nc00/sg0000/TensorizerBIR
|
|
2025-11-09T20:56:45Z INFO 748 [sg0000/Tensorizer/BirCodeGenLoop]: Running BirCodeGenLoop
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 0.007 seconds
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/SFKVectorizer]: Finished (changed=True)
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 3.305 seconds
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/LateLegalizeInst]: Finished (changed=False)
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.025 seconds
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp
|
|
2025-11-09T20:56:45Z INFO 749 [Tensorizer]: BirCodeGen estimate #instances=2930 in sg0001
|
|
2025-11-09T20:56:45Z INFO 748 [sg0000/Tensorizer/BirCodeGenLoop]: Finished (changed=False)
|
|
2025-11-09T20:56:45Z INFO 748 [sg0000/Tensorizer/BirCodeGenLoop]: BirCodeGenLoop finished after 0.291 seconds
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/CoalesceCCOp]: Finished (changed=False)
|
|
2025-11-09T20:56:45Z INFO 749 [Tensorizer]: IR signature: 2c7c85f5e6fc1e6eedac40e2e0275dc772cd11a224f1ad5f87df0233816fa2fc for nc01/sg0001/TensorizerBIR
|
|
2025-11-09T20:56:45Z INFO 749 [Tensorizer]: Weights total number of bytes: 163842
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.010 seconds
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling
|
|
2025-11-09T20:56:45Z INFO 749 [Tensorizer]: Successfully built model.
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/SimpleAllReduceTiling]: Finished (changed=False)
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.009 seconds
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/InsertCoreBarrier]: Finished (changed=False)
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.081 seconds
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/DMAProfiler]: Running DMAProfiler
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs:
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.965us (4.000KiB, est bw: 2.085GB/s, 12.101% of tot. time) for float32<32 x 32> TongaSB partitions[0] float32 (32, 288) %4(init=0.0)[i0.32,i1.32] = load float32<32 x 32> float32 (32, 32) %6[i0.32,i1.32] # id=7, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[i0.32];[i1.32]] -> [[i0.32];[i1.32]]
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.965us (4.000KiB, est bw: 2.085GB/s, 12.101% of tot. time) for float32<32 x 32> TongaSB partitions[0] float32 (32, 32) %10[i0.32,i1.32] = load float32<32 x 32> float32 (1, 1024) %'inp'[i0.32,i1.32] # id=9, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[i0.32];[i1.32]] -> [[i0.32];[i1.32]]
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.965us (4.000KiB, est bw: 2.085GB/s, 12.101% of tot. time) for float32<32 x 32> TongaSB partitions[0] float32 (32, 32) %485[i0.32,i1.32] = load float32<32 x 32> float32 (32, 32) %3[i0.32,i1.32] # id=13, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[i0.32];[i1.32]] -> [[i0.32];[i1.32]]
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.922us (1.000KiB, est bw: 0.533GB/s, 11.837% of tot. time) for float32<1 x 256> TongaSB partitions[0] float32 (1, 256) %316[0,i0.256] = load float32<1 x 256> float32 (32, 8) %304[0,i0.256] # id=306, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[];[i0.256]] -> [[];[i0.256]]
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.922us (1.000KiB, est bw: 0.533GB/s, 11.837% of tot. time) for uint32<1 x 256> TongaSB partitions[0] uint32 (1, 256) %319[0,i0.256] = load float32<1 x 256> float32 (32, 8) %307[0,i0.256] # id=309, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[];[i0.256]] -> [[];[i0.256]]
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.640us (1.000KiB, est bw: 0.625GB/s, 10.099% of tot. time) for uint32<1 x 256> uint32 (1, 256) %'topk_indices'[0,i0.256] = store uint32<1 x 256> TongaSB partitions[0] uint32 (1, 256) %'global_id_buf'(init=0.0)[0,i0.256] # id=322, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[];[i0.256]] -> [[];[i0.256]]
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.640us (1.000KiB, est bw: 0.625GB/s, 10.099% of tot. time) for float32<1 x 256> float32 (1, 256) %'topk_values'[0,i0.256] = store float32<1 x 256> TongaSB partitions[0] float32 (1, 256) %'val_buf'(init=0.0)[0,i0.256] # id=324, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[];[i0.256]] -> [[];[i0.256]]
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.609us (1.000KiB, est bw: 0.636GB/s, 9.912% of tot. time) for float32<32 x 8> float32 (32, 8) %304[i0.32,i1.8] = store float32<32 x 8> TongaSB partitions[0] float32 (32, 8) %296[i0.32,i1.8] # id=305, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[i0.32];[i1.8]] -> [[i0.32];[i1.8]]
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.609us (1.000KiB, est bw: 0.636GB/s, 9.912% of tot. time) for float32<32 x 8> float32 (32, 8) %307[i0.32,i1.8] = store float32<32 x 8> TongaSB partitions[0] float32 (32, 8) %517[i0.32,i1.8] # id=308, src_id=None, , instances=1 # dl = tensor_op_name: | /opt/conda/lib/python3.11/site-packages/neuronxcc/nki/_pre_prod_kernels/topk/topk.py:45:0 | [[i0.32];[i1.8]] -> [[i0.32];[i1.8]]
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/DMAProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.010 seconds
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:45Z INFO 750 [topk/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.007 seconds
|
|
2025-11-09T20:56:45Z INFO 748 [Tensorizer]: BirCodeGen estimate #instances=1629 in sg0000
|
|
2025-11-09T20:56:45Z INFO 748 [Tensorizer]: IR signature: 08681213ccb6cc032d583487e0fec5a0a200c09de565b3bf220de943b1b84eb2 for nc01/sg0000/TensorizerBIR
|
|
2025-11-09T20:56:45Z INFO 748 [Tensorizer]: Weights total number of bytes: 229634
|
|
2025-11-09T20:56:45Z INFO 748 [Tensorizer]: Successfully built model.
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DoNothing]: Running DoNothing
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DoNothing]: Finished (changed=True)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DoNothing]: DoNothing finished after 0.002 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.002 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/FactorizeBlkDims]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.002 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.004 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.007 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronValueNumbering]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.003 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerTranspose]: Running LowerTranspose
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerTranspose]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.010 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerBroadcast]: Running LowerBroadcast
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerBroadcast]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.003 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LateNeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.004 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SpillPSum]: Running SpillPSum
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SpillPSum]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SpillPSum]: SpillPSum finished after 0.006 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerIntrinsics]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.002 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LegalizeType]: Running LegalizeType
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LegalizeType]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LegalizeType]: LegalizeType finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronLICM]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.002 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferPSumTensor]: Running InferPSumTensor
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 0.004 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferPSumTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 0.005 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/WeightCoalescing]: Running WeightCoalescing
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/WeightCoalescing]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.002 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LegalizeSundaAccess]: Finished (changed=True)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.014 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.069 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/ExpandISAMacro]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.003 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.000 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SimplifyNeuronTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.002 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DMALocalityOpt]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DataStreaming]: Running DataStreaming
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DataStreaming]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DataStreaming]: DataStreaming finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SFKVectorizer]: Running SFKVectorizer
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SFKVectorizer]: Finished (changed=True)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 0.016 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LateLegalizeInst]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/CoalesceCCOp]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.000 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SimpleAllReduceTiling]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.000 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InsertCoreBarrier]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DMAProfiler]: Running DMAProfiler
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs:
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DMAProfiler]: Est. DMA time: 5.852us (1.000MiB, est bw: 179.191GB/s, 59.288% of tot. time) for float32<128 x 2048> TongaSB partitions[0] float32 (128, 2048) %13[i0.128,i1.2048] = load float32<128 x 2048> float32 (1, 256) %'x'[i0.128,i1.2048] # id=8, src_id=None, , instances=1 # dl = tensor_op_name: | if i0.128 == 0 and -i1.2048+255 >= 0 [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DMAProfiler]: Est. DMA time: 4.018us (1.000MiB, est bw: 260.951GB/s, 40.712% of tot. time) for float32<128 x 2048> float32 (1, 256) %'y'[i0.128,i1.2048] = store float32<128 x 2048> TongaSB partitions[0] float32 (128, 2048) %11[i0.128,i1.2048] # id=10, src_id=None, , instances=1 # dl = tensor_op_name: | if i0.128 == 0 and -i1.2048+255 >= 0 [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DMAProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.003 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DoNothing]: Running DoNothing
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DoNothing]: Finished (changed=True)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/DoNothing]: DoNothing finished after 0.000 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/FactorizeBlkDims]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.003 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.004 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronValueNumbering]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.002 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.003 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.004 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerTranspose]: Running LowerTranspose
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerTranspose]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.000 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerBroadcast]: Running LowerBroadcast
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerBroadcast]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.000 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LateNeuronInstComb]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SpillPSum]: Running SpillPSum
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SpillPSum]: Finished (changed=False)
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/SpillPSum]: SpillPSum finished after 0.001 seconds
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics
|
|
2025-11-09T20:56:46Z INFO 750 [cumsum/Tensorizer/LowerIntrinsics]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.000 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/LegalizeType]: Running LegalizeType
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/LegalizeType]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/LegalizeType]: LegalizeType finished after 0.001 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/NeuronLICM]: Running NeuronLICM
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/NeuronLICM]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.001 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/InferPSumTensor]: Running InferPSumTensor
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 0.001 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/InferPSumTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 0.001 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/WeightCoalescing]: Running WeightCoalescing
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/WeightCoalescing]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.000 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/LegalizeSundaAccess]: Finished (changed=True)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.003 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.007 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/ExpandISAMacro]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.001 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.000 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/SimplifyNeuronTensor]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.001 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/DMALocalityOpt]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.000 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/DataStreaming]: Running DataStreaming
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/DataStreaming]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/DataStreaming]: DataStreaming finished after 0.000 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/SFKVectorizer]: Running SFKVectorizer
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 0.000 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/SFKVectorizer]: Finished (changed=True)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 0.007 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/LateLegalizeInst]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.001 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/CoalesceCCOp]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.000 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/SimpleAllReduceTiling]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.000 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/InsertCoreBarrier]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.001 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/DMAProfiler]: Running DMAProfiler
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs:
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/DMAProfiler]: Est. DMA time: 5.852us (1.000MiB, est bw: 179.191GB/s, 59.288% of tot. time) for float32<128 x 2048> TongaSB partitions[0] float32 (128, 2048) %13[i0.128,i1.2048] = load float32<128 x 2048> float32 (1, 256) %'x'[i0.128,i1.2048] # id=8, src_id=None, , instances=1 # dl = tensor_op_name: | if i0.128 == 0 and -i1.2048+255 >= 0 [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/DMAProfiler]: Est. DMA time: 4.018us (1.000MiB, est bw: 260.951GB/s, 40.712% of tot. time) for float32<128 x 2048> float32 (1, 256) %'y'[i0.128,i1.2048] = store float32<128 x 2048> TongaSB partitions[0] float32 (128, 2048) %11[i0.128,i1.2048] # id=10, src_id=None, , instances=1 # dl = tensor_op_name: | if i0.128 == 0 and -i1.2048+255 >= 0 [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]]
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/DMAProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.002 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:47Z INFO 750 [cumsum/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.000 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/OptimizeNKIKernels]: Finished (changed=True)
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/OptimizeNKIKernels]: OptimizeNKIKernels finished after 11.523 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: Running CCOpFusion
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: Running CCOpFusion_iteration_0
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: CCOpFusion_iteration_0 finished after 0.106 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: CCOpFusion finished after 0.107 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/StaticProfiler]: Running StaticProfiler
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/StaticProfiler]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/StaticProfiler]: StaticProfiler finished after 0.072 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/SplitAPUnionSets]: Running SplitAPUnionSets
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/SplitAPUnionSets]: Finished (changed=True)
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/SplitAPUnionSets]: SplitAPUnionSets finished after 0.119 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/LateLegalizePostSplit]: Running LateLegalizePostSplit
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/LateLegalizePostSplit]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/LateLegalizePostSplit]: LateLegalizePostSplit finished after 0.056 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/InferSharedMemLoc]: Finished (changed=True)
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.022 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/LowerShardAxis]: Running LowerShardAxis
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/LowerShardAxis]: Finished (changed=True)
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/LowerShardAxis]: LowerShardAxis finished after 0.114 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: Running CCOpFusion
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: Running CCOpFusion_iteration_0
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: CCOpFusion_iteration_0 finished after 0.204 seconds
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: Finished (changed=False)
|
|
2025-11-09T20:56:47Z INFO 750 [sg0002/Tensorizer/CCOpFusion]: CCOpFusion finished after 0.206 seconds
|
|
2025-11-09T20:56:48Z INFO 750 [sg0002/Tensorizer/DumpGraphAndMetadata]: Running DumpGraphAndMetadata
|
|
2025-11-09T20:56:48Z INFO 750 [sg0002/Tensorizer/DumpGraphAndMetadata]: Finished (changed=False)
|
|
2025-11-09T20:56:48Z INFO 750 [sg0002/Tensorizer/DumpGraphAndMetadata]: DumpGraphAndMetadata finished after 0.262 seconds
|
|
2025-11-09T20:56:48Z INFO 750 [sg0002/Tensorizer/ZeroSizeTensorElimination]: Running ZeroSizeTensorElimination
|
|
2025-11-09T20:56:48Z INFO 750 [sg0002/Tensorizer/ZeroSizeTensorElimination]: Finished (changed=False)
|
|
2025-11-09T20:56:48Z INFO 750 [sg0002/Tensorizer/ZeroSizeTensorElimination]: ZeroSizeTensorElimination finished after 0.001 seconds
|
|
2025-11-09T20:56:48Z INFO 750 [sg0002/Tensorizer/LowerToSendRecv]: Running LowerToSendRecv
|
|
2025-11-09T20:56:48Z INFO 750 [sg0002/Tensorizer/LowerToSendRecv]: Finished (changed=True)
|
|
2025-11-09T20:56:48Z INFO 750 [sg0002/Tensorizer/LowerToSendRecv]: LowerToSendRecv finished after 0.188 seconds
|
|
2025-11-09T20:56:48Z INFO 750 [sg0002/Tensorizer/BirCodeGenLoop]: Running BirCodeGenLoop
|
|
2025-11-09T20:56:49Z INFO 750 [sg0002/Tensorizer/BirCodeGenLoop]: Finished (changed=False)
|
|
2025-11-09T20:56:50Z INFO 750 [sg0002/Tensorizer/BirCodeGenLoop]: BirCodeGenLoop finished after 1.403 seconds
|
|
2025-11-09T20:56:51Z INFO 750 [Tensorizer]: BirCodeGen estimate #instances=14853 in sg0002
|
|
2025-11-09T20:56:51Z INFO 750 [Tensorizer]: IR signature: 85ced9ba5fd95efbd79ceaf67928cade35e73184a981994b4d0ce7f09deea312 for nc00/sg0002/TensorizerBIR
|
|
2025-11-09T20:56:51Z INFO 750 [sg0002/Tensorizer/BirCodeGenLoop]: Running BirCodeGenLoop
|
|
2025-11-09T20:56:56Z INFO 750 [sg0002/Tensorizer/BirCodeGenLoop]: Finished (changed=False)
|
|
2025-11-09T20:56:56Z INFO 750 [sg0002/Tensorizer/BirCodeGenLoop]: BirCodeGenLoop finished after 5.176 seconds
|
|
2025-11-09T20:56:58Z INFO 750 [Tensorizer]: BirCodeGen estimate #instances=14853 in sg0002
|
|
2025-11-09T20:56:58Z INFO 750 [Tensorizer]: IR signature: cdc3ae2750683f7e5525e75a0bafd79eae6a1c0b01bf7ad12da6e789f8276c3f for nc01/sg0002/TensorizerBIR
|
|
2025-11-09T20:56:58Z INFO 750 [Tensorizer]: Weights total number of bytes: 262536
|
|
2025-11-09T20:56:58Z INFO 750 [Tensorizer]: Successfully built model.
|
|
2025-11-09T20:56:59Z USER 550 [root/Tensorizer/Tensorizer]: Tensorizer finished after 67.140 seconds
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: End tensorization
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input60
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input0
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input63
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input67
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input66
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input1
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input65
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input64
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input62
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input61
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input4
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input2
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input5
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input70
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input71
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input69
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input68
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input74
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input78
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input77
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input76
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input75
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input73
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input72
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input6
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input2
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input7
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input367
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input368
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input366
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input365
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input370
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input1
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input369
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: Network input: input3
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: wrote bir.json
|
|
2025-11-09T20:56:59Z INFO 550 [job.Frontend.0]: wrote tensor_map.json
|
|
2025-11-09T20:57:00Z INFO 550 [job.Frontend.0]: wrote bir.json
|
|
2025-11-09T20:57:00Z INFO 550 [job.Frontend.0]: wrote tensor_map.json
|
|
2025-11-09T20:57:00Z INFO 550 [job.Frontend.0]: wrote bir.json
|
|
2025-11-09T20:57:00Z INFO 550 [job.Frontend.0]: wrote tensor_map.json
|
|
2025-11-09T20:57:00Z INFO 550 [job.Frontend.0]: wrote bir.json
|
|
2025-11-09T20:57:00Z INFO 550 [job.Frontend.0]: wrote tensor_map.json
|
|
2025-11-09T20:57:01Z INFO 550 [job.Frontend.0]: wrote bir.json
|
|
2025-11-09T20:57:01Z INFO 550 [job.Frontend.0]: wrote tensor_map.json
|
|
2025-11-09T20:57:01Z INFO 550 [job.Frontend.0]: wrote bir.json
|
|
2025-11-09T20:57:01Z INFO 550 [job.Frontend.0]: wrote tensor_map.json
|
|
2025-11-09T20:57:02Z INFO 550 [job.Frontend.0]: Job #0 finished
|
|
2025-11-09T20:57:02Z INFO 550 [pipeline.Pipeline.0]: Finished job job.Frontend.0
|
|
2025-11-09T20:57:02Z INFO 550 [pipeline.Pipeline.0]: Starting job job.StaticIOTranspose.0
|
|
2025-11-09T20:57:02Z INFO 550 [pipeline.Pipeline.0]: Finished job job.StaticIOTranspose.0
|
|
2025-11-09T20:57:02Z INFO 550 [pipeline.Pipeline.0]: Starting job job.WalrusDriver.0
|
|
2025-11-09T20:57:02Z INFO 550 [job.WalrusDriver.0]: BackendDriver has 6 states with 2 core LNC
|
|
2025-11-09T20:57:02Z INFO 550 [job.WalrusDriver.0]: BackendDriver VNC cwd: /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/neuronxcc-u_vl19it
|
|
2025-11-09T20:57:02Z INFO 550 [job.WalrusDriver.0]: BackendDriver: found partitions within VNC, using VNC + MT modular flow.
|
|
2025-11-09T20:57:02Z INFO 550 [job.BIRLinker.1]: Creating directory nc00/sgLnk/sg00
|
|
2025-11-09T20:57:02Z INFO 550 [job.BIRLinker.2]: Creating directory nc01/sgLnk/sg00
|
|
2025-11-09T20:57:03Z INFO 550 [job.WalrusDriver.0]: BackendDriver in_state.num_states 6 with 2 core LNC
|
|
2025-11-09T20:57:03Z INFO 550 [job.WalrusDriver.0]: Executing /opt/conda/lib/python3.11/site-packages/neuronxcc/starfish/bin/walrus_driver --optlevel 2 --allocator coloring --verbose 35 --logfile-verbose 20 --logfile /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/log-neuron-cc.txt -o walrus_bir.out.json --enable-call-graph --enable-mt-backend --link-subgraphs nc00/sg00,nc01/sg00,nc00/sg01,nc01/sg01,nc00/sg02,nc01/sg02 --link-dir sgLnk/sg00 --vnc-nc-per-sengine 2 --execute-repetition 1 -i bir.json --min_split_size 10240 --skip_split_vns '' --no_split_dram --split_huge_dram_tensor 1.0 --preprocessing_only --max_tensorizer_distance 64 --pack_same_shape_only --instruction_fetch_latency 511 --max-partitions 1 --policy 3 --auxflag 0 --interleave none --schedule-delayed-latency 1 --postsched-mm-accum-reorder=false --max-load-lower-bound 0.14 --force-prefetch-follow-incoming-order -1 --allreduce-buffer-size 500 --dram-page-size 512 --dram-rotation-size -1 --allreduce-rotation-dis 8 --repeat-load-thres 4 --enable-mm-transpose-remat-optimization=true --save-len-thres 512 --save-dma-cnt-thres 32 --print-format json --relaxed-order=true --enable-anti-dependence-reduction=false --num-semaphores-per-queue 16 --numcores 1 --act-root-json /opt/conda/lib/python3.11/site-packages/neuronxcc/pwp/pwp_bin_trainium/act_info.json --dve-root-json /opt/conda/lib/python3.11/site-packages/neuronxcc/dve/dve_bin_gen3/dve_info.json --enable-verifier=true --enable-birsim=false --enable-birsim-sync-only=false --enable-data-race-checker=false --enable-new-backend=true --inject-error=NONE --enable-internal-partitioner --dge-levels spill_reload,scalar_dynamic_offset,io,vector_dynamic_offsets --dynamic-dma-scratch-size-per-partition=16384 --neff-output-filename /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/model.MODULE_e6b44ff520e6c4333666+e9aa1481.neff
|
|
2025-11-09T20:57:03Z INFO 550 [job.WalrusDriver.0]: Working directory is /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/neuronxcc-u_vl19it
|
|
2025-11-09T20:57:03Z INFO 550 [job.WalrusDriver.0]: propagate_exit=True
|
|
2025-11-09T20:57:03Z INFO 550 [job.WalrusDriver.0]: use_logger=False
|
|
2025-11-09T20:57:03Z INFO 550 [job.WalrusDriver.0]: expose_stderr=True
|
|
2025-11-09T20:57:04Z INFO 796 [Logging]: Logging to ../log-neuron-cc.txt at level 'INFO'
|
|
2025-11-09T20:57:04Z INFO 796 [BackendDriver]: max_allowed_parallelism=12
|
|
2025-11-09T20:57:04Z INFO 796 [BackendDriver]: Loading module from nc00/sg00/bir.json
|
|
2025-11-09T20:57:04Z INFO 796 [BackendDriver]: Loading module from nc01/sg01/bir.json
|
|
2025-11-09T20:57:04Z INFO 796 [BackendDriver]: Loading module from nc00/sg02/bir.json
|
|
2025-11-09T20:57:04Z INFO 796 [BackendDriver]: Loading module from nc01/sg02/bir.json
|
|
2025-11-09T20:57:04Z INFO 796 [BackendDriver]: Loading module from nc01/sg00/bir.json
|
|
2025-11-09T20:57:04Z INFO 796 [BackendDriver]: Loading module from nc00/sg01/bir.json
|
|
2025-11-09T20:57:05Z INFO 796 [BackendDriver]: Backend driver mtBackend: true numModules: 6 Cwd: "/models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/neuronxcc-u_vl19it"
|
|
2025-11-09T20:57:05Z INFO 796 [BackendDriver]: DynamicDMA is enabled
|
|
2025-11-09T20:57:05Z INFO 796 [BackendDriver]: DynamicDMA levels being enabled: io, spill_reload, scalar_dynamic_offset, vector_dynamic_offsets,
|
|
2025-11-09T20:57:05Z INFO 796 [BackendDriver]: Modular flow call graph is enabled
|
|
2025-11-09T20:57:05Z INFO 796 [BackendDriver]: Internal partitioner is enabled
|
|
2025-11-09T20:57:05Z USER 796 [BackendPassManager]: Running mod_parallel_pass
|
|
2025-11-09T20:57:05Z INFO 796 [BackendPassManager]: Inputs to mod_parallel_pass: modules=6 functions=6 allocs=1894 blocks=6 instructions=1640 Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:05Z USER 796 (nc01/sg02) [ModuleForkPass]: Running do_nothing
|
|
2025-11-09T20:57:05Z USER 796 (nc00/sg02) [ModuleForkPass]: Running do_nothing
|
|
2025-11-09T20:57:05Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to do_nothing: modules=1 functions=1 allocs=588 blocks=1 instructions=681 Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:05Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to do_nothing: modules=1 functions=1 allocs=588 blocks=1 instructions=681 Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:05Z USER 796 (nc00/sg02) [ModuleForkPass]: do_nothing finished after 0.005 seconds
|
|
2025-11-09T20:57:05Z USER 796 (nc01/sg02) [ModuleForkPass]: do_nothing finished after 0.005 seconds
|
|
2025-11-09T20:57:05Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 90mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:05Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 588 memory location(s), 1 block(s), and 681 instruction(s). Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:05Z USER 796 (nc01/sg02) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:06Z USER 796 (nc01/sg00) [ModuleForkPass]: Running do_nothing
|
|
2025-11-09T20:57:06Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=588 blocks=1 instructions=681 Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:06Z USER 796 (nc00/sg01) [ModuleForkPass]: Running do_nothing
|
|
2025-11-09T20:57:06Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to do_nothing: modules=1 functions=1 allocs=209 blocks=1 instructions=72 Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to do_nothing: modules=1 functions=1 allocs=150 blocks=1 instructions=67 Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:06Z USER 796 (nc00/sg01) [ModuleForkPass]: do_nothing finished after 0.004 seconds
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 91mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 91mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 150 memory location(s), 1 block(s), and 67 instruction(s). Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:06Z USER 796 (nc00/sg01) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=150 blocks=1 instructions=67 Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 588 memory location(s), 1 block(s), and 681 instruction(s). Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:06Z USER 796 (nc00/sg02) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=588 blocks=1 instructions=681 Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:06Z USER 796 (nc00/sg00) [ModuleForkPass]: Running do_nothing
|
|
2025-11-09T20:57:06Z USER 796 (nc01/sg01) [ModuleForkPass]: Running do_nothing
|
|
2025-11-09T20:57:06Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to do_nothing: modules=1 functions=1 allocs=150 blocks=1 instructions=67 Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:06Z USER 796 (nc01/sg01) [ModuleForkPass]: do_nothing finished after 0.003 seconds
|
|
2025-11-09T20:57:06Z USER 796 (nc01/sg00) [ModuleForkPass]: do_nothing finished after 0.004 seconds
|
|
2025-11-09T20:57:06Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 91mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:06Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 91mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:06Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 209 memory location(s), 1 block(s), and 72 instruction(s). Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:06Z USER 796 (nc01/sg00) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:06Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=209 blocks=1 instructions=72 Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to do_nothing: modules=1 functions=1 allocs=209 blocks=1 instructions=72 Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:06Z USER 796 (nc00/sg00) [ModuleForkPass]: do_nothing finished after 0.009 seconds
|
|
2025-11-09T20:57:06Z WARNING 796 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {convert.232.2325}@SB<0,0>(1x2)#Internal DebugInfo: <convert.232.2325||UNDEF||[1, 1, 1]>
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 91mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 209 memory location(s), 1 block(s), and 72 instruction(s). Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:06Z USER 796 (nc00/sg00) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=209 blocks=1 instructions=72 Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:06Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 150 memory location(s), 1 block(s), and 67 instruction(s). Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:06Z USER 796 (nc01/sg01) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:06Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=150 blocks=1 instructions=67 Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:06Z WARNING 796 [birverifier::InstVisitor]: (nc00/sg00) Non - output memory location with no reader: {convert.232.2325}@SB<0,0>(1x2)#Internal DebugInfo: <convert.232.2325||UNDEF||[1, 1, 1]>
|
|
2025-11-09T20:57:06Z USER 796 (nc00/sg00) [ModuleForkPass]: birverifier finished after 0.404 seconds
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 104mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 209 memory location(s), 1 block(s), and 72 instruction(s). Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:06Z USER 796 (nc01/sg00) [ModuleForkPass]: birverifier finished after 0.423 seconds
|
|
2025-11-09T20:57:06Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 107mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:06Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 209 memory location(s), 1 block(s), and 72 instruction(s). Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:06Z USER 796 (nc01/sg01) [ModuleForkPass]: birverifier finished after 0.496 seconds
|
|
2025-11-09T20:57:06Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 113mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:06Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 150 memory location(s), 1 block(s), and 67 instruction(s). Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:06Z USER 796 (nc00/sg01) [ModuleForkPass]: birverifier finished after 0.830 seconds
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 129mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:06Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 150 memory location(s), 1 block(s), and 67 instruction(s). Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:07Z USER 796 (nc00/sg02) [ModuleForkPass]: birverifier finished after 1.515 seconds
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 154mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 588 memory location(s), 1 block(s), and 681 instruction(s). Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:07Z USER 796 (nc01/sg02) [ModuleForkPass]: birverifier finished after 1.684 seconds
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 155mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 588 memory location(s), 1 block(s), and 681 instruction(s). Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:07Z USER 796 [ModuleForkPass]: Compilation status: Total modules: 6, Passed: 6, Failed: 0
|
|
2025-11-09T20:57:07Z USER 796 [BackendPassManager]: mod_parallel_pass finished after 1.803 seconds
|
|
2025-11-09T20:57:07Z INFO 796 [BackendPassManager]: curr_vmrss: 155mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:07Z USER 796 [BackendPassManager]: Running subgraph_parallel_pass
|
|
2025-11-09T20:57:07Z INFO 796 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=6 functions=6 allocs=1894 blocks=6 instructions=1640 Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:07Z USER 796 (sg00) [SubgraphForkPass]: Running lnc_verifier
|
|
2025-11-09T20:57:07Z USER 796 (sg01) [SubgraphForkPass]: Running lnc_verifier
|
|
2025-11-09T20:57:07Z USER 796 (sg02) [SubgraphForkPass]: Running lnc_verifier
|
|
2025-11-09T20:57:07Z INFO 796 (sg01) [SubgraphForkPass]: Inputs to lnc_verifier: modules=2 functions=2 allocs=300 blocks=2 instructions=134 Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:07Z USER 796 (sg01) [SubgraphForkPass]: lnc_verifier finished after 0.007 seconds
|
|
2025-11-09T20:57:07Z INFO 796 (sg01) [SubgraphForkPass]: curr_vmrss: 155mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:07Z INFO 796 (sg01) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 300 memory location(s), 2 block(s), and 134 instruction(s). Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:07Z INFO 796 (sg02) [SubgraphForkPass]: Inputs to lnc_verifier: modules=2 functions=2 allocs=1176 blocks=2 instructions=1362 Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:07Z INFO 796 (sg00) [SubgraphForkPass]: Inputs to lnc_verifier: modules=2 functions=2 allocs=418 blocks=2 instructions=144 Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:07Z USER 796 (sg00) [SubgraphForkPass]: lnc_verifier finished after 0.019 seconds
|
|
2025-11-09T20:57:07Z INFO 796 (sg00) [SubgraphForkPass]: curr_vmrss: 155mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:07Z USER 796 (sg02) [SubgraphForkPass]: lnc_verifier finished after 0.082 seconds
|
|
2025-11-09T20:57:07Z INFO 796 (sg02) [SubgraphForkPass]: curr_vmrss: 155mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:07Z INFO 796 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 418 memory location(s), 2 block(s), and 144 instruction(s). Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:07Z INFO 796 (sg02) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 1176 memory location(s), 2 block(s), and 1362 instruction(s). Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:07Z USER 796 [SubgraphForkPass]: Compilation status: Total subgraphs: 3, Passed: 3, Failed: 0
|
|
2025-11-09T20:57:07Z USER 796 [BackendPassManager]: subgraph_parallel_pass finished after 0.196 seconds
|
|
2025-11-09T20:57:07Z INFO 796 [BackendPassManager]: curr_vmrss: 155mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:07Z USER 796 [BackendPassManager]: Running mod_parallel_pass
|
|
2025-11-09T20:57:07Z INFO 796 [BackendPassManager]: Inputs to mod_parallel_pass: modules=6 functions=6 allocs=1894 blocks=6 instructions=1640 Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:07Z USER 796 (nc01/sg00) [ModuleForkPass]: Running expand_replication
|
|
2025-11-09T20:57:07Z USER 796 (nc01/sg02) [ModuleForkPass]: Running expand_replication
|
|
2025-11-09T20:57:07Z USER 796 (nc00/sg01) [ModuleForkPass]: Running expand_replication
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to expand_replication: modules=1 functions=1 allocs=150 blocks=1 instructions=67 Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg01) [ExpandReplication]: Found 0 replicated matmults
|
|
2025-11-09T20:57:07Z USER 796 (nc00/sg01) [ModuleForkPass]: expand_replication finished after 0.002 seconds
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 155mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:07Z USER 796 (nc00/sg02) [ModuleForkPass]: Running expand_replication
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to expand_replication: modules=1 functions=1 allocs=209 blocks=1 instructions=72 Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 150 memory location(s), 1 block(s), and 67 instruction(s). Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:07Z USER 796 (nc00/sg01) [ModuleForkPass]: Running unroll
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to unroll: modules=1 functions=1 allocs=150 blocks=1 instructions=67 Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to expand_replication: modules=1 functions=1 allocs=588 blocks=1 instructions=681 Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg01) [Unroll]: INFO (Unroll) Start unrolling at Sun Nov 9 20:57:07 2025
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg00) [ExpandReplication]: Found 0 replicated matmults
|
|
2025-11-09T20:57:07Z USER 796 (nc01/sg00) [ModuleForkPass]: expand_replication finished after 0.003 seconds
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 155mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 209 memory location(s), 1 block(s), and 72 instruction(s). Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:07Z USER 796 (nc01/sg00) [ModuleForkPass]: Running unroll
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to unroll: modules=1 functions=1 allocs=209 blocks=1 instructions=72 Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg00) [Unroll]: INFO (Unroll) Start unrolling at Sun Nov 9 20:57:07 2025
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to expand_replication: modules=1 functions=1 allocs=588 blocks=1 instructions=681 Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg02) [ExpandReplication]: Found 0 replicated matmults
|
|
2025-11-09T20:57:07Z USER 796 (nc01/sg02) [ModuleForkPass]: expand_replication finished after 0.004 seconds
|
|
2025-11-09T20:57:07Z USER 796 (nc01/sg01) [ModuleForkPass]: Running expand_replication
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 159mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg02) [ExpandReplication]: Found 0 replicated matmults
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to expand_replication: modules=1 functions=1 allocs=150 blocks=1 instructions=67 Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:07Z USER 796 (nc00/sg02) [ModuleForkPass]: expand_replication finished after 0.073 seconds
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg01) [ExpandReplication]: Found 0 replicated matmults
|
|
2025-11-09T20:57:07Z USER 796 (nc01/sg01) [ModuleForkPass]: expand_replication finished after 0.002 seconds
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 588 memory location(s), 1 block(s), and 681 instruction(s). Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:07Z USER 796 (nc01/sg02) [ModuleForkPass]: Running unroll
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 159mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 150 memory location(s), 1 block(s), and 67 instruction(s). Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:07Z USER 796 (nc01/sg01) [ModuleForkPass]: Running unroll
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to unroll: modules=1 functions=1 allocs=150 blocks=1 instructions=67 Max writers: 4 Max Readers: 8
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to unroll: modules=1 functions=1 allocs=588 blocks=1 instructions=681 Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg01) [Unroll]: INFO (Unroll) Start unrolling at Sun Nov 9 20:57:07 2025
|
|
2025-11-09T20:57:07Z INFO 796 (nc01/sg02) [Unroll]: INFO (Unroll) Start unrolling at Sun Nov 9 20:57:07 2025
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 160mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 588 memory location(s), 1 block(s), and 681 instruction(s). Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:07Z USER 796 (nc00/sg02) [ModuleForkPass]: Running unroll
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to unroll: modules=1 functions=1 allocs=588 blocks=1 instructions=681 Max writers: 65 Max Readers: 64
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg02) [Unroll]: INFO (Unroll) Start unrolling at Sun Nov 9 20:57:07 2025
|
|
2025-11-09T20:57:07Z USER 796 (nc00/sg00) [ModuleForkPass]: Running expand_replication
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to expand_replication: modules=1 functions=1 allocs=209 blocks=1 instructions=72 Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg00) [ExpandReplication]: Found 0 replicated matmults
|
|
2025-11-09T20:57:07Z USER 796 (nc00/sg00) [ModuleForkPass]: expand_replication finished after 0.001 seconds
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 161mb, ru_maxrss: 221mb (delta=0mb)
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 209 memory location(s), 1 block(s), and 72 instruction(s). Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:07Z USER 796 (nc00/sg00) [ModuleForkPass]: Running unroll
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to unroll: modules=1 functions=1 allocs=209 blocks=1 instructions=72 Max writers: 4 Max Readers: 9
|
|
2025-11-09T20:57:07Z INFO 796 (nc00/sg00) [Unroll]: INFO (Unroll) Start unrolling at Sun Nov 9 20:57:07 2025
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: INFO (Unroll) DONE unrolling Sun Nov 9 20:57:07 2025
|
|
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: sg0000 Instruction count after Unroll:
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: Total count: 1629
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: Matmult: 725
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: TensorScalarPtr: 250
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: TensorTensor: 220
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: GenericCopy: 164
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: Activation: 86
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: DMACopy: 65
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: Save: 49
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: Load: 43
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: Memset: 10
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: StreamShuffle: 8
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: CoreBarrier: 4
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: CollectiveCompute: 3
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: Select: 1
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: BIRKernel: 1
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [Unroll]: Unrolled DGE count with Dynamic AP: 64
|
|
2025-11-09T20:57:09Z USER 796 (nc00/sg00) [ModuleForkPass]: unroll finished after 1.485 seconds
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 234mb, ru_maxrss: 233mb (delta=12mb)
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1940 memory location(s), 1 block(s), and 1629 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:09Z USER 796 (nc00/sg00) [ModuleForkPass]: Running dead_code_elim_o1
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to dead_code_elim_o1: modules=1 functions=1 allocs=1940 blocks=1 instructions=1629 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [DeadCodeElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: INFO (Unroll) DONE unrolling Sun Nov 9 20:57:07 2025
|
|
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: sg0000 Instruction count after Unroll:
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: Total count: 1627
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: Matmult: 725
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: TensorScalarPtr: 250
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: TensorTensor: 220
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: GenericCopy: 164
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: Activation: 86
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: DMACopy: 64
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: Save: 48
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: Load: 43
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: Memset: 10
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: StreamShuffle: 8
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: CoreBarrier: 4
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: CollectiveCompute: 3
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: Select: 1
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: BIRKernel: 1
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [Unroll]: Unrolled DGE count with Dynamic AP: 64
|
|
2025-11-09T20:57:09Z USER 796 (nc01/sg00) [ModuleForkPass]: unroll finished after 1.686 seconds
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 236mb, ru_maxrss: 235mb (delta=14mb)
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1940 memory location(s), 1 block(s), and 1627 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [DeadCodeElim]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [DeadCodeElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [DeadCodeElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:09Z USER 796 (nc01/sg00) [ModuleForkPass]: Running dead_code_elim_o1
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to dead_code_elim_o1: modules=1 functions=1 allocs=1940 blocks=1 instructions=1627 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:09Z USER 796 (nc00/sg00) [ModuleForkPass]: dead_code_elim_o1 finished after 0.290 seconds
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 242mb, ru_maxrss: 240mb (delta=7mb)
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 921 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [DeadCodeElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: INFO (Unroll) DONE unrolling Sun Nov 9 20:57:07 2025
|
|
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [DeadCodeElim]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [DeadCodeElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [DeadCodeElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: sg0001 Instruction count after Unroll:
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: Total count: 2930
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: Matmult: 2060
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: GenericCopy: 179
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: TensorTensor: 168
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: TensorScalarPtr: 160
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: Load: 140
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: Activation: 116
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: Save: 45
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: DMACopy: 34
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: Memset: 12
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: StreamShuffle: 8
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: CoreBarrier: 4
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: CollectiveCompute: 2
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: Select: 1
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: BIRKernel: 1
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [Unroll]: Unrolled DGE count with Dynamic AP: 32
|
|
2025-11-09T20:57:09Z USER 796 (nc00/sg01) [ModuleForkPass]: unroll finished after 1.999 seconds
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 240mb, ru_maxrss: 240mb (delta=19mb)
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1897 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:09Z USER 796 (nc00/sg01) [ModuleForkPass]: Running dead_code_elim_o1
|
|
2025-11-09T20:57:09Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to dead_code_elim_o1: modules=1 functions=1 allocs=1897 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:09Z USER 796 (nc01/sg00) [ModuleForkPass]: dead_code_elim_o1 finished after 0.320 seconds
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 235mb, ru_maxrss: 240mb (delta=4mb)
|
|
2025-11-09T20:57:09Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:10Z INFO 796 (nc00/sg01) [DeadCodeElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: INFO (Unroll) DONE unrolling Sun Nov 9 20:57:07 2025
|
|
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: sg0001 Instruction count after Unroll:
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: Total count: 2928
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: Matmult: 2060
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: GenericCopy: 179
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: TensorTensor: 168
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: TensorScalarPtr: 160
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: Load: 140
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: Activation: 116
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: Save: 44
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: DMACopy: 33
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: Memset: 12
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: StreamShuffle: 8
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: CoreBarrier: 4
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: CollectiveCompute: 2
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: Select: 1
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: BIRKernel: 1
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [Unroll]: Unrolled DGE count with Dynamic AP: 32
|
|
2025-11-09T20:57:10Z USER 796 (nc01/sg01) [ModuleForkPass]: unroll finished after 2.212 seconds
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 238mb, ru_maxrss: 240mb (delta=19mb)
|
|
2025-11-09T20:57:10Z INFO 796 (nc00/sg01) [DeadCodeElim]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:10Z INFO 796 (nc00/sg01) [DeadCodeElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1897 memory location(s), 1 block(s), and 2928 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:10Z USER 796 (nc01/sg01) [ModuleForkPass]: Running dead_code_elim_o1
|
|
2025-11-09T20:57:10Z INFO 796 (nc00/sg01) [DeadCodeElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to dead_code_elim_o1: modules=1 functions=1 allocs=1897 blocks=1 instructions=2928 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:10Z USER 796 (nc00/sg01) [ModuleForkPass]: dead_code_elim_o1 finished after 0.314 seconds
|
|
2025-11-09T20:57:10Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 241mb, ru_maxrss: 240mb (delta=0mb)
|
|
2025-11-09T20:57:10Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [DeadCodeElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [DeadCodeElim]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [DeadCodeElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [DeadCodeElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:10Z USER 796 (nc01/sg01) [ModuleForkPass]: dead_code_elim_o1 finished after 0.377 seconds
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 257mb, ru_maxrss: 255mb (delta=15mb)
|
|
2025-11-09T20:57:10Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: INFO (Unroll) DONE unrolling Sun Nov 9 20:57:07 2025
|
|
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: sg0002 Instruction count after Unroll:
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: Total count: 8794
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: Matmult: 6646
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: GenericCopy: 900
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: Load: 298
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: Save: 174
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: TensorTensor: 135
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: Gather: 129
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: Max: 128
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: MaxIndexAndMatchReplace: 128
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: Activation: 95
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: TensorScalarPtr: 86
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: Memset: 26
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: CoreBarrier: 14
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: TensorReduce: 13
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: CollectiveCompute: 8
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: Select: 4
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: DMACopy: 4
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: Iota: 3
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: Reciprocal: 3
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [Unroll]: Unrolled DGE count with Dynamic AP: 3
|
|
2025-11-09T20:57:11Z USER 796 (nc01/sg02) [ModuleForkPass]: unroll finished after 3.415 seconds
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 289mb, ru_maxrss: 288mb (delta=67mb)
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 4000 memory location(s), 1 block(s), and 8794 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:11Z USER 796 (nc01/sg02) [ModuleForkPass]: Running dead_code_elim_o1
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to dead_code_elim_o1: modules=1 functions=1 allocs=4000 blocks=1 instructions=8794 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: INFO (Unroll) DONE unrolling Sun Nov 9 20:57:07 2025
|
|
|
|
2025-11-09T20:57:11Z INFO 796 (nc01/sg02) [DeadCodeElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: sg0002 Instruction count after Unroll:
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: Total count: 8806
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: Matmult: 6646
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: GenericCopy: 900
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: Load: 298
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: Save: 186
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: TensorTensor: 135
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: Gather: 129
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: Max: 128
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: MaxIndexAndMatchReplace: 128
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: Activation: 95
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: TensorScalarPtr: 86
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: Memset: 26
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: CoreBarrier: 14
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: TensorReduce: 13
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: CollectiveCompute: 8
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: Select: 4
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: DMACopy: 4
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: Iota: 3
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: Reciprocal: 3
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [Unroll]: Unrolled DGE count with Dynamic AP: 3
|
|
2025-11-09T20:57:11Z USER 796 (nc00/sg02) [ModuleForkPass]: unroll finished after 3.712 seconds
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 268mb, ru_maxrss: 288mb (delta=67mb)
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 4000 memory location(s), 1 block(s), and 8806 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:11Z USER 796 (nc00/sg02) [ModuleForkPass]: Running dead_code_elim_o1
|
|
2025-11-09T20:57:11Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to dead_code_elim_o1: modules=1 functions=1 allocs=4000 blocks=1 instructions=8806 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:12Z INFO 796 (nc01/sg02) [DeadCodeElim]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:12Z INFO 796 (nc01/sg02) [DeadCodeElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:12Z INFO 796 (nc01/sg02) [DeadCodeElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:12Z USER 796 (nc01/sg02) [ModuleForkPass]: dead_code_elim_o1 finished after 0.714 seconds
|
|
2025-11-09T20:57:12Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 246mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:12Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:12Z INFO 796 (nc00/sg02) [DeadCodeElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:12Z INFO 796 (nc00/sg02) [DeadCodeElim]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:12Z INFO 796 (nc00/sg02) [DeadCodeElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:12Z INFO 796 (nc00/sg02) [DeadCodeElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:13Z USER 796 (nc00/sg02) [ModuleForkPass]: dead_code_elim_o1 finished after 1.102 seconds
|
|
2025-11-09T20:57:13Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 246mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:13Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:13Z USER 796 [ModuleForkPass]: Compilation status: Total modules: 6, Passed: 6, Failed: 0
|
|
2025-11-09T20:57:13Z USER 796 [BackendPassManager]: mod_parallel_pass finished after 5.183 seconds
|
|
2025-11-09T20:57:13Z INFO 796 [BackendPassManager]: curr_vmrss: 246mb, ru_maxrss: 288mb (delta=67mb)
|
|
2025-11-09T20:57:13Z USER 796 [BackendPassManager]: Running subgraph_parallel_pass
|
|
2025-11-09T20:57:13Z INFO 796 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=6 functions=6 allocs=7660 blocks=6 instructions=25926 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:13Z USER 796 (sg01) [SubgraphForkPass]: Running localize_shared_memory
|
|
2025-11-09T20:57:13Z USER 796 (sg02) [SubgraphForkPass]: Running localize_shared_memory
|
|
2025-11-09T20:57:13Z INFO 796 (sg01) [SubgraphForkPass]: Inputs to localize_shared_memory: modules=2 functions=2 allocs=1857 blocks=2 instructions=5857 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:13Z USER 796 (sg00) [SubgraphForkPass]: Running localize_shared_memory
|
|
2025-11-09T20:57:13Z INFO 796 (sg00) [SubgraphForkPass]: Inputs to localize_shared_memory: modules=2 functions=2 allocs=1841 blocks=2 instructions=3253 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:13Z INFO 796 (sg02) [SubgraphForkPass]: Inputs to localize_shared_memory: modules=2 functions=2 allocs=3962 blocks=2 instructions=16816 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:13Z USER 796 (sg00) [SubgraphForkPass]: localize_shared_memory finished after 0.008 seconds
|
|
2025-11-09T20:57:13Z USER 796 (sg02) [SubgraphForkPass]: localize_shared_memory finished after 0.037 seconds
|
|
2025-11-09T20:57:13Z INFO 796 (sg00) [SubgraphForkPass]: curr_vmrss: 246mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:13Z USER 796 (sg01) [SubgraphForkPass]: localize_shared_memory finished after 0.100 seconds
|
|
2025-11-09T20:57:13Z INFO 796 (sg01) [SubgraphForkPass]: curr_vmrss: 246mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:13Z INFO 796 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 1837 memory location(s), 2 block(s), and 3253 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:13Z INFO 796 (sg01) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 1857 memory location(s), 2 block(s), and 5857 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:13Z INFO 796 (sg02) [SubgraphForkPass]: curr_vmrss: 246mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:13Z INFO 796 (sg02) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 3962 memory location(s), 2 block(s), and 16816 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:13Z USER 796 [SubgraphForkPass]: Compilation status: Total subgraphs: 3, Passed: 3, Failed: 0
|
|
2025-11-09T20:57:13Z USER 796 [BackendPassManager]: subgraph_parallel_pass finished after 0.220 seconds
|
|
2025-11-09T20:57:13Z INFO 796 [BackendPassManager]: curr_vmrss: 246mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:13Z USER 796 [BackendPassManager]: Running mod_parallel_pass
|
|
2025-11-09T20:57:13Z INFO 796 [BackendPassManager]: Inputs to mod_parallel_pass: modules=6 functions=6 allocs=7656 blocks=6 instructions=25926 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:13Z USER 796 (nc00/sg02) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:13Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:13Z USER 796 (nc01/sg02) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:13Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:13Z USER 796 (nc01/sg00) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:13Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:13Z USER 796 (nc00/sg00) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:13Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:13Z USER 796 (nc00/sg01) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:13Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:13Z USER 796 (nc01/sg01) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:13Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:13Z WARNING 796 [birverifier::InstVisitor]: (nc01/sg02) Non - output memory location with no reader: {divide.1_1259_i1}@SB<0,0>(1x1024)#Internal DebugInfo: <divide.1_1259||UNDEF||[1, 256, 1]>
|
|
2025-11-09T20:57:13Z WARNING 796 [birverifier::InstVisitor]: (nc01/sg02) Non - output memory location with no reader: {select.5_1264_i1}@SB<0,0>(1x1024)#Internal DebugInfo: <select.5_1264||UNDEF||[1, 256, 1]>
|
|
2025-11-09T20:57:13Z USER 796 (nc00/sg01) [ModuleForkPass]: birverifier finished after 0.518 seconds
|
|
2025-11-09T20:57:13Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 246mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:13Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:14Z USER 796 (nc01/sg01) [ModuleForkPass]: birverifier finished after 0.805 seconds
|
|
2025-11-09T20:57:14Z USER 796 (nc01/sg00) [ModuleForkPass]: birverifier finished after 0.906 seconds
|
|
2025-11-09T20:57:14Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 247mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:14Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 247mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:14Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:14Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:14Z USER 796 (nc00/sg00) [ModuleForkPass]: birverifier finished after 0.930 seconds
|
|
2025-11-09T20:57:14Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 247mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:14Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:14Z USER 796 (nc01/sg02) [ModuleForkPass]: birverifier finished after 1.430 seconds
|
|
2025-11-09T20:57:14Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 248mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:14Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:15Z USER 796 (nc00/sg02) [ModuleForkPass]: birverifier finished after 2.122 seconds
|
|
2025-11-09T20:57:15Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 251mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:15Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:15Z USER 796 [ModuleForkPass]: Compilation status: Total modules: 6, Passed: 6, Failed: 0
|
|
2025-11-09T20:57:15Z USER 796 [BackendPassManager]: mod_parallel_pass finished after 2.280 seconds
|
|
2025-11-09T20:57:15Z INFO 796 [BackendPassManager]: curr_vmrss: 251mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:15Z USER 796 [BackendPassManager]: Running subgraph_parallel_pass
|
|
2025-11-09T20:57:15Z INFO 796 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=6 functions=6 allocs=7656 blocks=6 instructions=25926 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:15Z USER 796 (sg00) [SubgraphForkPass]: Running lnc_verifier
|
|
2025-11-09T20:57:15Z USER 796 (sg01) [SubgraphForkPass]: Running lnc_verifier
|
|
2025-11-09T20:57:15Z INFO 796 (sg00) [SubgraphForkPass]: Inputs to lnc_verifier: modules=2 functions=2 allocs=1837 blocks=2 instructions=3253 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:15Z INFO 796 (sg01) [SubgraphForkPass]: Inputs to lnc_verifier: modules=2 functions=2 allocs=1857 blocks=2 instructions=5857 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:15Z USER 796 (sg02) [SubgraphForkPass]: Running lnc_verifier
|
|
2025-11-09T20:57:15Z INFO 796 (sg02) [SubgraphForkPass]: Inputs to lnc_verifier: modules=2 functions=2 allocs=3962 blocks=2 instructions=16816 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:15Z USER 796 (sg00) [SubgraphForkPass]: lnc_verifier finished after 0.015 seconds
|
|
2025-11-09T20:57:15Z INFO 796 (sg00) [SubgraphForkPass]: curr_vmrss: 251mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:15Z INFO 796 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 1837 memory location(s), 2 block(s), and 3253 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:15Z USER 796 (sg01) [SubgraphForkPass]: lnc_verifier finished after 0.106 seconds
|
|
2025-11-09T20:57:15Z INFO 796 (sg01) [SubgraphForkPass]: curr_vmrss: 251mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:15Z INFO 796 (sg01) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 1857 memory location(s), 2 block(s), and 5857 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:15Z USER 796 (sg02) [SubgraphForkPass]: lnc_verifier finished after 0.210 seconds
|
|
2025-11-09T20:57:15Z INFO 796 (sg02) [SubgraphForkPass]: curr_vmrss: 251mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:15Z INFO 796 (sg02) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 3962 memory location(s), 2 block(s), and 16816 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:15Z USER 796 [SubgraphForkPass]: Compilation status: Total subgraphs: 3, Passed: 3, Failed: 0
|
|
2025-11-09T20:57:15Z USER 796 [BackendPassManager]: subgraph_parallel_pass finished after 0.396 seconds
|
|
2025-11-09T20:57:15Z INFO 796 [BackendPassManager]: curr_vmrss: 251mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:15Z USER 796 [BackendPassManager]: Running mod_parallel_pass
|
|
2025-11-09T20:57:15Z INFO 796 [BackendPassManager]: Inputs to mod_parallel_pass: modules=6 functions=6 allocs=7656 blocks=6 instructions=25926 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:15Z USER 796 (nc00/sg02) [ModuleForkPass]: Running instruction_reorder
|
|
2025-11-09T20:57:15Z USER 796 (nc01/sg02) [ModuleForkPass]: Running instruction_reorder
|
|
2025-11-09T20:57:15Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to instruction_reorder: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:15Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to instruction_reorder: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:15Z USER 796 (nc01/sg00) [ModuleForkPass]: Running instruction_reorder
|
|
2025-11-09T20:57:15Z USER 796 (nc00/sg01) [ModuleForkPass]: Running instruction_reorder
|
|
2025-11-09T20:57:15Z USER 796 (nc00/sg00) [ModuleForkPass]: Running instruction_reorder
|
|
2025-11-09T20:57:15Z USER 796 (nc01/sg01) [ModuleForkPass]: Running instruction_reorder
|
|
2025-11-09T20:57:15Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to instruction_reorder: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:15Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to instruction_reorder: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:15Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to instruction_reorder: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:15Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to instruction_reorder: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:15Z USER 796 (nc01/sg00) [ModuleForkPass]: instruction_reorder finished after 0.005 seconds
|
|
2025-11-09T20:57:15Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:15Z USER 796 (nc00/sg00) [ModuleForkPass]: instruction_reorder finished after 0.005 seconds
|
|
2025-11-09T20:57:15Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:15Z USER 796 (nc01/sg00) [ModuleForkPass]: Running psum_legalization
|
|
2025-11-09T20:57:15Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to psum_legalization: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:15Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:15Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:15Z USER 796 (nc00/sg00) [ModuleForkPass]: Running psum_legalization
|
|
2025-11-09T20:57:15Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to psum_legalization: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:15Z USER 796 (nc00/sg00) [ModuleForkPass]: psum_legalization finished after 0.006 seconds
|
|
2025-11-09T20:57:15Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:15Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:15Z USER 796 (nc00/sg00) [ModuleForkPass]: Running non_ssa_legalization
|
|
2025-11-09T20:57:15Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:15Z INFO 796 (nc00/sg00) [NonSSALeg]: remove_redundant_loads
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg02) [ModuleForkPass]: instruction_reorder finished after 0.030 seconds
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: psum_legalization finished after 0.074 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: Running non_ssa_legalization
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [NonSSALeg]: remove_redundant_loads
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: instruction_reorder finished after 0.080 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: Running psum_legalization
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to psum_legalization: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [NonSSALeg]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [NonSSALeg]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [NonSSALeg]: [Non-SSA legalization]created 0 memorylocations
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: non_ssa_legalization finished after 0.076 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: Running legalize_cce_dma
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to legalize_cce_dma: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: legalize_cce_dma finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: Running pre_opts
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to pre_opts: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreOpts]: Skipped. No pre-opt passes enabled
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: pre_opts finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: Running error_injector
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to error_injector: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z WARNING 796 (nc00/sg00) [ErrorInjector]: Unrecognized injected error value "0"
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: error_injector finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: Running vn_splitter
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to vn_splitter: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [VNSplitter]: INFO (VNSplitter) Collected all the internal vnodes: size = 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [VNSplitter]: INFO (VNSplitter) Done with analyze and splitting: total dead nodes = 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: psum_legalization finished after 0.017 seconds
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg02) [ModuleForkPass]: Running psum_legalization
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to psum_legalization: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: instruction_reorder finished after 0.101 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: Running psum_legalization
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to psum_legalization: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ShrinkDN]: INFO (ShrinkDN): Shrunk 1 nodes. Total savings 448 bytes/partition
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: Running non_ssa_legalization
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [NonSSALeg]: remove_redundant_loads
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [NonSSALeg]: [Non-SSA legalization]created 0 memorylocations
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: non_ssa_legalization finished after 0.027 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: Running legalize_cce_dma
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to legalize_cce_dma: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: legalize_cce_dma finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: Running pre_opts
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to pre_opts: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreOpts]: Skipped. No pre-opt passes enabled
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: pre_opts finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: Running error_injector
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to error_injector: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z WARNING 796 (nc01/sg00) [ErrorInjector]: Unrecognized injected error value "0"
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: error_injector finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 [PerformanceProfiler]: number of tensorizer non-local-tensor caused reload left 0
|
|
2025-11-09T20:57:16Z INFO 796 [PerformanceProfiler]: number of tensorizer non-local-tensor caused spill left 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: Running vn_splitter
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to vn_splitter: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [VNSplitter]: INFO (VNSplitter) Collected all the internal vnodes: size = 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [VNSplitter]: INFO (VNSplitter) Done with analyze and splitting: total dead nodes = 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [VNSplitterPass]: INFO (VNSplitter) Time: 0 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [VNSplitterPass]: INFO (VerticalFusion) Time: 0.006 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [VNSplitterPass]: INFO (ShrinkDN) Time: 0.006 seconds
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: vn_splitter finished after 0.020 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: Running constant_propagate
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to constant_propagate: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ConstantPropagate]: [Constant_propagate for select] directly remove instruction number: 0
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: psum_legalization finished after 0.078 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: Running non_ssa_legalization
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [NonSSALeg]: remove_redundant_loads
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [NonSSALeg]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg02) [ModuleForkPass]: instruction_reorder finished after 0.195 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg02) [ModuleForkPass]: Running psum_legalization
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to psum_legalization: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ShrinkDN]: INFO (ShrinkDN): Shrunk 1 nodes. Total savings 448 bytes/partition
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [NonSSALeg]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ConstantPropagate]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [NonSSALeg]: [Non-SSA legalization]created 0 memorylocations
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: non_ssa_legalization finished after 0.102 seconds
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg02) [ModuleForkPass]: psum_legalization finished after 0.110 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: Running legalize_cce_dma
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to legalize_cce_dma: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: legalize_cce_dma finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg02) [ModuleForkPass]: Running non_ssa_legalization
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: Running pre_opts
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to pre_opts: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreOpts]: Skipped. No pre-opt passes enabled
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [NonSSALeg]: remove_redundant_loads
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: pre_opts finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: Running error_injector
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to error_injector: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z WARNING 796 (nc01/sg01) [ErrorInjector]: Unrecognized injected error value "0"
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: error_injector finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: Running vn_splitter
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to vn_splitter: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [VNSplitter]: INFO (VNSplitter) Collected all the internal vnodes: size = 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [VNSplitter]: INFO (VNSplitter) Done with analyze and splitting: total dead nodes = 0
|
|
2025-11-09T20:57:16Z INFO 796 [PerformanceProfiler]: number of tensorizer non-local-tensor caused reload left 0
|
|
2025-11-09T20:57:16Z INFO 796 [PerformanceProfiler]: number of tensorizer non-local-tensor caused spill left 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [VNSplitterPass]: INFO (VNSplitter) Time: 0 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [VNSplitterPass]: INFO (VerticalFusion) Time: 0.083 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [VNSplitterPass]: INFO (ShrinkDN) Time: 0.016 seconds
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: vn_splitter finished after 0.102 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: Running constant_propagate
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to constant_propagate: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ConstantPropagate]: [Constant_propagate for select] directly remove instruction number: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ConstantPropagate]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [NonSSALeg]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:16Z INFO 796 [PerformanceProfiler]: number of tensorizer non-local-tensor caused reload left 0
|
|
2025-11-09T20:57:16Z INFO 796 [PerformanceProfiler]: number of tensorizer non-local-tensor caused spill left 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [NonSSALeg]: [Non-SSA legalization]created 0 memorylocations
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [VNSplitterPass]: INFO (VNSplitter) Time: 0 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [VNSplitterPass]: INFO (VerticalFusion) Time: 0.07 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [VNSplitterPass]: INFO (ShrinkDN) Time: 0.007 seconds
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: vn_splitter finished after 0.169 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: Running constant_propagate
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to constant_propagate: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: non_ssa_legalization finished after 0.208 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: Running legalize_cce_dma
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to legalize_cce_dma: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ConstantPropagate]: [Constant_propagate for select] directly remove instruction number: 0
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: legalize_cce_dma finished after 0.003 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: Running pre_opts
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to pre_opts: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [PreOpts]: Skipped. No pre-opt passes enabled
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: pre_opts finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: Running error_injector
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to error_injector: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z WARNING 796 (nc00/sg01) [ErrorInjector]: Unrecognized injected error value "0"
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: error_injector finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: Running vn_splitter
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to vn_splitter: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [VNSplitter]: INFO (VNSplitter) Collected all the internal vnodes: size = 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [VNSplitter]: INFO (VNSplitter) Done with analyze and splitting: total dead nodes = 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ConstantPropagate]: [Constant_propagate for Affineselect] directly remove instruction number: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ConstantPropagate]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ConstantPropagate]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg02) [ModuleForkPass]: psum_legalization finished after 0.304 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg02) [ModuleForkPass]: Running non_ssa_legalization
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [NonSSALeg]: remove_redundant_loads
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: constant_propagate finished after 0.292 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: Running lower_ac
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to lower_ac: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [LowerAC]: INFO (LowerAC) Lowered 0 loads, 0 saves, 0 copies.
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 [PerformanceProfiler]: number of tensorizer non-local-tensor caused reload left 0
|
|
2025-11-09T20:57:16Z INFO 796 [PerformanceProfiler]: number of tensorizer non-local-tensor caused spill left 0
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: lower_ac finished after 0.074 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 252mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: Running input_dma_coalescing
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to input_dma_coalescing: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: DMA input Coalescing combined 0 input loads
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [NonSSALeg]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: input_dma_coalescing finished after 0.010 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: Running remat_optimization
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to remat_optimization: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ConstantPropagate]: [Constant_propagate for Affineselect] directly remove instruction number: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [RematOpt]: Removed 0 remat instructions
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: remat_optimization finished after 0.008 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ConstantPropagate]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: Running coalesce_multichannel_cc_ops
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to coalesce_multichannel_cc_ops: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: coalesce_multichannel_cc_ops finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: Running infer_stream_ids
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to infer_stream_ids: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: infer_stream_ids finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: Running pre_sched
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to pre_sched: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: Start PRE scheduling 2 cores: 1 at: Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: Start...
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: Found 1 Splits CCs
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: Grouped CCs to 1 clusters.
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: To Spill 0 multi-layer tensors
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: set uninit flag on 0 insts
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: Done.
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: Start split live ranges Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [VNSplitterPass]: INFO (VNSplitter) Time: 0 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [VNSplitterPass]: INFO (VerticalFusion) Time: 0.016 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [VNSplitterPass]: INFO (ShrinkDN) Time: 0.103 seconds
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: vn_splitter finished after 0.216 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: No split opportunities:
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: Running constant_propagate
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to constant_propagate: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: End split live ranges Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: Strt remove redundncies Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: remove_redundant_memsets
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: remove_redundant_memsets: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: remove_redundant_loads
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ConstantPropagate]: [Constant_propagate for Affineselect] directly remove instruction number: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: End remove redundncies Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: Start DCE Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ConstantPropagate]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: End DCE Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [NonSSALeg]: [Non-SSA legalization]created 0 memorylocations
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg02) [ModuleForkPass]: non_ssa_legalization finished after 0.481 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ConstantPropagate]: [Constant_propagate for select] directly remove instruction number: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg02) [ModuleForkPass]: Running legalize_cce_dma
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to legalize_cce_dma: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: constant_propagate finished after 0.315 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: Running lower_ac
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to lower_ac: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [LowerAC]: INFO (LowerAC) Lowered 0 loads, 0 saves, 0 copies.
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: lower_ac finished after 0.001 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: Running input_dma_coalescing
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to input_dma_coalescing: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: Start build flow dependencies Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [build_flow_deps]: Start build fdeps. Invocation: 1Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: DMA input Coalescing combined 0 input loads
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: input_dma_coalescing finished after 0.009 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [build_flow_deps]: Allocs: 918 instructions: 1625
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: Running remat_optimization
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to remat_optimization: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ConstantPropagate]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: constant_propagate finished after 0.669 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: Running lower_ac
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to lower_ac: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [LowerAC]: INFO (LowerAC) Lowered 0 loads, 0 saves, 0 copies.
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: lower_ac finished after 0.001 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: Running input_dma_coalescing
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to input_dma_coalescing: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [RematOpt]: Removed 0 remat instructions
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: remat_optimization finished after 0.071 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: DMA input Coalescing combined 0 input loads
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: input_dma_coalescing finished after 0.003 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: Running coalesce_multichannel_cc_ops
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to coalesce_multichannel_cc_ops: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: Running remat_optimization
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to remat_optimization: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: coalesce_multichannel_cc_ops finished after 0.001 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: Running infer_stream_ids
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to infer_stream_ids: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: infer_stream_ids finished after 0.001 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg01) [ModuleForkPass]: Running pre_sched
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to pre_sched: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: Start PRE scheduling 2 cores: 1 at: Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: Start...
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: Found 2 Splits CCs
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: Grouped CCs to 2 clusters.
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: To Spill 0 multi-layer tensors
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: set uninit flag on 0 insts
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: Done.
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: Start split live ranges Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg02) [ModuleForkPass]: legalize_cce_dma finished after 0.100 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [RematOpt]: Removed 0 remat instructions
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: remat_optimization finished after 0.005 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: Running coalesce_multichannel_cc_ops
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to coalesce_multichannel_cc_ops: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg02) [ModuleForkPass]: Running pre_opts
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to pre_opts: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [PreOpts]: Skipped. No pre-opt passes enabled
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg02) [ModuleForkPass]: pre_opts finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg02) [ModuleForkPass]: Running error_injector
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: coalesce_multichannel_cc_ops finished after 0.001 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to error_injector: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z WARNING 796 (nc01/sg02) [ErrorInjector]: Unrecognized injected error value "0"
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg02) [ModuleForkPass]: error_injector finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: Running infer_stream_ids
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to infer_stream_ids: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg02) [ModuleForkPass]: Running vn_splitter
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: infer_stream_ids finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to vn_splitter: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg00) [ModuleForkPass]: Running pre_sched
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to pre_sched: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: Start PRE scheduling 2 cores: 1 at: Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: Start...
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: Found 1 Splits CCs
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: Grouped CCs to 1 clusters.
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [VNSplitter]: INFO (VNSplitter) Collected all the internal vnodes: size = 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg02) [VNSplitter]: INFO (VNSplitter) Done with analyze and splitting: total dead nodes = 0
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: To Spill 0 multi-layer tensors
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: set uninit flag on 0 insts
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: Done.
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: Start split live ranges Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [build_flow_deps]: Build fdeps inserted 3834 edges
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [build_flow_deps]: Done build fdeps 3834 Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: End build flow dependencies Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: Start remove useless insts Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: remove_useless_insts
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ConstantPropagate]: [Constant_propagate for Affineselect] directly remove instruction number: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: remove Useless Instructions: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: End remove useless insts Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: Start scratchpad optimization Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: End scratchpad optimization Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: No split opportunities:
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: End split live ranges Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: Strt remove redundncies Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: remove_redundant_memsets
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: remove_redundant_memsets: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: remove_redundant_loads
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [NonSSALeg]: [Non-SSA legalization]created 0 memorylocations
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg02) [ModuleForkPass]: non_ssa_legalization finished after 0.306 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: End remove redundncies Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: Start DCE Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: No split opportunities:
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: End split live ranges Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: Strt remove redundncies Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: remove_redundant_memsets
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg02) [ModuleForkPass]: Running legalize_cce_dma
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to legalize_cce_dma: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: remove_redundant_memsets: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: remove_redundant_loads
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ConstantPropagate]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: End remove redundncies Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: Start DCE Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg02) [ModuleForkPass]: legalize_cce_dma finished after 0.079 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg02) [ModuleForkPass]: Running pre_opts
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to pre_opts: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [PreOpts]: Skipped. No pre-opt passes enabled
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg02) [ModuleForkPass]: pre_opts finished after 0.001 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg02) [ModuleForkPass]: Running error_injector
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to error_injector: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z WARNING 796 (nc00/sg02) [ErrorInjector]: Unrecognized injected error value "0"
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg02) [ModuleForkPass]: error_injector finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg02) [ModuleForkPass]: Running vn_splitter
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to vn_splitter: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: constant_propagate finished after 0.283 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: Running lower_ac
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to lower_ac: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [VNSplitter]: INFO (VNSplitter) Collected all the internal vnodes: size = 6
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg02) [VNSplitter]: INFO (VNSplitter) Done with analyze and splitting: total dead nodes = 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [PreSched]: DONE PRE scheduling Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [LowerAC]: INFO (LowerAC) Lowered 0 loads, 0 saves, 0 copies.
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: lower_ac finished after 0.001 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: Running input_dma_coalescing
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to input_dma_coalescing: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: DMA input Coalescing combined 0 input loads
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: input_dma_coalescing finished after 0.004 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: Running remat_optimization
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to remat_optimization: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [RematOpt]: Removed 0 remat instructions
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: remat_optimization finished after 0.005 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: Running coalesce_multichannel_cc_ops
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to coalesce_multichannel_cc_ops: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: coalesce_multichannel_cc_ops finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: Running infer_stream_ids
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to infer_stream_ids: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: infer_stream_ids finished after 0.000 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z USER 796 (nc00/sg01) [ModuleForkPass]: Running pre_sched
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: End DCE Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg01) [PreSched]: End DCE Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to pre_sched: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [PreSched]: Start PRE scheduling 2 cores: 1 at: Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: Start...
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: pre_sched finished after 0.382 seconds
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 253mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: Found 2 Splits CCs
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: Grouped CCs to 2 clusters.
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z USER 796 (nc01/sg00) [ModuleForkPass]: Running tensor_copy_elim
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: To Spill 0 multi-layer tensors
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: set uninit flag on 0 insts
|
|
2025-11-09T20:57:16Z INFO 796 [LayerSpiller]: LayerSpill: Done.
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [PreSched]: Start split live ranges Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [TensorCopyElim]: Tensor CP elimination: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [TensorCopyElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [PreSched]: No split opportunities:
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [PreSched]: Start build flow dependencies Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [build_flow_deps]: Start build fdeps. Invocation: 2Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [PreSched]: End split live ranges Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [PreSched]: Strt remove redundncies Sun Nov 9 20:57:16 2025
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [PreSched]: remove_redundant_memsets
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [TensorCopyElim]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [TensorCopyElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc01/sg00) [TensorCopyElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg00) [build_flow_deps]: Allocs: 919 instructions: 1628
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [PreSched]: remove_redundant_memsets: 0
|
|
2025-11-09T20:57:16Z INFO 796 (nc00/sg01) [PreSched]: remove_redundant_loads
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: End remove redundncies Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: Start DCE Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: tensor_copy_elim finished after 0.109 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: Running dynamic_dma_setup
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to dynamic_dma_setup: modules=1 functions=1 allocs=918 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: dynamic_dma_setup finished after 0.000 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: Running runtime_memory_reservation
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to runtime_memory_reservation: modules=1 functions=1 allocs=919 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: runtime_memory_reservation finished after 0.000 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: Running lower_klir_kernel
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=920 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: lower_klir_kernel finished after 0.001 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [build_flow_deps]: Build fdeps inserted 3836 edges
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: Running lower_nki_kernel
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=920 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [build_flow_deps]: Done build fdeps 3836 Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PreSched]: End build flow dependencies Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PreSched]: Start remove useless insts Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PreSched]: remove_useless_insts
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PreSched]: remove Useless Instructions: 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PreSched]: End remove useless insts Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PreSched]: Start scratchpad optimization Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PreSched]: End scratchpad optimization Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg02) [ShrinkDN]: INFO (ShrinkDN): Shrunk 2 nodes. Total savings 14336 bytes/partition
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: lower_nki_kernel finished after 0.001 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: Running coloring_allocator_psum
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to coloring_allocator_psum: modules=1 functions=1 allocs=920 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:17Z INFO 796 [PerformanceProfiler]: number of tensorizer non-local-tensor caused reload left 0
|
|
2025-11-09T20:57:17Z INFO 796 [PerformanceProfiler]: number of tensorizer non-local-tensor caused spill left 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: allocating PSUM
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: main loop
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg02) [VNSplitterPass]: INFO (VNSplitter) Time: 0.001 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg02) [VNSplitterPass]: INFO (VerticalFusion) Time: 0.019 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg02) [VNSplitterPass]: INFO (ShrinkDN) Time: 0.268 seconds
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg02) [ModuleForkPass]: vn_splitter finished after 0.313 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg02) [ModuleForkPass]: Running constant_propagate
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to constant_propagate: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: renumber locations
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: size = 230
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: build_no_bitmap start
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: 100% PSUM demand before spilling
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: PSUM high-water mark = 8 tensors
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: found 506 edges
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: mean: 4.4
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: median: 5.30025
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: adjacency vectors require 4048 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: build_no_bitmap done
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: find costs
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: best-of-n loop, heuristic = 0, allow_psum_spill_within_accum_group = false
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: lo = 230
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: hi = 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: inf = 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: total = 230
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: simplify
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: select ranges
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: no more spills
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: PSUM score = 0 (lower is better)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: spilling from PSUM cost about 0 cycles
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [PSUM_Allocator]: 100% PSUM utilization after allocation
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg02) [ConstantPropagate]: [Constant_propagate for select] directly remove instruction number: 0
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: coloring_allocator_psum finished after 0.016 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: Running dma_optimization_psum
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to dma_optimization_psum: modules=1 functions=1 allocs=920 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: dma_optimization_psum finished after 0.004 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PreSched]: DONE PRE scheduling Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: pre_sched finished after 0.392 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: Running tensor_copy_elim
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: Running address_rotation_psum
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [PreSched]: Start build flow dependencies Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [build_flow_deps]: Start build fdeps. Invocation: 3Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to address_rotation_psum: modules=1 functions=1 allocs=920 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [TensorCopyElim]: Tensor CP elimination: 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [TensorCopyElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 26 PSUM Banks
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [TensorCopyElim]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [build_flow_deps]: Allocs: 928 instructions: 2927
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [TensorCopyElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [TensorCopyElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 4 PSUM Banks
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 54 PSUM Banks
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:17Z INFO 796 [PerformanceProfiler]: number of tensorizer non-local-tensor caused reload left 0
|
|
2025-11-09T20:57:17Z INFO 796 [PerformanceProfiler]: number of tensorizer non-local-tensor caused spill left 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg02) [VNSplitterPass]: INFO (VNSplitter) Time: 0.002 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg02) [VNSplitterPass]: INFO (VerticalFusion) Time: 0.085 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg02) [VNSplitterPass]: INFO (ShrinkDN) Time: 0.119 seconds
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg02) [ModuleForkPass]: vn_splitter finished after 0.321 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg02) [ModuleForkPass]: Running constant_propagate
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to constant_propagate: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: tensor_copy_elim finished after 0.089 seconds
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: address_rotation_psum finished after 0.012 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: Running dynamic_dma_setup
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to dynamic_dma_setup: modules=1 functions=1 allocs=919 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: dynamic_dma_setup finished after 0.000 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: Running runtime_memory_reservation
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to runtime_memory_reservation: modules=1 functions=1 allocs=920 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: runtime_memory_reservation finished after 0.000 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 921 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: Running lower_klir_kernel
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=921 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: lower_klir_kernel finished after 0.001 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: Running coloring_allocator_sb
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 921 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: Running lower_nki_kernel
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=921 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to coloring_allocator_sb: modules=1 functions=1 allocs=920 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: lower_nki_kernel finished after 0.001 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes loaded 15803140
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: End DCE Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA average loaded DMA size 3323 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes saved 13107200
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA average saved DMA size 2133 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 2129920
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 130 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: allocating SB
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 254mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 921 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: main loop
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: Running coloring_allocator_psum
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to coloring_allocator_psum: modules=1 functions=1 allocs=921 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: renumber locations
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg02) [ConstantPropagate]: [Constant_propagate for select] directly remove instruction number: 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: size = 652
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg02) [ConstantPropagate]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: allocating PSUM
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: main loop
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: renumber locations
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: size = 230
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: build_no_bitmap start
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: find partners
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: 100% PSUM demand before spilling
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: PSUM high-water mark = 8 tensors
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: found 506 edges
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: mean: 4.4
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: median: 5.30025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: adjacency vectors require 4048 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: build_no_bitmap done
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: find costs
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: found 100 accumulation groups
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: largest = custom-call.177.2093_i2
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: tensors = 17
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: requires 33280 bytes/partition
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: expanding partners
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: best-of-n loop, heuristic = 0, allow_psum_spill_within_accum_group = false
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: lo = 230
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: hi = 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: inf = 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: total = 230
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: simplify
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: select ranges
|
|
2025-11-09T20:57:17Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: no more spills
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: PSUM score = 0 (lower is better)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: spilling from PSUM cost about 0 cycles
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [PSUM_Allocator]: 100% PSUM utilization after allocation
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: coloring_allocator_psum finished after 0.090 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 255mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 921 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: Running dma_optimization_psum
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to dma_optimization_psum: modules=1 functions=1 allocs=921 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: dma_optimization_psum finished after 0.005 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 255mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 921 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: Running address_rotation_psum
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to address_rotation_psum: modules=1 functions=1 allocs=921 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 26 PSUM Banks
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 4 PSUM Banks
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: find loads
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: Start build flow dependencies Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [build_flow_deps]: Start build fdeps. Invocation: 4Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [build_flow_deps]: Allocs: 929 instructions: 2930
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: 2 pin count
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: 34 remat count
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: 2 pinned tensors will require about 16392 bytes/partition
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: build interference graph
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: pass 1 int-tree
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 54 PSUM Banks
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [build_flow_deps]: Build fdeps inserted 8073 edges
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [build_flow_deps]: Done build fdeps 8073 Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [PreSched]: End build flow dependencies Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [PreSched]: Start remove useless insts Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [PreSched]: remove_useless_insts
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: address_rotation_psum finished after 0.089 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 255mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 921 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: Running coloring_allocator_sb
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to coloring_allocator_sb: modules=1 functions=1 allocs=921 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes loaded 15803140
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA average loaded DMA size 3323 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes saved 13107202
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA average saved DMA size 2132 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 2129920
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 130 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [PreSched]: remove Useless Instructions: 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [PreSched]: End remove useless insts Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [PreSched]: Start scratchpad optimization Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [PreSched]: End scratchpad optimization Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: allocating SB
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: main loop
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Num intervals 652 Num locations 652
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: renumber locations
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: size = 653
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: find partners
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: found 100 accumulation groups
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: largest = custom-call.177.2093_i0
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: tensors = 17
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: requires 33280 bytes/partition
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: expanding partners
|
|
2025-11-09T20:57:17Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: info.neighbors partners Done
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: edge: 24460
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: mean: 75.0307
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: median: 67.4806
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: find costs
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: best-of-n loop, heuristic = 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: initialize safe & unsafe
|
|
2025-11-09T20:57:17Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: find loads
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: 2 pin count
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: 34 remat count
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: 2 pinned tensors will require about 16392 bytes/partition
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: build interference graph
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: pass 1 int-tree
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: safe = 455
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: unsafe = 174
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: inf = 21
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: total = 650
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: simplify
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: simplify_step3_sorted2 #Unsafe 147 #Pinned 0 #Safe 0 minCost 0.00832306 maxCost 0.0673281 locations 652
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: new candidates = 7
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: select ranges
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Num intervals 653 Num locations 653
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg02) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: info.neighbors partners Done
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Total: 650
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Spilled: 0.000 (0)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Allocated: 1.000 (650)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Rover zone: 0.691 (449)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Pre-rover zone: 0.009 (6)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Post-rover zone: 0.300 (195)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Slice zone: 0.000 (0)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Blocks nothing: 0.002 (1)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Blocks medium: 0.000 (0)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Blocks tall: 0.998 (649)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Visited until tall blocking (mean): 0.991
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Visited until tall blocking (median): 1.000
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Visited until tall blocking (p95): 1.000
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: Success
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: edge: 24468
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: mean: 74.9403
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: median: 66.0559
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: find costs
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg02) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg02) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: best-of-n loop, heuristic = 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: initialize safe & unsafe
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: safe = 456
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: unsafe = 174
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: inf = 21
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: total = 651
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: simplify
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: simplify_step3_sorted2 #Unsafe 147 #Pinned 0 #Safe 0 minCost 0.00832306 maxCost 0.0673281 locations 653
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: new candidates = 7
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: select ranges
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: SB spills = 0 tensors
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: size = 0 bytes/partition
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: remats = 0 tensors
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: unpinned = 0 tensors
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: size = 0 bytes/partition
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: SB score = 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: spilling from SB cost about 0 cycles
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: 16392 bytes/partition (100%) successfully pinned
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: pinning saved approximately 8300 cycles
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [SB_Allocator]: 0% SB utilization after allocation
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Total: 651
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Spilled: 0.000 (0)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Allocated: 1.000 (651)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Rover zone: 0.693 (451)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Pre-rover zone: 0.008 (5)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Post-rover zone: 0.300 (195)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Slice zone: 0.000 (0)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Blocks nothing: 0.002 (1)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Blocks medium: 0.000 (0)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Blocks tall: 0.998 (650)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Visited until tall blocking (mean): 0.990
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Visited until tall blocking (median): 1.000
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Visited until tall blocking (p95): 1.000
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: Success
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes loaded 15803140
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average loaded DMA size 3323 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes saved 13107200
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average saved DMA size 2133 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 2129920
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 130 bytes
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: coloring_allocator_sb finished after 0.424 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 255mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: SB spills = 0 tensors
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: size = 0 bytes/partition
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: remats = 0 tensors
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: unpinned = 0 tensors
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: size = 0 bytes/partition
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: SB score = 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=920 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: spilling from SB cost about 0 cycles
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: 16392 bytes/partition (100%) successfully pinned
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: pinning saved approximately 8300 cycles
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [SB_Allocator]: 0% SB utilization after allocation
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg02) [ConstantPropagate]: [Constant_propagate for Affineselect] directly remove instruction number: 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: address_rotation_sb finished after 0.011 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: Running dma_optimization_sb
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to dma_optimization_sb: modules=1 functions=1 allocs=920 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: DMA optimization In bytes loaded or saved 28910340, 18.3927% input load, 16.3215% output write, 65.2859% spill/reload [sg0000]
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: removed 0 identical load
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: adjusted 0 DMACopy remat
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: sub-graph will get execute 1 times
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [Load Merging]: removed 0 remat/cloned instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [PreSched]: DONE PRE scheduling Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg01) [ModuleForkPass]: pre_sched finished after 0.991 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2927 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes loaded 15803140
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average loaded DMA size 3323 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes saved 13107202
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average saved DMA size 2132 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 2129920
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 130 bytes
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: coloring_allocator_sb finished after 0.297 seconds
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg01) [ModuleForkPass]: Running tensor_copy_elim
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=928 blocks=1 instructions=2927 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [Load shrink]: shrinked 0 GCA remat/cloned instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 921 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [Load Merging + Load shrink] reduced input/const loading DMA traffic 0, 0% out of total dma traffic(5.31738e+06)
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=921 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [Re-allocation Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [remove extra save] removed 0 memlocs and 0 instructions
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: address_rotation_sb finished after 0.008 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 921 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: Running dma_optimization_sb
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to dma_optimization_sb: modules=1 functions=1 allocs=921 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: DMA optimization In bytes loaded or saved 28910342, 18.3927% input load, 16.3215% output write, 65.2859% spill/reload [sg0000]
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: removed 0 identical load
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: adjusted 0 DMACopy remat
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: sub-graph will get execute 1 times
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [Load Merging]: removed 0 remat/cloned instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [Load shrink]: shrinked 0 GCA remat/cloned instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [Load Merging + Load shrink] reduced input/const loading DMA traffic 0, 0% out of total dma traffic(5.31738e+06)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [Re-allocation Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [remove extra save] removed 0 memlocs and 0 instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [TensorCopyElim]: Tensor CP elimination: 1
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [build_flow_deps]: Build fdeps inserted 8075 edges
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [build_flow_deps]: Done build fdeps 8075 Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: End build flow dependencies Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: Start remove useless insts Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: remove_useless_insts
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: DMA SpillSave Coalescing Round 0 combined 0 SpillSaves and Reloads
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: average loaded DMA size 3323 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: average saved DMA size 2132 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes loaded 15803140
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing average loaded DMA size 3323 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes saved 13107202
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing average saved DMA size 2132 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [Experiment partial DMA access] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: [DMA optimization] reduced DMA traffic 0, 0% out of total dma traffic
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: DMA optimization Out bytes loaded or saved 28910342, 18.3927% input load, 16.3215% output write, 65.2859% spill/reload [sg0000]
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes loaded 15803140
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average loaded DMA size 3323 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes saved 13107202
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average saved DMA size 2132 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes DMAcopyed 2129920
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average DMAcopyed DMA size 130 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average DMA size 1137 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: INFO: Finished set_spill_canreadUninit(module);
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: DMA optimization re-enable optimization
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: dma_optimization_sb finished after 0.087 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc00/sg00) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=920 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 4 Sb address
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [TensorCopyElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: DMA SpillSave Coalescing Round 0 combined 0 SpillSaves and Reloads
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: average loaded DMA size 3323 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: average saved DMA size 2133 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes loaded 15803140
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing average loaded DMA size 3323 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes saved 13107200
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing average saved DMA size 2133 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: remove Useless Instructions: 0
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: End remove useless insts Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: Start scratchpad optimization Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 16 Sb address
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg01) [PreSched]: End scratchpad optimization Sun Nov 9 20:57:17 2025
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [Experiment partial DMA access] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: [DMA optimization] reduced DMA traffic 0, 0% out of total dma traffic
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: DMA optimization Out bytes loaded or saved 28910340, 18.3927% input load, 16.3215% output write, 65.2859% spill/reload [sg0000]
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes loaded 15803140
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average loaded DMA size 3323 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes saved 13107200
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average saved DMA size 2133 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes DMAcopyed 2129920
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average DMAcopyed DMA size 130 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average DMA size 1137 bytes
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: INFO: Finished set_spill_canreadUninit(module);
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: DMA optimization re-enable optimization
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: dma_optimization_sb finished after 0.191 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg00) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=919 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 4 Sb address
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 16 Sb address
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [TensorCopyElim]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [TensorCopyElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [TensorCopyElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg01) [ModuleForkPass]: tensor_copy_elim finished after 0.195 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg02) [ConstantPropagate]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc00/sg02) [ConstantPropagate]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 927 memory location(s), 1 block(s), and 2926 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg01) [ModuleForkPass]: Running dynamic_dma_setup
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to dynamic_dma_setup: modules=1 functions=1 allocs=927 blocks=1 instructions=2926 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg01) [ModuleForkPass]: dynamic_dma_setup finished after 0.000 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2926 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg01) [ModuleForkPass]: Running runtime_memory_reservation
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to runtime_memory_reservation: modules=1 functions=1 allocs=928 blocks=1 instructions=2926 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg01) [ModuleForkPass]: runtime_memory_reservation finished after 0.000 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2926 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg01) [ModuleForkPass]: Running lower_klir_kernel
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=929 blocks=1 instructions=2926 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg01) [ModuleForkPass]: lower_klir_kernel finished after 0.001 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2926 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg01) [ModuleForkPass]: Running lower_nki_kernel
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=929 blocks=1 instructions=2926 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg01) [ModuleForkPass]: lower_nki_kernel finished after 0.001 seconds
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2926 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:17Z USER 796 (nc01/sg01) [ModuleForkPass]: Running coloring_allocator_psum
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to coloring_allocator_psum: modules=1 functions=1 allocs=929 blocks=1 instructions=2926 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:17Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: allocating PSUM
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: main loop
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: renumber locations
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: size = 228
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: build_no_bitmap start
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: 100% PSUM demand before spilling
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: PSUM high-water mark = 8 tensors
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: found 566 edges
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: mean: 4.96491
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: median: 4.84557
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: adjacency vectors require 4528 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: build_no_bitmap done
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: find costs
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: best-of-n loop, heuristic = 0, allow_psum_spill_within_accum_group = false
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: lo = 228
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: hi = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: inf = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: total = 228
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: simplify
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: select ranges
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PreSched]: DONE PRE scheduling Sun Nov 9 20:57:18 2025
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg01) [ModuleForkPass]: pre_sched finished after 1.192 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2930 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg01) [ModuleForkPass]: Running tensor_copy_elim
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: no more spills
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: PSUM score = 0 (lower is better)
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=929 blocks=1 instructions=2930 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: spilling from PSUM cost about 0 cycles
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [PSUM_Allocator]: 100% PSUM utilization after allocation
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg01) [ModuleForkPass]: coloring_allocator_psum finished after 0.110 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2926 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg01) [ModuleForkPass]: Running dma_optimization_psum
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to dma_optimization_psum: modules=1 functions=1 allocs=929 blocks=1 instructions=2926 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg01) [ModuleForkPass]: dma_optimization_psum finished after 0.074 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2926 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg01) [ModuleForkPass]: Running address_rotation_psum
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to address_rotation_psum: modules=1 functions=1 allocs=929 blocks=1 instructions=2926 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [TensorCopyElim]: Tensor CP elimination: 1
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: PSUM Rotation rotated 18 PSUM Banks
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [TensorCopyElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: PSUM Rotation rotated 28 PSUM Banks
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 22 Sb address
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 1 Sb address
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: PSUM Rotation rotated 11 PSUM Banks
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg01) [ModuleForkPass]: address_rotation_psum finished after 0.119 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2926 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg01) [ModuleForkPass]: Running coloring_allocator_sb
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to coloring_allocator_sb: modules=1 functions=1 allocs=929 blocks=1 instructions=2926 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 45 Sb address
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes loaded 54583812
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: INFO: Pre GCA average loaded DMA size 3112 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes saved 15728640
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: INFO: Pre GCA average saved DMA size 2792 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 1064960
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 130 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: address_rotation_sb finished after 0.395 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: Running coloring_allocator_dram
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to coloring_allocator_dram: modules=1 functions=1 allocs=919 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: allocating SB
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: main loop
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [TensorCopyElim]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: renumber locations
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: size = 662
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Local
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: reserved space = 164096 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: spill space = 0 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: aligned spill space = 0 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: renumber locations
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: size = 0
|
|
2025-11-09T20:57:18Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:18Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: Num intervals 0 Num locations 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: lo = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: hi = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: total = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: simplify
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: select ranges
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: CC buffer size limit 524288000
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: allreduce_dram_hwm 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: Real CC buffer size 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: DRAM hwm after allocation: 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DRAM_Allocator]: DRAM allocation successful
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: coloring_allocator_dram finished after 0.008 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: Running address_rotation_dram
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to address_rotation_dram: modules=1 functions=1 allocs=919 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: Runtime page size at 512MB
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: find partners
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: DRAM hwm before rotation 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: allreduce buffer size 524288000
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: allreduce hwm 8388608
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: Real CC buffer size 8388608
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: DRAM hwm after rotation 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: DRAM Rotation rotated 0 Dram address
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: address_rotation_dram finished after 0.003 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: found 200 accumulation groups
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: largest = custom-call.184.1835_i3
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: tensors = 17
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: requires 33280 bytes/partition
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: expanding partners
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [TensorCopyElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [TensorCopyElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: Running tensorcopy_accel
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to tensorcopy_accel: modules=1 functions=1 allocs=919 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [TensorCopyAccel::Impl]: Running peephole optimization pass
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [TensorCopyAccel::Impl]: Accelerated 34 out of 172 tensorcopy in Function: sg0000 average acceleration factor: 1
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: tensorcopy_accel finished after 0.006 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1625 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: Running peephole_opts
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to peephole_opts: modules=1 functions=1 allocs=919 blocks=1 instructions=1625 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [PeepholeOpts]: PeepholeOpts enabled? Recip: true Tsp: true Tc: false SplitSelect: true SimplifyMemset true
|
|
2025-11-09T20:57:18Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:18Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: peephole_opts finished after 0.083 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 919 memory location(s), 1 block(s), and 1626 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: Running lower_kernel
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg01) [ModuleForkPass]: tensor_copy_elim finished after 0.378 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 928 memory location(s), 1 block(s), and 2929 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: find loads
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: 2 pin count
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 22 Sb address
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: 133 remat count
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: 2 pinned tensors will require about 16392 bytes/partition
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: build interference graph
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: pass 1 int-tree
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg01) [ModuleForkPass]: Running dynamic_dma_setup
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to lower_kernel: modules=1 functions=1 allocs=919 blocks=1 instructions=1626 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Started running LowerKernel
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: BIR SB coloring allocator is disabled
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Start of kernel lowering pass, number of insts: 1626, number of allocs: 919
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to dynamic_dma_setup: modules=1 functions=1 allocs=928 blocks=1 instructions=2929 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg01) [ModuleForkPass]: dynamic_dma_setup finished after 0.001 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Found InstBIRKernel: [CausalAttentionMMSoftmaxMMWithoutSwap]I-2744-0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Scan BKs time (s): 0.001251
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Set architecture: gen3
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Input/output shapes for Kernel inst [I-2744-0]
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2929 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: input0: [ 2 128 2048 ]
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: input1: [ 2 128 2048 ]
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg01) [ModuleForkPass]: Running runtime_memory_reservation
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to runtime_memory_reservation: modules=1 functions=1 allocs=929 blocks=1 instructions=2929 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg01) [ModuleForkPass]: runtime_memory_reservation finished after 0.000 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 930 memory location(s), 1 block(s), and 2929 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg01) [ModuleForkPass]: Running lower_klir_kernel
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=930 blocks=1 instructions=2929 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: input2: [ 2 2048 128 ]
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: input3: ap
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: output0: [ 2 128 2048 ]
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: do_input1_tp=false
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: do_out_tp=true
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Legalized inp_ap=[[262144,2],[2048,128],[1,2048]]
|
|
Offset: 524288
|
|
Memory Location: {reshape.16}@DRAM<Shared>(1048576x2)#Internal DebugInfo: <reshape.16||NHC||[1048576, 1, 1]>
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Legalized inp_ap=[[262144,2],[2048,128],[1,2048]]
|
|
Offset: 524288
|
|
Memory Location: {reshape.24}@DRAM<Shared>(1048576x2)#Internal DebugInfo: <reshape.24||NHC||[1048576, 1, 1]>
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: AP of Q indicates standalone Q tensor.
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: parallel_split_n = input1_ap[1].getStep() / input1_ap[2].getNum() = 2048 / 2048 = 1
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Sharding/tiling split_i=0, split_n=1
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Flash attention has been disabled
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Scratch sbuf for kernel I-2744-0: [108544, 168828)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: seq_len=2048, seq_len2=2048, complete_seq_len2=2048
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Creating identity matrices with AffineSelect
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg01) [ModuleForkPass]: lower_klir_kernel finished after 0.002 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 930 memory location(s), 1 block(s), and 2929 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Num intervals 662 Num locations 662
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg01) [ModuleForkPass]: Running lower_nki_kernel
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=930 blocks=1 instructions=2929 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: info.neighbors partners Done
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg01) [ModuleForkPass]: lower_nki_kernel finished after 0.002 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 930 memory location(s), 1 block(s), and 2929 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg01) [ModuleForkPass]: Running coloring_allocator_psum
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to coloring_allocator_psum: modules=1 functions=1 allocs=930 blocks=1 instructions=2929 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 1 Sb address
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg02) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: edge: 20869
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: mean: 63.0483
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: median: 52.3935
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: find costs
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 46 Sb address
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: best-of-n loop, heuristic = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: initialize safe & unsafe
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg00) [ModuleForkPass]: address_rotation_sb finished after 0.706 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: safe = 433
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: unsafe = 194
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: inf = 33
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: total = 660
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: simplify
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: simplify_step3_sorted2 #Unsafe 0 #Pinned 0 #Safe 0 minCost 1.79769e+308 maxCost 2.22507e-308 locations 662
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: select ranges
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: seq_len=2048, seq_len2=2048, complete_seq_len2=2048
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Creating identity matrices with AffineSelect
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg02) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg00) [ModuleForkPass]: Running coloring_allocator_dram
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to coloring_allocator_dram: modules=1 functions=1 allocs=920 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Local
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: reserved space = 164096 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: spill space = 0 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: aligned spill space = 0 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: renumber locations
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: size = 0
|
|
2025-11-09T20:57:18Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:18Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: Num intervals 0 Num locations 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: lo = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: hi = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: total = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: simplify
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: select ranges
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: CC buffer size limit 524288000
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: allreduce_dram_hwm 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: Real CC buffer size 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: DRAM hwm after allocation: 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DRAM_Allocator]: DRAM allocation successful
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Total: 660
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Spilled: 0.000 (0)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Allocated: 1.000 (660)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Rover zone: 0.817 (539)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Pre-rover zone: 0.014 (9)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Post-rover zone: 0.170 (112)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Slice zone: 0.000 (0)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Blocks nothing: 0.002 (1)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Blocks medium: 0.000 (0)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Blocks tall: 0.998 (659)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Visited until tall blocking (mean): 0.995
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Visited until tall blocking (median): 1.000
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Visited until tall blocking (p95): 1.000
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: Success
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg00) [ModuleForkPass]: coloring_allocator_dram finished after 0.013 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 256mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PSUM_Allocator]: allocating PSUM
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg00) [ModuleForkPass]: Running address_rotation_dram
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to address_rotation_dram: modules=1 functions=1 allocs=920 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: Runtime page size at 512MB
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg02) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: DRAM hwm before rotation 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: allreduce buffer size 524288000
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: allreduce hwm 8388608
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: Real CC buffer size 8388608
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: DRAM hwm after rotation 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: DRAM Rotation rotated 0 Dram address
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg00) [ModuleForkPass]: address_rotation_dram finished after 0.011 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 257mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: SB spills = 0 tensors
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: size = 0 bytes/partition
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: remats = 0 tensors
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: unpinned = 0 tensors
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: size = 0 bytes/partition
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: SB score = 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: spilling from SB cost about 0 cycles
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: 16392 bytes/partition (100%) successfully pinned
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: pinning saved approximately 8300 cycles
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [SB_Allocator]: 0% SB utilization after allocation
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg00) [ModuleForkPass]: Running tensorcopy_accel
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to tensorcopy_accel: modules=1 functions=1 allocs=920 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [TensorCopyAccel::Impl]: Running peephole optimization pass
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [TensorCopyAccel::Impl]: Accelerated 34 out of 173 tensorcopy in Function: sg0000 average acceleration factor: 1
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg00) [ModuleForkPass]: tensorcopy_accel finished after 0.007 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 257mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PSUM_Allocator]: main loop
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1628 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg02) [ModuleForkPass]: constant_propagate finished after 1.594 seconds
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg00) [ModuleForkPass]: Running peephole_opts
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to peephole_opts: modules=1 functions=1 allocs=920 blocks=1 instructions=1628 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [PeepholeOpts]: PeepholeOpts enabled? Recip: true Tsp: true Tc: false SplitSelect: true SimplifyMemset true
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 257mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg02) [ModuleForkPass]: Running lower_ac
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to lower_ac: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PSUM_Allocator]: renumber locations
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PSUM_Allocator]: size = 228
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes loaded 54583812
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: INFO: Post GCA average loaded DMA size 3112 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes saved 15728640
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: INFO: Post GCA average saved DMA size 2792 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 1064960
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 130 bytes
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg01) [ModuleForkPass]: coloring_allocator_sb finished after 0.489 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 257mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2926 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg01) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=929 blocks=1 instructions=2926 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [LowerKernel]: Lower BKs time (s): 0.442759
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: lower_kernel finished after 0.317 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 258mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg00) [ModuleForkPass]: peephole_opts finished after 0.091 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 258mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 920 memory location(s), 1 block(s), and 1629 instruction(s). Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z USER 796 (nc00/sg00) [ModuleForkPass]: Running lower_kernel
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to lower_kernel: modules=1 functions=1 allocs=920 blocks=1 instructions=1629 Max writers: 16 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: Started running LowerKernel
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: BIR SB coloring allocator is disabled
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: Start of kernel lowering pass, number of insts: 1629, number of allocs: 920
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1486 memory location(s), 1 block(s), and 2627 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: Found InstBIRKernel: [CausalAttentionMMSoftmaxMMWithoutSwap]I-2744-0
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg01) [ModuleForkPass]: address_rotation_sb finished after 0.010 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: Scan BKs time (s): 0.003928
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: Set architecture: gen3
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 258mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: Input/output shapes for Kernel inst [I-2744-0]
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: input0: [ 2 128 2048 ]
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: input1: [ 2 128 2048 ]
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: input2: [ 2 2048 128 ]
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: input3: ap
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: output0: [ 2 128 2048 ]
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: do_input1_tp=false
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: do_out_tp=true
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: Legalized inp_ap=[[262144,2],[2048,128],[1,2048]]
|
|
Offset: 0
|
|
Memory Location: {reshape.16}@DRAM<Shared>(1048576x2)#Internal DebugInfo: <reshape.16||NHC||[1048576, 1, 1]>
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: Legalized inp_ap=[[262144,2],[2048,128],[1,2048]]
|
|
Offset: 0
|
|
Memory Location: {reshape.24}@DRAM<Shared>(1048576x2)#Internal DebugInfo: <reshape.24||NHC||[1048576, 1, 1]>
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: AP of Q indicates standalone Q tensor.
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: parallel_split_n = input1_ap[1].getStep() / input1_ap[2].getNum() = 2048 / 2048 = 1
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: Sharding/tiling split_i=0, split_n=1
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 929 memory location(s), 1 block(s), and 2926 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: Flash attention has been disabled
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: Scratch sbuf for kernel I-2744-0: [108544, 168828)
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: seq_len=2048, seq_len2=2048, complete_seq_len2=2048
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg01) [ModuleForkPass]: Running dma_optimization_sb
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: Creating identity matrices with AffineSelect
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to dma_optimization_sb: modules=1 functions=1 allocs=929 blocks=1 instructions=2926 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: DMA optimization In bytes loaded or saved 70312452, 62.7173% input load, 5.96524% output write, 31.3175% spill/reload [sg0001]
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: Running lower_klir_kernel
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=1486 blocks=1 instructions=2627 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: lower_klir_kernel finished after 0.006 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 259mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1486 memory location(s), 1 block(s), and 2627 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: Running lower_nki_kernel
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=1486 blocks=1 instructions=2627 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: removed 0 identical load
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: lower_nki_kernel finished after 0.002 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 259mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1486 memory location(s), 1 block(s), and 2627 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: Running non_ssa_legalization
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=1486 blocks=1 instructions=2627 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [NonSSALeg]: remove_redundant_loads
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [NonSSALeg]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: adjusted 0 DMACopy remat
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PSUM_Allocator]: build_no_bitmap start
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PSUM_Allocator]: 100% PSUM demand before spilling
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PSUM_Allocator]: PSUM high-water mark = 8 tensors
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PSUM_Allocator]: found 566 edges
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PSUM_Allocator]: mean: 4.96491
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PSUM_Allocator]: median: 4.84557
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PSUM_Allocator]: adjacency vectors require 4528 bytes
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PSUM_Allocator]: build_no_bitmap done
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg01) [PSUM_Allocator]: find costs
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: sub-graph will get execute 27 times
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [Load Merging]: removed 0 remat/cloned instructions
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [Load shrink]: shrinked 0 GCA remat/cloned instructions
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [Load Merging + Load shrink] reduced input/const loading DMA traffic 4718592, 6.71089% out of total dma traffic(4.40981e+07)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg02) [LowerAC]: INFO (LowerAC) Lowered 0 loads, 0 saves, 0 copies.
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg02) [ModuleForkPass]: lower_ac finished after 0.112 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 259mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg02) [ModuleForkPass]: Running input_dma_coalescing
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to input_dma_coalescing: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [Re-allocation Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [remove extra save] removed 0 memlocs and 0 instructions
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: seq_len=2048, seq_len2=2048, complete_seq_len2=2048
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:18Z INFO 796 (nc00/sg00) [LowerKernel]: Creating identity matrices with AffineSelect
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [NonSSALeg]: [Non-SSA legalization]created 16 memorylocations
|
|
2025-11-09T20:57:18Z USER 796 (nc01/sg00) [ModuleForkPass]: non_ssa_legalization finished after 0.191 seconds
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 260mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:18Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1494 memory location(s), 1 block(s), and 2627 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg00) [ModuleForkPass]: Running dynamic_dma_cleanup
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to dynamic_dma_cleanup: modules=1 functions=1 allocs=1494 blocks=1 instructions=2627 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: best-of-n loop, heuristic = 0, allow_psum_spill_within_accum_group = false
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: lo = 228
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: hi = 0
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: inf = 0
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: DMA input Coalescing combined 0 input loads
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: total = 228
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: simplify
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg02) [ModuleForkPass]: input_dma_coalescing finished after 0.186 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 259mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: select ranges
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg02) [ModuleForkPass]: Running remat_optimization
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to remat_optimization: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg00) [ModuleForkPass]: dynamic_dma_cleanup finished after 0.079 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 259mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1494 memory location(s), 1 block(s), and 2627 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg00) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=1494 blocks=1 instructions=2627 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: no more spills
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: PSUM score = 0 (lower is better)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: spilling from PSUM cost about 0 cycles
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [PSUM_Allocator]: 100% PSUM utilization after allocation
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg01) [ModuleForkPass]: coloring_allocator_psum finished after 0.599 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 260mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 930 memory location(s), 1 block(s), and 2929 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:19Z WARNING 796 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {I-2744-0_s0_aten__mul_broadcast.7-t210_b0}@SB<0,118020>(128x4)#Internal DebugInfo: <I-2744-0_s0_aten__mul_broadcast.7-t210_b0||NC||[128, 1]>
|
|
2025-11-09T20:57:19Z WARNING 796 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {I-2744-0_s0_aten__mul_broadcast.7-t210_b1}@SB<0,118020>(128x4)#Internal DebugInfo: <I-2744-0_s0_aten__mul_broadcast.7-t210_b1||NC||[128, 1]>
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg02) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg01) [ModuleForkPass]: Running dma_optimization_psum
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to dma_optimization_psum: modules=1 functions=1 allocs=930 blocks=1 instructions=2929 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [LowerKernel]: Lower BKs time (s): 0.458896
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: lower_kernel finished after 0.389 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 260mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1487 memory location(s), 1 block(s), and 2630 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: DMA SpillSave Coalescing Round 0 combined 0 SpillSaves and Reloads
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: average loaded DMA size 3091 bytes
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: average saved DMA size 2792 bytes
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes loaded 49865220
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: INFO: Post DMA coalescing average loaded DMA size 3091 bytes
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes saved 15728640
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: INFO: Post DMA coalescing average saved DMA size 2792 bytes
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: Running lower_klir_kernel
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=1487 blocks=1 instructions=2630 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [Experiment partial DMA access] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: [DMA optimization] reduced DMA traffic 4718592, 6.71089% out of total dma traffic
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: DMA optimization Out bytes loaded or saved 65593860, 60.0353% input load, 6.39435% output write, 33.5704% spill/reload [sg0001]
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes loaded 49865220
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization average loaded DMA size 3091 bytes
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes saved 15728640
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization average saved DMA size 2792 bytes
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes DMAcopyed 1064960
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization average DMAcopyed DMA size 130 bytes
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization average DMA size 2225 bytes
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: INFO: Finished set_spill_canreadUninit(module);
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: DMA optimization re-enable optimization
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg01) [ModuleForkPass]: dma_optimization_sb finished after 0.409 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 260mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 917 memory location(s), 1 block(s), and 2915 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg01) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=917 blocks=1 instructions=2915 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 7 Sb address
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 42 Sb address
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: lower_klir_kernel finished after 0.078 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 261mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1487 memory location(s), 1 block(s), and 2630 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: Running lower_nki_kernel
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=1487 blocks=1 instructions=2630 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: lower_nki_kernel finished after 0.006 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [RematOpt]: Removed 0 remat instructions
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg02) [ModuleForkPass]: remat_optimization finished after 0.215 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 261mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg02) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg02) [ModuleForkPass]: Running coalesce_multichannel_cc_ops
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to coalesce_multichannel_cc_ops: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 261mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1487 memory location(s), 1 block(s), and 2630 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: Running non_ssa_legalization
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=1487 blocks=1 instructions=2630 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [NonSSALeg]: remove_redundant_loads
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg01) [ModuleForkPass]: dma_optimization_psum finished after 0.127 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 261mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 930 memory location(s), 1 block(s), and 2929 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg01) [ModuleForkPass]: Running address_rotation_psum
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to address_rotation_psum: modules=1 functions=1 allocs=930 blocks=1 instructions=2929 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [NonSSALeg]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg02) [ModuleForkPass]: coalesce_multichannel_cc_ops finished after 0.011 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 261mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg02) [ModuleForkPass]: Running infer_stream_ids
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to infer_stream_ids: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: PSUM Rotation rotated 18 PSUM Banks
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: PSUM Rotation rotated 28 PSUM Banks
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg02) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [NonSSALeg]: [Non-SSA legalization]created 16 memorylocations
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: non_ssa_legalization finished after 0.200 seconds
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg02) [ModuleForkPass]: infer_stream_ids finished after 0.017 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 261mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 261mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1495 memory location(s), 1 block(s), and 2630 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: Running dynamic_dma_cleanup
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to dynamic_dma_cleanup: modules=1 functions=1 allocs=1495 blocks=1 instructions=2630 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: dynamic_dma_cleanup finished after 0.006 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: PSUM Rotation rotated 11 PSUM Banks
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg01) [ModuleForkPass]: address_rotation_psum finished after 0.201 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 261mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 930 memory location(s), 1 block(s), and 2929 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg01) [ModuleForkPass]: Running coloring_allocator_sb
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to coloring_allocator_sb: modules=1 functions=1 allocs=930 blocks=1 instructions=2929 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes loaded 54583812
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg02) [ConstantPropagate]: [Constant_propagate for Affineselect] directly remove instruction number: 0
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg02) [ModuleForkPass]: Running pre_sched
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: INFO: Pre GCA average loaded DMA size 3112 bytes
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes saved 15728642
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: INFO: Pre GCA average saved DMA size 2792 bytes
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 1064960
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 130 bytes
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to pre_sched: modules=1 functions=1 allocs=1758 blocks=1 instructions=8020 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg02) [PreSched]: Start PRE scheduling 2 cores: 1 at: Sun Nov 9 20:57:19 2025
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 262mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1495 memory location(s), 1 block(s), and 2630 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=1495 blocks=1 instructions=2630 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: allocating SB
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: main loop
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: renumber locations
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: size = 663
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: find partners
|
|
2025-11-09T20:57:19Z WARNING 796 [birverifier::InstVisitor]: (nc00/sg00) Non - output memory location with no reader: {I-2744-0_s0_aten__mul_broadcast.7-t210_b0}@SB<0,118020>(128x4)#Internal DebugInfo: <I-2744-0_s0_aten__mul_broadcast.7-t210_b0||NC||[128, 1]>
|
|
2025-11-09T20:57:19Z INFO 796 [LayerSpiller]: LayerSpill: Start...
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: found 200 accumulation groups
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: largest = custom-call.184.1835_i1
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: tensors = 17
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: requires 33280 bytes/partition
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: expanding partners
|
|
2025-11-09T20:57:19Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:19Z WARNING 796 [birverifier::InstVisitor]: (nc00/sg00) Non - output memory location with no reader: {I-2744-0_s0_aten__mul_broadcast.7-t210_b1}@SB<0,118020>(128x4)#Internal DebugInfo: <I-2744-0_s0_aten__mul_broadcast.7-t210_b1||NC||[128, 1]>
|
|
2025-11-09T20:57:19Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: find loads
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: 2 pin count
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: 133 remat count
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: 2 pinned tensors will require about 16392 bytes/partition
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: build interference graph
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: pass 1 int-tree
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Num intervals 663 Num locations 663
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: info.neighbors partners Done
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg00) [ModuleForkPass]: birverifier finished after 0.709 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 263mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1494 memory location(s), 1 block(s), and 2627 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg00) [ModuleForkPass]: Running dynamic_dma_scan
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to dynamic_dma_scan: modules=1 functions=1 allocs=1494 blocks=1 instructions=2627 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: edge: 20877
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: mean: 62.9774
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: median: 52.4622
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: find costs
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg02) [ConstantPropagate]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: best-of-n loop, heuristic = 0
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: initialize safe & unsafe
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: safe = 434
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: unsafe = 194
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: inf = 33
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: total = 661
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: simplify
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: simplify_step3_sorted2 #Unsafe 0 #Pinned 0 #Safe 0 minCost 1.79769e+308 maxCost 2.22507e-308 locations 663
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: select ranges
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Total: 661
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Spilled: 0.000 (0)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Allocated: 1.000 (661)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Rover zone: 0.817 (540)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Pre-rover zone: 0.014 (9)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Post-rover zone: 0.169 (112)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Slice zone: 0.000 (0)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Blocks nothing: 0.002 (1)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Blocks medium: 0.000 (0)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Blocks tall: 0.998 (660)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Visited until tall blocking (mean): 0.993
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Visited until tall blocking (median): 1.000
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Visited until tall blocking (p95): 1.000
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: Success
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg00) [ModuleForkPass]: dynamic_dma_scan finished after 0.096 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 264mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1494 memory location(s), 1 block(s), and 2627 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z USER 796 (nc01/sg00) [ModuleForkPass]: Running build_fdeps
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to build_fdeps: modules=1 functions=1 allocs=1494 blocks=1 instructions=2627 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg00) [build_flow_deps]: Start build fdeps. Invocation: 5Sun Nov 9 20:57:19 2025
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: SB spills = 0 tensors
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: size = 0 bytes/partition
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: remats = 0 tensors
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: unpinned = 0 tensors
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: size = 0 bytes/partition
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: SB score = 0
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: spilling from SB cost about 0 cycles
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: 16392 bytes/partition (100%) successfully pinned
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: pinning saved approximately 8300 cycles
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [SB_Allocator]: 0% SB utilization after allocation
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes loaded 54583812
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: INFO: Post GCA average loaded DMA size 3112 bytes
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes saved 15728642
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: INFO: Post GCA average saved DMA size 2792 bytes
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 1064960
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 130 bytes
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg01) [ModuleForkPass]: coloring_allocator_sb finished after 0.411 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 264mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 930 memory location(s), 1 block(s), and 2929 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:19Z INFO 796 [LayerSpiller]: LayerSpill: Found 2 Splits CCs
|
|
2025-11-09T20:57:19Z INFO 796 [LayerSpiller]: Grouped CCs to 2 clusters.
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg01) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=930 blocks=1 instructions=2929 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:19Z INFO 796 (nc01/sg00) [build_flow_deps]: Allocs: 1494 instructions: 2627
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: birverifier finished after 0.403 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 263mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1495 memory location(s), 1 block(s), and 2630 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: Running dynamic_dma_scan
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to dynamic_dma_scan: modules=1 functions=1 allocs=1495 blocks=1 instructions=2630 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg01) [ModuleForkPass]: address_rotation_sb finished after 0.008 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 263mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 930 memory location(s), 1 block(s), and 2929 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg01) [ModuleForkPass]: Running dma_optimization_sb
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to dma_optimization_sb: modules=1 functions=1 allocs=930 blocks=1 instructions=2929 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: DMA optimization In bytes loaded or saved 70312454, 62.7173% input load, 5.96524% output write, 31.3175% spill/reload [sg0001]
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: removed 0 identical load
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: dynamic_dma_scan finished after 0.008 seconds
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 263mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1495 memory location(s), 1 block(s), and 2630 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z USER 796 (nc00/sg00) [ModuleForkPass]: Running build_fdeps
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to build_fdeps: modules=1 functions=1 allocs=1495 blocks=1 instructions=2630 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [build_flow_deps]: Start build fdeps. Invocation: 6Sun Nov 9 20:57:19 2025
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg00) [build_flow_deps]: Allocs: 1495 instructions: 2630
|
|
2025-11-09T20:57:19Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: adjusted 0 DMACopy remat
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: sub-graph will get execute 27 times
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [Load Merging]: removed 0 remat/cloned instructions
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [Load shrink]: shrinked 0 GCA remat/cloned instructions
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [Load Merging + Load shrink] reduced input/const loading DMA traffic 4718592, 6.71089% out of total dma traffic(4.40981e+07)
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [Re-allocation Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [remove extra save] removed 0 memlocs and 0 instructions
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: DMA SpillSave Coalescing Round 0 combined 0 SpillSaves and Reloads
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: average loaded DMA size 3091 bytes
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: average saved DMA size 2792 bytes
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes loaded 49865220
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: INFO: Post DMA coalescing average loaded DMA size 3091 bytes
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes saved 15728642
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: INFO: Post DMA coalescing average saved DMA size 2792 bytes
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 39 Sb address
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [Experiment partial DMA access] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: [DMA optimization] reduced DMA traffic 4718592, 6.71089% out of total dma traffic
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: DMA optimization Out bytes loaded or saved 65593862, 60.0353% input load, 6.39436% output write, 33.5704% spill/reload [sg0001]
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes loaded 49865220
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization average loaded DMA size 3091 bytes
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes saved 15728642
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization average saved DMA size 2792 bytes
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes DMAcopyed 1064960
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization average DMAcopyed DMA size 130 bytes
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: INFO: Post DMA optimization average DMA size 2225 bytes
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: INFO: Finished set_spill_canreadUninit(module);
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: DMA optimization re-enable optimization
|
|
2025-11-09T20:57:20Z USER 796 (nc00/sg01) [ModuleForkPass]: dma_optimization_sb finished after 0.111 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 263mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 2918 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:20Z USER 796 (nc00/sg01) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=918 blocks=1 instructions=2918 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 7 Sb address
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 42 Sb address
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 21 Sb address
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: address_rotation_sb finished after 0.980 seconds
|
|
2025-11-09T20:57:20Z INFO 796 [LayerSpiller]: LayerSpill: To Spill 0 multi-layer tensors
|
|
2025-11-09T20:57:20Z INFO 796 [LayerSpiller]: LayerSpill: set uninit flag on 0 insts
|
|
2025-11-09T20:57:20Z INFO 796 [LayerSpiller]: LayerSpill: Done.
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg02) [PreSched]: Start split live ranges Sun Nov 9 20:57:19 2025
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 264mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 917 memory location(s), 1 block(s), and 2915 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: Running coloring_allocator_dram
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to coloring_allocator_dram: modules=1 functions=1 allocs=917 blocks=1 instructions=2915 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Local
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: reserved space = 98304 bytes
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: spill space = 0 bytes
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: aligned spill space = 0 bytes
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: renumber locations
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: size = 0
|
|
2025-11-09T20:57:20Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:20Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: Num intervals 0 Num locations 0
|
|
2025-11-09T20:57:20Z USER 796 (nc00/sg02) [ModuleForkPass]: constant_propagate finished after 3.068 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: lo = 0
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: hi = 0
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: total = 0
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: simplify
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 264mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: select ranges
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: CC buffer size limit 524288000
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: allreduce_dram_hwm 0
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: Real CC buffer size 0
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: DRAM hwm after allocation: 0
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DRAM_Allocator]: DRAM allocation successful
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: coloring_allocator_dram finished after 0.086 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 264mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 917 memory location(s), 1 block(s), and 2915 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: Running address_rotation_dram
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to address_rotation_dram: modules=1 functions=1 allocs=917 blocks=1 instructions=2915 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: Runtime page size at 512MB
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: DRAM hwm before rotation 0
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: allreduce buffer size 524288000
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: allreduce hwm 8388608
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: Real CC buffer size 8388608
|
|
2025-11-09T20:57:20Z USER 796 (nc00/sg02) [ModuleForkPass]: Running lower_ac
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to lower_ac: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: DRAM hwm after rotation 0
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: DRAM Rotation rotated 0 Dram address
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: address_rotation_dram finished after 0.007 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 264mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 917 memory location(s), 1 block(s), and 2915 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: Running tensorcopy_accel
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to tensorcopy_accel: modules=1 functions=1 allocs=917 blocks=1 instructions=2915 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [TensorCopyAccel::Impl]: Running peephole optimization pass
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [TensorCopyAccel::Impl]: Accelerated 26 out of 189 tensorcopy in Function: sg0001 average acceleration factor: 1
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: tensorcopy_accel finished after 0.013 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 264mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 917 memory location(s), 1 block(s), and 2915 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: Running peephole_opts
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to peephole_opts: modules=1 functions=1 allocs=917 blocks=1 instructions=2915 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [PeepholeOpts]: PeepholeOpts enabled? Recip: true Tsp: true Tc: false SplitSelect: true SimplifyMemset true
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [build_flow_deps]: Build fdeps inserted 5870 edges
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [build_flow_deps]: Done build fdeps 5870 Sun Nov 9 20:57:20 2025
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg00) [ModuleForkPass]: build_fdeps finished after 0.488 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 265mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg02) [PreSched]: No split opportunities:
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg02) [PreSched]: End split live ranges Sun Nov 9 20:57:20 2025
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg02) [PreSched]: Strt remove redundncies Sun Nov 9 20:57:20 2025
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg02) [PreSched]: remove_redundant_memsets
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1494 memory location(s), 1 block(s), and 2627 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg00) [ModuleForkPass]: Running remove_redundancies
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to remove_redundancies: modules=1 functions=1 allocs=1494 blocks=1 instructions=2627 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [RemoveRedundancies]: remove_clobbered_writes
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: peephole_opts finished after 0.087 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 266mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 917 memory location(s), 1 block(s), and 2916 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: Running lower_kernel
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to lower_kernel: modules=1 functions=1 allocs=917 blocks=1 instructions=2916 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Started running LowerKernel
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: BIR SB coloring allocator is disabled
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Start of kernel lowering pass, number of insts: 2916, number of allocs: 917
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Found InstBIRKernel: [CausalAttentionMMSoftmaxMMWithoutSwap]I-2442-0
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Scan BKs time (s): 0.000414
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Set architecture: gen3
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [RemoveRedundancies]: remove_clobbered_writes: 0
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [RemoveRedundancies]: remove_useless_insts
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Input/output shapes for Kernel inst [I-2442-0]
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: input0: [ 2 128 2048 ]
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: input1: [ 2 128 2048 ]
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: input2: [ 2 2048 128 ]
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: input3: ap
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: output0: [ 2 128 2048 ]
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: do_input1_tp=false
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: do_out_tp=true
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Legalized inp_ap=[[262144,2],[2048,128],[1,2048]]
|
|
Offset: 524288
|
|
Memory Location: {reshape.60}@DRAM<Shared>(1048576x2)#Internal DebugInfo: <reshape.60||NHC||[1048576, 1, 1]>
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Legalized inp_ap=[[262144,2],[2048,128],[1,2048]]
|
|
Offset: 524288
|
|
Memory Location: {reshape.68}@DRAM<Shared>(1048576x2)#Internal DebugInfo: <reshape.68||NHC||[1048576, 1, 1]>
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: AP of Q indicates standalone Q tensor.
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: parallel_split_n = input1_ap[1].getStep() / input1_ap[2].getNum() = 2048 / 2048 = 1
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Sharding/tiling split_i=0, split_n=1
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Flash attention has been disabled
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Scratch sbuf for kernel I-2442-0: [47104, 107388)
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: seq_len=2048, seq_len2=2048, complete_seq_len2=2048
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Creating identity matrices with AffineSelect
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [LowerAC]: INFO (LowerAC) Lowered 0 loads, 0 saves, 0 copies.
|
|
2025-11-09T20:57:20Z USER 796 (nc00/sg02) [ModuleForkPass]: lower_ac finished after 0.119 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 266mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:20Z USER 796 (nc00/sg02) [ModuleForkPass]: Running input_dma_coalescing
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to input_dma_coalescing: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [build_flow_deps]: Build fdeps inserted 5872 edges
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [build_flow_deps]: Done build fdeps 5872 Sun Nov 9 20:57:20 2025
|
|
2025-11-09T20:57:20Z USER 796 (nc00/sg00) [ModuleForkPass]: build_fdeps finished after 0.408 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 266mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1495 memory location(s), 1 block(s), and 2630 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:20Z USER 796 (nc00/sg00) [ModuleForkPass]: Running remove_redundancies
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to remove_redundancies: modules=1 functions=1 allocs=1495 blocks=1 instructions=2630 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [RemoveRedundancies]: remove_clobbered_writes
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [RemoveRedundancies]: remove_clobbered_writes: 0
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [RemoveRedundancies]: remove_useless_insts
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [RemoveRedundancies]: remove Useless Instructions: 14
|
|
2025-11-09T20:57:20Z USER 796 (nc00/sg00) [ModuleForkPass]: remove_redundancies finished after 0.005 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg02) [PreSched]: remove_redundant_memsets: 1
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg02) [PreSched]: remove_redundant_loads
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [RemoveRedundancies]: remove Useless Instructions: 14
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg00) [ModuleForkPass]: remove_redundancies finished after 0.095 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 268mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1488 memory location(s), 1 block(s), and 2613 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg00) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1488 blocks=1 instructions=2613 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB}
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 268mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1489 memory location(s), 1 block(s), and 2616 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:20Z USER 796 (nc00/sg00) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1489 blocks=1 instructions=2616 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB}
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: seq_len=2048, seq_len2=2048, complete_seq_len2=2048
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Creating identity matrices with AffineSelect
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [LowerKernel]: Lower BKs time (s): 0.348522
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: lower_kernel finished after 0.296 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 274mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1484 memory location(s), 1 block(s), and 3917 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: Running lower_klir_kernel
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=1484 blocks=1 instructions=3917 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg02) [PreSched]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: lower_klir_kernel finished after 0.008 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 275mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1484 memory location(s), 1 block(s), and 3917 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: Running lower_nki_kernel
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=1484 blocks=1 instructions=3917 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: lower_nki_kernel finished after 0.005 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 276mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg02) [PreSched]: End remove redundncies Sun Nov 9 20:57:20 2025
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1484 memory location(s), 1 block(s), and 3917 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg02) [PreSched]: Start DCE Sun Nov 9 20:57:20 2025
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg01) [ModuleForkPass]: Running non_ssa_legalization
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=1484 blocks=1 instructions=3917 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [NonSSALeg]: remove_redundant_loads
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg01) [NonSSALeg]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: DMA input Coalescing combined 0 input loads
|
|
2025-11-09T20:57:20Z USER 796 (nc00/sg02) [ModuleForkPass]: input_dma_coalescing finished after 0.489 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 276mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:20Z USER 796 (nc00/sg02) [ModuleForkPass]: Running remat_optimization
|
|
2025-11-09T20:57:20Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to remat_optimization: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg00) [ModuleForkPass]: anti_dependency_analyzer finished after 0.498 seconds
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 277mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1488 memory location(s), 1 block(s), and 2613 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:20Z USER 796 (nc01/sg00) [ModuleForkPass]: Running tensor_copy_elim
|
|
2025-11-09T20:57:20Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=1488 blocks=1 instructions=2613 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:21Z USER 796 (nc00/sg00) [ModuleForkPass]: anti_dependency_analyzer finished after 0.508 seconds
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 276mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1489 memory location(s), 1 block(s), and 2616 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:21Z USER 796 (nc00/sg00) [ModuleForkPass]: Running tensor_copy_elim
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=1489 blocks=1 instructions=2616 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg00) [TensorCopyElim]: Tensor CP elimination: 32
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg00) [TensorCopyElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg02) [PreSched]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:21Z USER 796 (nc01/sg00) [ModuleForkPass]: tensor_copy_elim finished after 0.190 seconds
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 276mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [NonSSALeg]: [Non-SSA legalization]created 16 memorylocations
|
|
2025-11-09T20:57:21Z USER 796 (nc01/sg01) [ModuleForkPass]: non_ssa_legalization finished after 0.386 seconds
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 276mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2581 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:21Z USER 796 (nc01/sg00) [ModuleForkPass]: Running dead_code_elim_o0
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=1455 blocks=1 instructions=2581 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1492 memory location(s), 1 block(s), and 3917 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:21Z USER 796 (nc01/sg01) [ModuleForkPass]: Running dynamic_dma_cleanup
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to dynamic_dma_cleanup: modules=1 functions=1 allocs=1492 blocks=1 instructions=3917 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg00) [TensorCopyElim]: Tensor CP elimination: 32
|
|
2025-11-09T20:57:21Z USER 796 (nc01/sg01) [ModuleForkPass]: dynamic_dma_cleanup finished after 0.008 seconds
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 276mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1492 memory location(s), 1 block(s), and 3917 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:21Z USER 796 (nc01/sg01) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=1492 blocks=1 instructions=3917 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:21Z WARNING 796 [birverifier::InstVisitor]: (nc01/sg01) Non - output memory location with no reader: {I-2442-0_s0_aten__mul_broadcast.7-t210_b0}@SB<0,56580>(128x4)#Internal DebugInfo: <I-2442-0_s0_aten__mul_broadcast.7-t210_b0||NC||[128, 1]>
|
|
2025-11-09T20:57:21Z WARNING 796 [birverifier::InstVisitor]: (nc01/sg01) Non - output memory location with no reader: {I-2442-0_s0_aten__mul_broadcast.7-t210_b1}@SB<0,56580>(128x4)#Internal DebugInfo: <I-2442-0_s0_aten__mul_broadcast.7-t210_b1||NC||[128, 1]>
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg00) [TensorCopyElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:21Z USER 796 (nc01/sg00) [ModuleForkPass]: dead_code_elim_o0 finished after 0.117 seconds
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 276mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2581 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:21Z USER 796 (nc00/sg00) [ModuleForkPass]: tensor_copy_elim finished after 0.311 seconds
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 276mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2584 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg02) [PreSched]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:21Z USER 796 (nc00/sg00) [ModuleForkPass]: Running dead_code_elim_o0
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=1456 blocks=1 instructions=2584 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg02) [PreSched]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg02) [PreSched]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg02) [PreSched]: End DCE Sun Nov 9 20:57:21 2025
|
|
2025-11-09T20:57:21Z USER 796 (nc00/sg00) [ModuleForkPass]: dead_code_elim_o0 finished after 0.098 seconds
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 276mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2584 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 22 Sb address
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg02) [PreSched]: Start build flow dependencies Sun Nov 9 20:57:21 2025
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg02) [build_flow_deps]: Start build fdeps. Invocation: 7Sun Nov 9 20:57:21 2025
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 22 Sb address
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg02) [build_flow_deps]: Allocs: 1758 instructions: 8019
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:21Z USER 796 (nc01/sg01) [ModuleForkPass]: birverifier finished after 0.684 seconds
|
|
2025-11-09T20:57:21Z USER 796 (nc00/sg01) [ModuleForkPass]: address_rotation_sb finished after 1.770 seconds
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 276mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 276mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1492 memory location(s), 1 block(s), and 3917 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:21Z USER 796 (nc01/sg01) [ModuleForkPass]: Running dynamic_dma_scan
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to dynamic_dma_scan: modules=1 functions=1 allocs=1492 blocks=1 instructions=3917 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 2918 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:21Z USER 796 (nc00/sg01) [ModuleForkPass]: Running coloring_allocator_dram
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to coloring_allocator_dram: modules=1 functions=1 allocs=918 blocks=1 instructions=2918 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Local
|
|
2025-11-09T20:57:21Z USER 796 (nc01/sg01) [ModuleForkPass]: dynamic_dma_scan finished after 0.021 seconds
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 275mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1492 memory location(s), 1 block(s), and 3917 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:21Z USER 796 (nc01/sg01) [ModuleForkPass]: Running build_fdeps
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to build_fdeps: modules=1 functions=1 allocs=1492 blocks=1 instructions=3917 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [build_flow_deps]: Start build fdeps. Invocation: 8Sun Nov 9 20:57:21 2025
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg02) [RematOpt]: Removed 0 remat instructions
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: reserved space = 98304 bytes
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: spill space = 0 bytes
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: aligned spill space = 0 bytes
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:57:21Z USER 796 (nc00/sg02) [ModuleForkPass]: remat_optimization finished after 1.073 seconds
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: renumber locations
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: size = 0
|
|
2025-11-09T20:57:21Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 275mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:21Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:21Z INFO 796 (nc01/sg01) [build_flow_deps]: Allocs: 1492 instructions: 3917
|
|
2025-11-09T20:57:21Z USER 796 (nc00/sg02) [ModuleForkPass]: Running coalesce_multichannel_cc_ops
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to coalesce_multichannel_cc_ops: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: Num intervals 0 Num locations 0
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: lo = 0
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: hi = 0
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: total = 0
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: simplify
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: select ranges
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: CC buffer size limit 524288000
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: allreduce_dram_hwm 0
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: Real CC buffer size 0
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: DRAM hwm after allocation: 0
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg01) [DRAM_Allocator]: DRAM allocation successful
|
|
2025-11-09T20:57:21Z USER 796 (nc00/sg01) [ModuleForkPass]: coloring_allocator_dram finished after 0.109 seconds
|
|
2025-11-09T20:57:21Z USER 796 (nc00/sg02) [ModuleForkPass]: coalesce_multichannel_cc_ops finished after 0.019 seconds
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 275mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:21Z USER 796 (nc00/sg02) [ModuleForkPass]: Running infer_stream_ids
|
|
2025-11-09T20:57:21Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to infer_stream_ids: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg02) [ModuleForkPass]: infer_stream_ids finished after 0.009 seconds
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 275mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8796 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg02) [ModuleForkPass]: Running pre_sched
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to pre_sched: modules=1 functions=1 allocs=2204 blocks=1 instructions=8796 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [PreSched]: Start PRE scheduling 2 cores: 1 at: Sun Nov 9 20:57:21 2025
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 275mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 2918 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: Running address_rotation_dram
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to address_rotation_dram: modules=1 functions=1 allocs=918 blocks=1 instructions=2918 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: Runtime page size at 512MB
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: DRAM hwm before rotation 0
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: allreduce buffer size 524288000
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: allreduce hwm 8388608
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: Real CC buffer size 8388608
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: DRAM hwm after rotation 0
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: DRAM Rotation rotated 0 Dram address
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: address_rotation_dram finished after 0.013 seconds
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 275mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 2918 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: Running tensorcopy_accel
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to tensorcopy_accel: modules=1 functions=1 allocs=918 blocks=1 instructions=2918 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [TensorCopyAccel::Impl]: Running peephole optimization pass
|
|
2025-11-09T20:57:22Z INFO 796 [LayerSpiller]: LayerSpill: Start...
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [TensorCopyAccel::Impl]: Accelerated 26 out of 190 tensorcopy in Function: sg0001 average acceleration factor: 1
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: tensorcopy_accel finished after 0.003 seconds
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 275mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 2918 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: Running peephole_opts
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to peephole_opts: modules=1 functions=1 allocs=918 blocks=1 instructions=2918 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [PeepholeOpts]: PeepholeOpts enabled? Recip: true Tsp: true Tc: false SplitSelect: true SimplifyMemset true
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: peephole_opts finished after 0.105 seconds
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 277mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 918 memory location(s), 1 block(s), and 2919 instruction(s). Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: Running lower_kernel
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to lower_kernel: modules=1 functions=1 allocs=918 blocks=1 instructions=2919 Max writers: 16 Max Readers: 448
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Started running LowerKernel
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: BIR SB coloring allocator is disabled
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Start of kernel lowering pass, number of insts: 2919, number of allocs: 918
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Found InstBIRKernel: [CausalAttentionMMSoftmaxMMWithoutSwap]I-2442-0
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Scan BKs time (s): 0.002287
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Set architecture: gen3
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Input/output shapes for Kernel inst [I-2442-0]
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: input0: [ 2 128 2048 ]
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: input1: [ 2 128 2048 ]
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: input2: [ 2 2048 128 ]
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: input3: ap
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: output0: [ 2 128 2048 ]
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: do_input1_tp=false
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: do_out_tp=true
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Legalized inp_ap=[[262144,2],[2048,128],[1,2048]]
|
|
Offset: 0
|
|
Memory Location: {reshape.60}@DRAM<Shared>(1048576x2)#Internal DebugInfo: <reshape.60||NHC||[1048576, 1, 1]>
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Legalized inp_ap=[[262144,2],[2048,128],[1,2048]]
|
|
Offset: 0
|
|
Memory Location: {reshape.68}@DRAM<Shared>(1048576x2)#Internal DebugInfo: <reshape.68||NHC||[1048576, 1, 1]>
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: AP of Q indicates standalone Q tensor.
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: parallel_split_n = input1_ap[1].getStep() / input1_ap[2].getNum() = 2048 / 2048 = 1
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Sharding/tiling split_i=0, split_n=1
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Flash attention has been disabled
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Scratch sbuf for kernel I-2442-0: [47104, 107388)
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: seq_len=2048, seq_len2=2048, complete_seq_len2=2048
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Creating identity matrices with AffineSelect
|
|
2025-11-09T20:57:22Z INFO 796 [LayerSpiller]: LayerSpill: Found 2 Splits CCs
|
|
2025-11-09T20:57:22Z INFO 796 [LayerSpiller]: Grouped CCs to 2 clusters.
|
|
2025-11-09T20:57:22Z INFO 796 [LayerSpiller]: LayerSpill: To Spill 0 multi-layer tensors
|
|
2025-11-09T20:57:22Z INFO 796 [LayerSpiller]: LayerSpill: set uninit flag on 0 insts
|
|
2025-11-09T20:57:22Z INFO 796 [LayerSpiller]: LayerSpill: Done.
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [PreSched]: Start split live ranges Sun Nov 9 20:57:21 2025
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: seq_len=2048, seq_len2=2048, complete_seq_len2=2048
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Creating identity matrices with AffineSelect
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [PreSched]: No split opportunities:
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [PreSched]: End split live ranges Sun Nov 9 20:57:22 2025
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [PreSched]: Strt remove redundncies Sun Nov 9 20:57:22 2025
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [PreSched]: remove_redundant_memsets
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [LowerKernel]: Lower BKs time (s): 0.269305
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: lower_kernel finished after 0.313 seconds
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 284mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg02) [build_flow_deps]: Build fdeps inserted 20936 edges
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg02) [build_flow_deps]: Done build fdeps 20936 Sun Nov 9 20:57:22 2025
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg02) [PreSched]: End build flow dependencies Sun Nov 9 20:57:22 2025
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg02) [PreSched]: Start remove useless insts Sun Nov 9 20:57:22 2025
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg02) [PreSched]: remove_useless_insts
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1485 memory location(s), 1 block(s), and 3920 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: Running lower_klir_kernel
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=1485 blocks=1 instructions=3920 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [build_flow_deps]: Build fdeps inserted 10125 edges
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [build_flow_deps]: Done build fdeps 10125 Sun Nov 9 20:57:22 2025
|
|
2025-11-09T20:57:22Z USER 796 (nc01/sg01) [ModuleForkPass]: build_fdeps finished after 0.686 seconds
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 284mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1492 memory location(s), 1 block(s), and 3917 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc01/sg01) [ModuleForkPass]: Running remove_redundancies
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to remove_redundancies: modules=1 functions=1 allocs=1492 blocks=1 instructions=3917 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [RemoveRedundancies]: remove_clobbered_writes
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: lower_klir_kernel finished after 0.006 seconds
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 284mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1485 memory location(s), 1 block(s), and 3920 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: Running lower_nki_kernel
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=1485 blocks=1 instructions=3920 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: lower_nki_kernel finished after 0.005 seconds
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 284mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1485 memory location(s), 1 block(s), and 3920 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: Running non_ssa_legalization
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=1485 blocks=1 instructions=3920 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [NonSSALeg]: remove_redundant_loads
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [RemoveRedundancies]: remove_clobbered_writes: 0
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [NonSSALeg]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [NonSSALeg]: [Non-SSA legalization]created 16 memorylocations
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: non_ssa_legalization finished after 0.011 seconds
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 285mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1493 memory location(s), 1 block(s), and 3920 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: Running dynamic_dma_cleanup
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to dynamic_dma_cleanup: modules=1 functions=1 allocs=1493 blocks=1 instructions=3920 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: dynamic_dma_cleanup finished after 0.001 seconds
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 285mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1493 memory location(s), 1 block(s), and 3920 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=1493 blocks=1 instructions=3920 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z WARNING 796 [birverifier::InstVisitor]: (nc00/sg01) Non - output memory location with no reader: {I-2442-0_s0_aten__mul_broadcast.7-t210_b0}@SB<0,56580>(128x4)#Internal DebugInfo: <I-2442-0_s0_aten__mul_broadcast.7-t210_b0||NC||[128, 1]>
|
|
2025-11-09T20:57:22Z WARNING 796 [birverifier::InstVisitor]: (nc00/sg01) Non - output memory location with no reader: {I-2442-0_s0_aten__mul_broadcast.7-t210_b1}@SB<0,56580>(128x4)#Internal DebugInfo: <I-2442-0_s0_aten__mul_broadcast.7-t210_b1||NC||[128, 1]>
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [RemoveRedundancies]: remove_useless_insts
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [PreSched]: remove_redundant_memsets: 5
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [PreSched]: remove_redundant_loads
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg02) [PreSched]: remove Useless Instructions: 0
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg02) [PreSched]: End remove useless insts Sun Nov 9 20:57:22 2025
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg02) [PreSched]: Start scratchpad optimization Sun Nov 9 20:57:22 2025
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: birverifier finished after 0.090 seconds
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 285mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1493 memory location(s), 1 block(s), and 3920 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: Running dynamic_dma_scan
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to dynamic_dma_scan: modules=1 functions=1 allocs=1493 blocks=1 instructions=3920 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: dynamic_dma_scan finished after 0.072 seconds
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 285mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1493 memory location(s), 1 block(s), and 3920 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc00/sg01) [ModuleForkPass]: Running build_fdeps
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to build_fdeps: modules=1 functions=1 allocs=1493 blocks=1 instructions=3920 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [build_flow_deps]: Start build fdeps. Invocation: 9Sun Nov 9 20:57:22 2025
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg01) [build_flow_deps]: Allocs: 1493 instructions: 3920
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [PreSched]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [PreSched]: End remove redundncies Sun Nov 9 20:57:22 2025
|
|
2025-11-09T20:57:22Z INFO 796 (nc00/sg02) [PreSched]: Start DCE Sun Nov 9 20:57:22 2025
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [RemoveRedundancies]: remove Useless Instructions: 14
|
|
2025-11-09T20:57:22Z USER 796 (nc01/sg01) [ModuleForkPass]: remove_redundancies finished after 0.204 seconds
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 285mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1486 memory location(s), 1 block(s), and 3903 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z USER 796 (nc01/sg01) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1486 blocks=1 instructions=3903 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB}
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg01) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:22Z INFO 796 (nc01/sg02) [PreSched]: End scratchpad optimization Sun Nov 9 20:57:22 2025
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [build_flow_deps]: Build fdeps inserted 10127 edges
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [build_flow_deps]: Done build fdeps 10127 Sun Nov 9 20:57:23 2025
|
|
2025-11-09T20:57:23Z USER 796 (nc00/sg01) [ModuleForkPass]: build_fdeps finished after 0.310 seconds
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 287mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1493 memory location(s), 1 block(s), and 3920 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:23Z USER 796 (nc00/sg01) [ModuleForkPass]: Running remove_redundancies
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to remove_redundancies: modules=1 functions=1 allocs=1493 blocks=1 instructions=3920 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [RemoveRedundancies]: remove_clobbered_writes
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [RemoveRedundancies]: remove_clobbered_writes: 0
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [RemoveRedundancies]: remove_useless_insts
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [RemoveRedundancies]: remove Useless Instructions: 14
|
|
2025-11-09T20:57:23Z USER 796 (nc00/sg01) [ModuleForkPass]: remove_redundancies finished after 0.095 seconds
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 287mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1487 memory location(s), 1 block(s), and 3906 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:23Z USER 796 (nc00/sg01) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1487 blocks=1 instructions=3906 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB}
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg02) [PreSched]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg02) [PreSched]: DONE PRE scheduling Sun Nov 9 20:57:23 2025
|
|
2025-11-09T20:57:23Z USER 796 (nc01/sg02) [ModuleForkPass]: pre_sched finished after 3.802 seconds
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 288mb, ru_maxrss: 288mb (delta=0mb)
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8019 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:23Z USER 796 (nc01/sg02) [ModuleForkPass]: Running tensor_copy_elim
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=1758 blocks=1 instructions=8019 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:23Z USER 796 (nc01/sg01) [ModuleForkPass]: anti_dependency_analyzer finished after 0.708 seconds
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 291mb, ru_maxrss: 290mb (delta=2mb)
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1486 memory location(s), 1 block(s), and 3903 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:23Z USER 796 (nc01/sg01) [ModuleForkPass]: Running tensor_copy_elim
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=1486 blocks=1 instructions=3903 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg02) [TensorCopyElim]: Tensor CP elimination: 0
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg01) [TensorCopyElim]: Tensor CP elimination: 32
|
|
2025-11-09T20:57:23Z USER 796 (nc00/sg01) [ModuleForkPass]: anti_dependency_analyzer finished after 0.493 seconds
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 291mb, ru_maxrss: 290mb (delta=2mb)
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg01) [TensorCopyElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1487 memory location(s), 1 block(s), and 3906 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:23Z USER 796 (nc00/sg01) [ModuleForkPass]: Running tensor_copy_elim
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=1487 blocks=1 instructions=3906 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg02) [TensorCopyElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:23Z USER 796 (nc01/sg01) [ModuleForkPass]: tensor_copy_elim finished after 0.264 seconds
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 290mb, ru_maxrss: 290mb (delta=0mb)
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3871 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:23Z USER 796 (nc01/sg01) [ModuleForkPass]: Running dead_code_elim_o0
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=1453 blocks=1 instructions=3871 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:23Z USER 796 (nc01/sg01) [ModuleForkPass]: dead_code_elim_o0 finished after 0.101 seconds
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 290mb, ru_maxrss: 290mb (delta=0mb)
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3871 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [TensorCopyElim]: Tensor CP elimination: 32
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg02) [PreSched]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg02) [PreSched]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg02) [TensorCopyElim]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg01) [TensorCopyElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg02) [PreSched]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:23Z INFO 796 (nc00/sg02) [PreSched]: End DCE Sun Nov 9 20:57:23 2025
|
|
2025-11-09T20:57:23Z INFO 796 (nc01/sg02) [TensorCopyElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:24Z USER 796 (nc00/sg01) [ModuleForkPass]: tensor_copy_elim finished after 0.392 seconds
|
|
2025-11-09T20:57:24Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 290mb, ru_maxrss: 290mb (delta=0mb)
|
|
2025-11-09T20:57:24Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3874 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:24Z USER 796 (nc00/sg01) [ModuleForkPass]: Running dead_code_elim_o0
|
|
2025-11-09T20:57:24Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=1454 blocks=1 instructions=3874 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [TensorCopyElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:24Z USER 796 (nc01/sg02) [ModuleForkPass]: tensor_copy_elim finished after 0.884 seconds
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 290mb, ru_maxrss: 290mb (delta=2mb)
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1758 memory location(s), 1 block(s), and 8019 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:24Z USER 796 (nc01/sg02) [ModuleForkPass]: Running dynamic_dma_setup
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to dynamic_dma_setup: modules=1 functions=1 allocs=1758 blocks=1 instructions=8019 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:24Z USER 796 (nc01/sg02) [ModuleForkPass]: dynamic_dma_setup finished after 0.001 seconds
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 290mb, ru_maxrss: 290mb (delta=0mb)
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1759 memory location(s), 1 block(s), and 8019 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:24Z USER 796 (nc01/sg02) [ModuleForkPass]: Running runtime_memory_reservation
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to runtime_memory_reservation: modules=1 functions=1 allocs=1759 blocks=1 instructions=8019 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:24Z USER 796 (nc01/sg02) [ModuleForkPass]: runtime_memory_reservation finished after 0.001 seconds
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 290mb, ru_maxrss: 290mb (delta=0mb)
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1760 memory location(s), 1 block(s), and 8019 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:24Z USER 796 (nc01/sg02) [ModuleForkPass]: Running lower_klir_kernel
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=1760 blocks=1 instructions=8019 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:24Z USER 796 (nc01/sg02) [ModuleForkPass]: lower_klir_kernel finished after 0.009 seconds
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 290mb, ru_maxrss: 290mb (delta=0mb)
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1760 memory location(s), 1 block(s), and 8019 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:24Z USER 796 (nc01/sg02) [ModuleForkPass]: Running lower_nki_kernel
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=1760 blocks=1 instructions=8019 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:24Z USER 796 (nc01/sg02) [ModuleForkPass]: lower_nki_kernel finished after 0.007 seconds
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 290mb, ru_maxrss: 290mb (delta=0mb)
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1760 memory location(s), 1 block(s), and 8019 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:24Z USER 796 (nc01/sg02) [ModuleForkPass]: Running coloring_allocator_psum
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to coloring_allocator_psum: modules=1 functions=1 allocs=1760 blocks=1 instructions=8019 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:24Z USER 796 (nc00/sg01) [ModuleForkPass]: dead_code_elim_o0 finished after 0.179 seconds
|
|
2025-11-09T20:57:24Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 290mb, ru_maxrss: 290mb (delta=0mb)
|
|
2025-11-09T20:57:24Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3874 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [PSUM_Allocator]: allocating PSUM
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [PSUM_Allocator]: main loop
|
|
2025-11-09T20:57:24Z INFO 796 (nc00/sg02) [PreSched]: Start build flow dependencies Sun Nov 9 20:57:24 2025
|
|
2025-11-09T20:57:24Z INFO 796 (nc00/sg02) [build_flow_deps]: Start build fdeps. Invocation: 10Sun Nov 9 20:57:24 2025
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [PSUM_Allocator]: renumber locations
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [PSUM_Allocator]: size = 625
|
|
2025-11-09T20:57:24Z INFO 796 (nc00/sg02) [build_flow_deps]: Allocs: 2204 instructions: 8791
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [PSUM_Allocator]: build_no_bitmap start
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [PSUM_Allocator]: 100% PSUM demand before spilling
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [PSUM_Allocator]: PSUM high-water mark = 8 tensors
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [PSUM_Allocator]: found 838 edges
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [PSUM_Allocator]: mean: 2.6816
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [PSUM_Allocator]: median: 1.9709
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [PSUM_Allocator]: adjacency vectors require 6704 bytes
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [PSUM_Allocator]: build_no_bitmap done
|
|
2025-11-09T20:57:24Z INFO 796 (nc01/sg02) [PSUM_Allocator]: find costs
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: best-of-n loop, heuristic = 0, allow_psum_spill_within_accum_group = false
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: lo = 588
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: hi = 37
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: inf = 0
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: total = 625
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: simplify
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: select ranges
|
|
2025-11-09T20:57:25Z INFO 796 (nc00/sg02) [build_flow_deps]: Build fdeps inserted 32694 edges
|
|
2025-11-09T20:57:25Z INFO 796 (nc00/sg02) [build_flow_deps]: Done build fdeps 32694 Sun Nov 9 20:57:25 2025
|
|
2025-11-09T20:57:25Z INFO 796 (nc00/sg02) [PreSched]: End build flow dependencies Sun Nov 9 20:57:25 2025
|
|
2025-11-09T20:57:25Z INFO 796 (nc00/sg02) [PreSched]: Start remove useless insts Sun Nov 9 20:57:25 2025
|
|
2025-11-09T20:57:25Z INFO 796 (nc00/sg02) [PreSched]: remove_useless_insts
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: no more spills
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: PSUM score = 0 (lower is better)
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: spilling from PSUM cost about 0 cycles
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [PSUM_Allocator]: 100% PSUM utilization after allocation
|
|
2025-11-09T20:57:25Z USER 796 (nc01/sg02) [ModuleForkPass]: coloring_allocator_psum finished after 1.318 seconds
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 292mb, ru_maxrss: 290mb (delta=0mb)
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1760 memory location(s), 1 block(s), and 8019 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:25Z USER 796 (nc01/sg02) [ModuleForkPass]: Running dma_optimization_psum
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to dma_optimization_psum: modules=1 functions=1 allocs=1760 blocks=1 instructions=8019 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:25Z INFO 796 (nc00/sg02) [PreSched]: remove Useless Instructions: 0
|
|
2025-11-09T20:57:25Z INFO 796 (nc00/sg02) [PreSched]: End remove useless insts Sun Nov 9 20:57:25 2025
|
|
2025-11-09T20:57:25Z INFO 796 (nc00/sg02) [PreSched]: Start scratchpad optimization Sun Nov 9 20:57:25 2025
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:25Z USER 796 (nc01/sg02) [ModuleForkPass]: dma_optimization_psum finished after 0.185 seconds
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 291mb, ru_maxrss: 290mb (delta=0mb)
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1760 memory location(s), 1 block(s), and 8019 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:25Z USER 796 (nc01/sg02) [ModuleForkPass]: Running address_rotation_psum
|
|
2025-11-09T20:57:25Z INFO 796 (nc00/sg02) [PreSched]: End scratchpad optimization Sun Nov 9 20:57:25 2025
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to address_rotation_psum: modules=1 functions=1 allocs=1760 blocks=1 instructions=8019 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: PSUM Rotation rotated 0 PSUM Banks
|
|
2025-11-09T20:57:25Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: PSUM Rotation rotated 19 PSUM Banks
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: PSUM Rotation rotated 6 PSUM Banks
|
|
2025-11-09T20:57:26Z USER 796 (nc01/sg02) [ModuleForkPass]: address_rotation_psum finished after 0.296 seconds
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 293mb, ru_maxrss: 291mb (delta=1mb)
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1760 memory location(s), 1 block(s), and 8019 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:26Z USER 796 (nc01/sg02) [ModuleForkPass]: Running coloring_allocator_sb
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to coloring_allocator_sb: modules=1 functions=1 allocs=1760 blocks=1 instructions=8019 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes loaded 123985042
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: INFO: Pre GCA average loaded DMA size 3676 bytes
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes saved 8465728
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: INFO: Pre GCA average saved DMA size 3848 bytes
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 4100
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 241 bytes
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: allocating SB
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: main loop
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: renumber locations
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: size = 1098
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: find partners
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: found 618 accumulation groups
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: largest = custom-call.351.1631_i3
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: tensors = 17
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: requires 33280 bytes/partition
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: expanding partners
|
|
2025-11-09T20:57:26Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:26Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:26Z INFO 796 (nc00/sg02) [PreSched]: DONE PRE scheduling Sun Nov 9 20:57:26 2025
|
|
2025-11-09T20:57:26Z USER 796 (nc00/sg02) [ModuleForkPass]: pre_sched finished after 4.873 seconds
|
|
2025-11-09T20:57:26Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 292mb, ru_maxrss: 291mb (delta=3mb)
|
|
2025-11-09T20:57:26Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2204 memory location(s), 1 block(s), and 8791 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:26Z USER 796 (nc00/sg02) [ModuleForkPass]: Running tensor_copy_elim
|
|
2025-11-09T20:57:26Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=2204 blocks=1 instructions=8791 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: find loads
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: 2 pin count
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: 276 remat count
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: 2 pinned tensors will require about 16392 bytes/partition
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: build interference graph
|
|
2025-11-09T20:57:26Z INFO 796 (nc01/sg02) [SB_Allocator]: pass 1 int-tree
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Num intervals 1098 Num locations 1098
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: info.neighbors partners Done
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: edge: 14777
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: mean: 26.9162
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: median: 22.2029
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: find costs
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: best-of-n loop, heuristic = 0
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: initialize safe & unsafe
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: safe = 997
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: unsafe = 89
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: inf = 10
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: total = 1096
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: simplify
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: simplify_step3_sorted2 #Unsafe 0 #Pinned 0 #Safe 0 minCost 1.79769e+308 maxCost 2.22507e-308 locations 1098
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: select ranges
|
|
2025-11-09T20:57:27Z INFO 796 (nc00/sg02) [TensorCopyElim]: Tensor CP elimination: 63
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Total: 1096
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Spilled: 0.000 (0)
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Allocated: 1.000 (1096)
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Rover zone: 0.922 (1010)
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Pre-rover zone: 0.022 (24)
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Post-rover zone: 0.057 (62)
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Slice zone: 0.000 (0)
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Blocks nothing: 0.024 (26)
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Blocks medium: 0.002 (2)
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Visited until medium blocking (mean): 0.716
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Visited until medium blocking (median): 0.714
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Visited until medium blocking (p95): 0.714
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Blocks tall: 0.974 (1068)
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Visited until tall blocking (mean): 0.829
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Visited until tall blocking (median): 0.997
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Visited until tall blocking (p95): 1.000
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: Success
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: SB spills = 0 tensors
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: size = 0 bytes/partition
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: remats = 0 tensors
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: unpinned = 0 tensors
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: size = 0 bytes/partition
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: SB score = 0
|
|
2025-11-09T20:57:27Z INFO 796 (nc00/sg02) [TensorCopyElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: spilling from SB cost about 0 cycles
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: 16392 bytes/partition (100%) successfully pinned
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: pinning saved approximately 8300 cycles
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [SB_Allocator]: 0% SB utilization after allocation
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes loaded 123985042
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: INFO: Post GCA average loaded DMA size 3676 bytes
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes saved 8465728
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: INFO: Post GCA average saved DMA size 3848 bytes
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 4100
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 241 bytes
|
|
2025-11-09T20:57:27Z USER 796 (nc01/sg02) [ModuleForkPass]: coloring_allocator_sb finished after 1.810 seconds
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 293mb, ru_maxrss: 292mb (delta=1mb)
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1760 memory location(s), 1 block(s), and 8019 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:27Z USER 796 (nc01/sg02) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:27Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=1760 blocks=1 instructions=8019 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [TensorCopyElim]: remove_must_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [TensorCopyElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [TensorCopyElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys
|
|
2025-11-09T20:57:28Z USER 796 (nc00/sg02) [ModuleForkPass]: tensor_copy_elim finished after 1.416 seconds
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 291mb, ru_maxrss: 292mb (delta=1mb)
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2141 memory location(s), 1 block(s), and 8728 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:28Z USER 796 (nc00/sg02) [ModuleForkPass]: Running dynamic_dma_setup
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to dynamic_dma_setup: modules=1 functions=1 allocs=2141 blocks=1 instructions=8728 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:28Z USER 796 (nc00/sg02) [ModuleForkPass]: dynamic_dma_setup finished after 0.001 seconds
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 290mb, ru_maxrss: 292mb (delta=0mb)
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2142 memory location(s), 1 block(s), and 8728 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:28Z USER 796 (nc00/sg02) [ModuleForkPass]: Running runtime_memory_reservation
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to runtime_memory_reservation: modules=1 functions=1 allocs=2142 blocks=1 instructions=8728 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:28Z USER 796 (nc00/sg02) [ModuleForkPass]: runtime_memory_reservation finished after 0.000 seconds
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 290mb, ru_maxrss: 292mb (delta=0mb)
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2143 memory location(s), 1 block(s), and 8728 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:28Z USER 796 (nc00/sg02) [ModuleForkPass]: Running lower_klir_kernel
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=2143 blocks=1 instructions=8728 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:28Z USER 796 (nc00/sg02) [ModuleForkPass]: lower_klir_kernel finished after 0.100 seconds
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:28Z USER 796 (nc01/sg02) [ModuleForkPass]: address_rotation_sb finished after 0.535 seconds
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 290mb, ru_maxrss: 292mb (delta=0mb)
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1760 memory location(s), 1 block(s), and 8019 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:28Z USER 796 (nc01/sg02) [ModuleForkPass]: Running dma_optimization_sb
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to dma_optimization_sb: modules=1 functions=1 allocs=1760 blocks=1 instructions=8019 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: DMA optimization In bytes loaded or saved 132450770, 87.2726% input load, 0% output write, 12.7274% spill/reload [sg0002]
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 290mb, ru_maxrss: 292mb (delta=0mb)
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2143 memory location(s), 1 block(s), and 8728 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:28Z USER 796 (nc00/sg02) [ModuleForkPass]: Running lower_nki_kernel
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=2143 blocks=1 instructions=8728 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs
|
|
2025-11-09T20:57:28Z USER 796 (nc00/sg02) [ModuleForkPass]: lower_nki_kernel finished after 0.103 seconds
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 291mb, ru_maxrss: 292mb (delta=0mb)
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2143 memory location(s), 1 block(s), and 8728 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:28Z USER 796 (nc00/sg02) [ModuleForkPass]: Running coloring_allocator_psum
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to coloring_allocator_psum: modules=1 functions=1 allocs=2143 blocks=1 instructions=8728 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:28Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: removed 0 identical load
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: adjusted 0 DMACopy remat
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: sub-graph will get execute 1 times
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [Load Merging]: removed 0 remat/cloned instructions
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [Load shrink]: shrinked 0 GCA remat/cloned instructions
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [Load Merging + Load shrink] reduced input/const loading DMA traffic 4198400, 3.16978% out of total dma traffic(1.15593e+08)
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [Re-allocation Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [remove extra save] removed 0 memlocs and 0 instructions
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:28Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: DMA SpillSave Coalescing Round 0 combined 0 SpillSaves and Reloads
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: average loaded DMA size 3677 bytes
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: average saved DMA size 3848 bytes
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes loaded 119786642
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: INFO: Post DMA coalescing average loaded DMA size 3677 bytes
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes saved 8465728
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: INFO: Post DMA coalescing average saved DMA size 3848 bytes
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [Experiment partial DMA access] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: [DMA optimization] reduced DMA traffic 4198400, 3.16978% out of total dma traffic
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: DMA optimization Out bytes loaded or saved 128252370, 86.856% input load, 0% output write, 13.144% spill/reload [sg0002]
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes loaded 119786642
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization average loaded DMA size 3677 bytes
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes saved 8465728
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization average saved DMA size 3848 bytes
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes DMAcopyed 4100
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization average DMAcopyed DMA size 241 bytes
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization average DMA size 3686 bytes
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: INFO: Finished set_spill_canreadUninit(module);
|
|
2025-11-09T20:57:29Z INFO 796 (nc00/sg02) [PSUM_Allocator]: allocating PSUM
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: DMA optimization re-enable optimization
|
|
2025-11-09T20:57:29Z USER 796 (nc01/sg02) [ModuleForkPass]: dma_optimization_sb finished after 0.702 seconds
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 291mb, ru_maxrss: 292mb (delta=0mb)
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8009 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:29Z USER 796 (nc01/sg02) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=1749 blocks=1 instructions=8009 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 7 Sb address
|
|
2025-11-09T20:57:29Z INFO 796 (nc00/sg02) [PSUM_Allocator]: main loop
|
|
2025-11-09T20:57:29Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 134 Sb address
|
|
2025-11-09T20:57:29Z INFO 796 (nc00/sg02) [PSUM_Allocator]: renumber locations
|
|
2025-11-09T20:57:29Z INFO 796 (nc00/sg02) [PSUM_Allocator]: size = 749
|
|
2025-11-09T20:57:29Z INFO 796 (nc00/sg02) [PSUM_Allocator]: build_no_bitmap start
|
|
2025-11-09T20:57:29Z INFO 796 (nc00/sg02) [PSUM_Allocator]: 100% PSUM demand before spilling
|
|
2025-11-09T20:57:29Z INFO 796 (nc00/sg02) [PSUM_Allocator]: PSUM high-water mark = 8 tensors
|
|
2025-11-09T20:57:29Z INFO 796 (nc00/sg02) [PSUM_Allocator]: found 900 edges
|
|
2025-11-09T20:57:29Z INFO 796 (nc00/sg02) [PSUM_Allocator]: mean: 2.4032
|
|
2025-11-09T20:57:29Z INFO 796 (nc00/sg02) [PSUM_Allocator]: median: 1.51685
|
|
2025-11-09T20:57:29Z INFO 796 (nc00/sg02) [PSUM_Allocator]: adjacency vectors require 7200 bytes
|
|
2025-11-09T20:57:29Z INFO 796 (nc00/sg02) [PSUM_Allocator]: build_no_bitmap done
|
|
2025-11-09T20:57:29Z INFO 796 (nc00/sg02) [PSUM_Allocator]: find costs
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: best-of-n loop, heuristic = 0, allow_psum_spill_within_accum_group = false
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: lo = 712
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: hi = 37
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: inf = 0
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: total = 749
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: simplify
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: select ranges
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: no more spills
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: PSUM score = 0 (lower is better)
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: spilling from PSUM cost about 0 cycles
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [PSUM_Allocator]: 100% PSUM utilization after allocation
|
|
2025-11-09T20:57:30Z USER 796 (nc00/sg02) [ModuleForkPass]: coloring_allocator_psum finished after 1.613 seconds
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 293mb, ru_maxrss: 292mb (delta=0mb)
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2143 memory location(s), 1 block(s), and 8728 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:30Z USER 796 (nc00/sg02) [ModuleForkPass]: Running dma_optimization_psum
|
|
2025-11-09T20:57:30Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to dma_optimization_psum: modules=1 functions=1 allocs=2143 blocks=1 instructions=8728 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 35 Sb address
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 1 Sb address
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 39 Sb address
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:30Z USER 796 (nc01/sg02) [ModuleForkPass]: address_rotation_sb finished after 1.689 seconds
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 292mb, ru_maxrss: 292mb (delta=0mb)
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8009 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:30Z USER 796 (nc01/sg02) [ModuleForkPass]: Running coloring_allocator_dram
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to coloring_allocator_dram: modules=1 functions=1 allocs=1749 blocks=1 instructions=8009 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Local
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [DRAM_Allocator]: reserved space = 32768 bytes
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [DRAM_Allocator]: spill space = 0 bytes
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [DRAM_Allocator]: aligned spill space = 0 bytes
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [DRAM_Allocator]: renumber locations
|
|
2025-11-09T20:57:30Z INFO 796 (nc01/sg02) [DRAM_Allocator]: size = 0
|
|
2025-11-09T20:57:30Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:30Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: Num intervals 0 Num locations 0
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: lo = 0
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: hi = 0
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: total = 0
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: simplify
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: select ranges
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: CC buffer size limit 524288000
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: allreduce_dram_hwm 0
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: Real CC buffer size 0
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: DRAM hwm after allocation: 0
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DRAM_Allocator]: DRAM allocation successful
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: coloring_allocator_dram finished after 0.192 seconds
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 294mb, ru_maxrss: 293mb (delta=1mb)
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8009 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: Running address_rotation_dram
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to address_rotation_dram: modules=1 functions=1 allocs=1749 blocks=1 instructions=8009 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: Runtime page size at 512MB
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: DRAM hwm before rotation 0
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: allreduce buffer size 524288000
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: allreduce hwm 8388608
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: Real CC buffer size 8388608
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: DRAM hwm after rotation 0
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: DRAM Rotation rotated 0 Dram address
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: address_rotation_dram finished after 0.099 seconds
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 292mb, ru_maxrss: 293mb (delta=0mb)
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8009 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: Running tensorcopy_accel
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to tensorcopy_accel: modules=1 functions=1 allocs=1749 blocks=1 instructions=8009 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [TensorCopyAccel::Impl]: Running peephole optimization pass
|
|
2025-11-09T20:57:31Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:31Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:31Z USER 796 (nc00/sg02) [ModuleForkPass]: dma_optimization_psum finished after 0.986 seconds
|
|
2025-11-09T20:57:31Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 293mb, ru_maxrss: 293mb (delta=1mb)
|
|
2025-11-09T20:57:31Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2143 memory location(s), 1 block(s), and 8728 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc00/sg02) [ModuleForkPass]: Running address_rotation_psum
|
|
2025-11-09T20:57:31Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to address_rotation_psum: modules=1 functions=1 allocs=2143 blocks=1 instructions=8728 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [TensorCopyAccel::Impl]: Accelerated 313 out of 713 tensorcopy in Function: sg0002 average acceleration factor: 1
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: tensorcopy_accel finished after 0.116 seconds
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 293mb, ru_maxrss: 293mb (delta=0mb)
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8009 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: Running peephole_opts
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to peephole_opts: modules=1 functions=1 allocs=1749 blocks=1 instructions=8009 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [PeepholeOpts]: PeepholeOpts enabled? Recip: true Tsp: true Tc: false SplitSelect: true SimplifyMemset true
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: peephole_opts finished after 0.013 seconds
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 293mb, ru_maxrss: 293mb (delta=0mb)
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8013 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: Running lower_kernel
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to lower_kernel: modules=1 functions=1 allocs=1749 blocks=1 instructions=8013 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [LowerKernel]: Started running LowerKernel
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [LowerKernel]: BIR SB coloring allocator is disabled
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [LowerKernel]: Start of kernel lowering pass, number of insts: 8013, number of allocs: 1749
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [LowerKernel]: Scan BKs time (s): 0.000301
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [LowerKernel]: Lower BKs time (s): 1e-06
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: lower_kernel finished after 0.000 seconds
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 293mb, ru_maxrss: 293mb (delta=0mb)
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8013 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: Running lower_klir_kernel
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=1749 blocks=1 instructions=8013 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: lower_klir_kernel finished after 0.065 seconds
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 293mb, ru_maxrss: 293mb (delta=0mb)
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8013 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: Running lower_nki_kernel
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=1749 blocks=1 instructions=8013 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: lower_nki_kernel finished after 0.001 seconds
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 293mb, ru_maxrss: 293mb (delta=0mb)
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8013 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: Running non_ssa_legalization
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=1749 blocks=1 instructions=8013 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [NonSSALeg]: remove_redundant_loads
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [NonSSALeg]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [NonSSALeg]: [Non-SSA legalization]created 0 memorylocations
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: non_ssa_legalization finished after 0.024 seconds
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 293mb, ru_maxrss: 293mb (delta=0mb)
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8013 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: Running dynamic_dma_cleanup
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to dynamic_dma_cleanup: modules=1 functions=1 allocs=1749 blocks=1 instructions=8013 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: dynamic_dma_cleanup finished after 0.005 seconds
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 293mb, ru_maxrss: 293mb (delta=0mb)
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8013 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=1749 blocks=1 instructions=8013 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z WARNING 796 [birverifier::InstVisitor]: (nc01/sg02) Non - output memory location with no reader: {divide.1_1259_i1}@SB<32,16384>(1x1024)#Internal DebugInfo: <divide.1_1259||UNDEF||[1, 256, 1]>
|
|
2025-11-09T20:57:31Z WARNING 796 [birverifier::InstVisitor]: (nc01/sg02) Non - output memory location with no reader: {select.5_1264_i1}@SB<96,17536>(1x1024)#Internal DebugInfo: <select.5_1264||UNDEF||[1, 256, 1]>
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: birverifier finished after 0.300 seconds
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 293mb, ru_maxrss: 293mb (delta=0mb)
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8013 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: Running dynamic_dma_scan
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to dynamic_dma_scan: modules=1 functions=1 allocs=1749 blocks=1 instructions=8013 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: dynamic_dma_scan finished after 0.015 seconds
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 293mb, ru_maxrss: 293mb (delta=0mb)
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8013 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z USER 796 (nc01/sg02) [ModuleForkPass]: Running build_fdeps
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to build_fdeps: modules=1 functions=1 allocs=1749 blocks=1 instructions=8013 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [build_flow_deps]: Start build fdeps. Invocation: 11Sun Nov 9 20:57:31 2025
|
|
2025-11-09T20:57:31Z INFO 796 (nc01/sg02) [build_flow_deps]: Allocs: 1749 instructions: 8013
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: PSUM Rotation rotated 62 PSUM Banks
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: PSUM Rotation rotated 19 PSUM Banks
|
|
2025-11-09T20:57:32Z INFO 796 (nc01/sg02) [build_flow_deps]: Build fdeps inserted 20941 edges
|
|
2025-11-09T20:57:32Z INFO 796 (nc01/sg02) [build_flow_deps]: Done build fdeps 20941 Sun Nov 9 20:57:32 2025
|
|
2025-11-09T20:57:32Z USER 796 (nc01/sg02) [ModuleForkPass]: build_fdeps finished after 0.910 seconds
|
|
2025-11-09T20:57:32Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 295mb, ru_maxrss: 294mb (delta=1mb)
|
|
2025-11-09T20:57:32Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8013 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:32Z USER 796 (nc01/sg02) [ModuleForkPass]: Running remove_redundancies
|
|
2025-11-09T20:57:32Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to remove_redundancies: modules=1 functions=1 allocs=1749 blocks=1 instructions=8013 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:32Z INFO 796 (nc01/sg02) [RemoveRedundancies]: remove_clobbered_writes
|
|
2025-11-09T20:57:32Z INFO 796 (nc01/sg02) [RemoveRedundancies]: remove_clobbered_writes: 0
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: PSUM Rotation rotated 5 PSUM Banks
|
|
2025-11-09T20:57:32Z USER 796 (nc00/sg02) [ModuleForkPass]: address_rotation_psum finished after 1.524 seconds
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 295mb, ru_maxrss: 294mb (delta=1mb)
|
|
2025-11-09T20:57:32Z INFO 796 (nc01/sg02) [RemoveRedundancies]: remove_useless_insts
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2143 memory location(s), 1 block(s), and 8728 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:32Z USER 796 (nc00/sg02) [ModuleForkPass]: Running coloring_allocator_sb
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to coloring_allocator_sb: modules=1 functions=1 allocs=2143 blocks=1 instructions=8728 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes loaded 124322718
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: INFO: Pre GCA average loaded DMA size 3623 bytes
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes saved 8483147
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: INFO: Pre GCA average saved DMA size 3267 bytes
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 6148
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 11 bytes
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:32Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:33Z INFO 796 (nc01/sg02) [RemoveRedundancies]: remove Useless Instructions: 0
|
|
2025-11-09T20:57:33Z USER 796 (nc01/sg02) [ModuleForkPass]: remove_redundancies finished after 0.200 seconds
|
|
2025-11-09T20:57:33Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 294mb, ru_maxrss: 294mb (delta=0mb)
|
|
2025-11-09T20:57:33Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8013 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:33Z USER 796 (nc01/sg02) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:33Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1749 blocks=1 instructions=8013 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:33Z INFO 796 (nc01/sg02) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB}
|
|
2025-11-09T20:57:33Z INFO 796 (nc01/sg02) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:33Z INFO 796 (nc00/sg02) [SB_Allocator]: allocating SB
|
|
2025-11-09T20:57:33Z INFO 796 (nc00/sg02) [SB_Allocator]: main loop
|
|
2025-11-09T20:57:33Z INFO 796 (nc00/sg02) [SB_Allocator]: renumber locations
|
|
2025-11-09T20:57:33Z INFO 796 (nc00/sg02) [SB_Allocator]: size = 1348
|
|
2025-11-09T20:57:33Z INFO 796 (nc00/sg02) [SB_Allocator]: find partners
|
|
2025-11-09T20:57:33Z INFO 796 (nc00/sg02) [SB_Allocator]: found 742 accumulation groups
|
|
2025-11-09T20:57:33Z INFO 796 (nc00/sg02) [SB_Allocator]: largest = custom-call.348.1611_i1
|
|
2025-11-09T20:57:33Z INFO 796 (nc00/sg02) [SB_Allocator]: tensors = 17
|
|
2025-11-09T20:57:33Z INFO 796 (nc00/sg02) [SB_Allocator]: requires 33280 bytes/partition
|
|
2025-11-09T20:57:33Z INFO 796 (nc00/sg02) [SB_Allocator]: expanding partners
|
|
2025-11-09T20:57:33Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:33Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:34Z USER 796 (nc01/sg02) [ModuleForkPass]: anti_dependency_analyzer finished after 1.135 seconds
|
|
2025-11-09T20:57:34Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 307mb, ru_maxrss: 306mb (delta=12mb)
|
|
2025-11-09T20:57:34Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8013 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:34Z USER 796 (nc01/sg02) [ModuleForkPass]: Running tensor_copy_elim
|
|
2025-11-09T20:57:34Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=1749 blocks=1 instructions=8013 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: find loads
|
|
2025-11-09T20:57:34Z INFO 796 (nc01/sg02) [TensorCopyElim]: Tensor CP elimination: 0
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: 2 pin count
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: 285 remat count
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: 2 pinned tensors will require about 16392 bytes/partition
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: build interference graph
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: pass 1 int-tree
|
|
2025-11-09T20:57:34Z INFO 796 (nc01/sg02) [TensorCopyElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:34Z USER 796 (nc01/sg02) [ModuleForkPass]: tensor_copy_elim finished after 0.313 seconds
|
|
2025-11-09T20:57:34Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 303mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:34Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8013 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:34Z USER 796 (nc01/sg02) [ModuleForkPass]: Running dead_code_elim_o0
|
|
2025-11-09T20:57:34Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=1749 blocks=1 instructions=8013 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Num intervals 1348 Num locations 1348
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: info.neighbors partners Done
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: edge: 16356
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: mean: 24.2671
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: median: 19.1176
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: find costs
|
|
2025-11-09T20:57:34Z USER 796 (nc01/sg02) [ModuleForkPass]: dead_code_elim_o0 finished after 0.207 seconds
|
|
2025-11-09T20:57:34Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 303mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:34Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1749 memory location(s), 1 block(s), and 8013 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: best-of-n loop, heuristic = 0
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: initialize safe & unsafe
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: safe = 1247
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: unsafe = 89
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: inf = 10
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: total = 1346
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: simplify
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: simplify_step3_sorted2 #Unsafe 0 #Pinned 0 #Safe 0 minCost 1.79769e+308 maxCost 2.22507e-308 locations 1348
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: select ranges
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Total: 1346
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Spilled: 0.000 (0)
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Allocated: 1.000 (1346)
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Rover zone: 0.897 (1207)
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Pre-rover zone: 0.047 (63)
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Post-rover zone: 0.053 (72)
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Slice zone: 0.003 (4)
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Blocks nothing: 0.087 (117)
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Blocks medium: 0.009 (12)
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Visited until medium blocking (mean): 0.574
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Visited until medium blocking (median): 0.544
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Visited until medium blocking (p95): 0.839
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Blocks tall: 0.904 (1217)
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Visited until tall blocking (mean): 0.715
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Visited until tall blocking (median): 0.956
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Visited until tall blocking (p95): 1.000
|
|
2025-11-09T20:57:34Z INFO 796 (nc00/sg02) [SB_Allocator]: Success
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [SB_Allocator]: SB spills = 0 tensors
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [SB_Allocator]: size = 0 bytes/partition
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [SB_Allocator]: remats = 0 tensors
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [SB_Allocator]: unpinned = 0 tensors
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [SB_Allocator]: size = 0 bytes/partition
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [SB_Allocator]: SB score = 0
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [SB_Allocator]: spilling from SB cost about 0 cycles
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [SB_Allocator]: 16392 bytes/partition (100%) successfully pinned
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [SB_Allocator]: pinning saved approximately 8300 cycles
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [SB_Allocator]: 0% SB utilization after allocation
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes loaded 124322718
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: INFO: Post GCA average loaded DMA size 3623 bytes
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes saved 8483147
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: INFO: Post GCA average saved DMA size 3267 bytes
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 6148
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 11 bytes
|
|
2025-11-09T20:57:35Z USER 796 (nc00/sg02) [ModuleForkPass]: coloring_allocator_sb finished after 2.517 seconds
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 303mb, ru_maxrss: 306mb (delta=12mb)
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2143 memory location(s), 1 block(s), and 8728 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:35Z USER 796 (nc00/sg02) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=2143 blocks=1 instructions=8728 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:35Z USER 796 (nc00/sg02) [ModuleForkPass]: address_rotation_sb finished after 0.278 seconds
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 299mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2143 memory location(s), 1 block(s), and 8728 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:35Z USER 796 (nc00/sg02) [ModuleForkPass]: Running dma_optimization_sb
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to dma_optimization_sb: modules=1 functions=1 allocs=2143 blocks=1 instructions=8728 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: DMA optimization In bytes loaded or saved 132805865, 87.166% input load, 3.01192e-06% output write, 12.834% spill/reload [sg0002]
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: removed 0 identical load
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: adjusted 0 DMACopy remat
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: sub-graph will get execute 1 times
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [Load Merging]: removed 0 remat/cloned instructions
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [Load shrink]: shrinked 0 GCA remat/cloned instructions
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [Load Merging + Load shrink] reduced input/const loading DMA traffic 4194304, 3.15822% out of total dma traffic(1.15762e+08)
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [spill optimization round 0]: removed 2 spill/reload instructions
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [spill optimization round 0]: removed 2 spill/reload memory locations
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [spill optimization round 1]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [spill optimization round 1]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:35Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 8, 4.69365e-05% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [Re-allocation Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [remove extra save] removed 0 memlocs and 0 instructions
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload instructions
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload memory locations
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: DMA SpillSave Coalescing Round 0 combined 0 SpillSaves and Reloads
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: average loaded DMA size 3622 bytes
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: average saved DMA size 3269 bytes
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes loaded 120128410
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: INFO: Post DMA coalescing average loaded DMA size 3622 bytes
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes saved 8483143
|
|
2025-11-09T20:57:36Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: INFO: Post DMA coalescing average saved DMA size 3269 bytes
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [Experiment partial DMA access] reduced DMA traffic 0, 0% out of total spill/reload dma traffic
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: [DMA optimization] reduced DMA traffic 4194312, 3.15823% out of total dma traffic
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: DMA optimization Out bytes loaded or saved 128611553, 86.7475% input load, 3.11014e-06% output write, 13.2525% spill/reload [sg0002]
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes loaded 120128410
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization average loaded DMA size 3622 bytes
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes saved 8483143
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization average saved DMA size 3269 bytes
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes DMAcopyed 6148
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization average DMAcopyed DMA size 11 bytes
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: INFO: Post DMA optimization average DMA size 3541 bytes
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: INFO: Finished set_spill_canreadUninit(module);
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: DMA optimization re-enable optimization
|
|
2025-11-09T20:57:37Z USER 796 (nc00/sg02) [ModuleForkPass]: dma_optimization_sb finished after 1.305 seconds
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 300mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8717 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:37Z USER 796 (nc00/sg02) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=2131 blocks=1 instructions=8717 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 9 Sb address
|
|
2025-11-09T20:57:37Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 148 Sb address
|
|
2025-11-09T20:57:38Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 54 Sb address
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 2 Sb address
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 140 Sb address
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: address_rotation_sb finished after 2.281 seconds
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 301mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8717 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: Running coloring_allocator_dram
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to coloring_allocator_dram: modules=1 functions=1 allocs=2131 blocks=1 instructions=8717 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Local
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: reserved space = 36872 bytes
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: spill space = 5120 bytes
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: aligned spill space = 20480 bytes
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: renumber locations
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: size = 5
|
|
2025-11-09T20:57:39Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:39Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: Num intervals 5 Num locations 5
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: lo = 5
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: hi = 0
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: total = 5
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: simplify
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: select ranges
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: CC buffer size limit 524288000
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: allreduce_dram_hwm 0
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: Real CC buffer size 0
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: DRAM hwm after allocation: 4096
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DRAM_Allocator]: DRAM allocation successful
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: coloring_allocator_dram finished after 0.203 seconds
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 302mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8717 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: Running address_rotation_dram
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to address_rotation_dram: modules=1 functions=1 allocs=2131 blocks=1 instructions=8717 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: Runtime page size at 512MB
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: DRAM hwm before rotation 1024
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: allreduce buffer size 524288000
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: allreduce hwm 8388608
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: Real CC buffer size 8388608
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: DRAM hwm after rotation 1024
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: DRAM Rotation rotated 0 Dram address
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: address_rotation_dram finished after 0.014 seconds
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 301mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8717 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: Running tensorcopy_accel
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to tensorcopy_accel: modules=1 functions=1 allocs=2131 blocks=1 instructions=8717 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [TensorCopyAccel::Impl]: Running peephole optimization pass
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [TensorCopyAccel::Impl]: Accelerated 313 out of 852 tensorcopy in Function: sg0002 average acceleration factor: 1
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: tensorcopy_accel finished after 0.107 seconds
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 301mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8717 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: Running peephole_opts
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to peephole_opts: modules=1 functions=1 allocs=2131 blocks=1 instructions=8717 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [PeepholeOpts]: PeepholeOpts enabled? Recip: true Tsp: true Tc: false SplitSelect: true SimplifyMemset true
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: peephole_opts finished after 0.085 seconds
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 300mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8721 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: Running lower_kernel
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to lower_kernel: modules=1 functions=1 allocs=2131 blocks=1 instructions=8721 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [LowerKernel]: Started running LowerKernel
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [LowerKernel]: BIR SB coloring allocator is disabled
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [LowerKernel]: Start of kernel lowering pass, number of insts: 8721, number of allocs: 2131
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [LowerKernel]: Scan BKs time (s): 0.000494
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [LowerKernel]: Lower BKs time (s): 0
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: lower_kernel finished after 0.001 seconds
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 300mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8721 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: Running lower_klir_kernel
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=2131 blocks=1 instructions=8721 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: lower_klir_kernel finished after 0.001 seconds
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 300mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8721 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: Running lower_nki_kernel
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=2131 blocks=1 instructions=8721 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: lower_nki_kernel finished after 0.001 seconds
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 300mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8721 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: Running non_ssa_legalization
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=2131 blocks=1 instructions=8721 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [NonSSALeg]: remove_redundant_loads
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [NonSSALeg]: remove_redundant_loads: 0
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [NonSSALeg]: [Non-SSA legalization]created 0 memorylocations
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: non_ssa_legalization finished after 0.089 seconds
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 300mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8721 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: Running dynamic_dma_cleanup
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to dynamic_dma_cleanup: modules=1 functions=1 allocs=2131 blocks=1 instructions=8721 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: dynamic_dma_cleanup finished after 0.008 seconds
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 300mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8721 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:39Z USER 796 (nc00/sg02) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:57:39Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=2131 blocks=1 instructions=8721 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:40Z USER 796 (nc00/sg02) [ModuleForkPass]: birverifier finished after 0.291 seconds
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 300mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8721 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:40Z USER 796 (nc00/sg02) [ModuleForkPass]: Running dynamic_dma_scan
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to dynamic_dma_scan: modules=1 functions=1 allocs=2131 blocks=1 instructions=8721 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:40Z USER 796 (nc00/sg02) [ModuleForkPass]: dynamic_dma_scan finished after 0.008 seconds
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 300mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8721 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:40Z USER 796 (nc00/sg02) [ModuleForkPass]: Running build_fdeps
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to build_fdeps: modules=1 functions=1 allocs=2131 blocks=1 instructions=8721 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [build_flow_deps]: Start build fdeps. Invocation: 12Sun Nov 9 20:57:40 2025
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [build_flow_deps]: Allocs: 2131 instructions: 8721
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [build_flow_deps]: Build fdeps inserted 32634 edges
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [build_flow_deps]: Done build fdeps 32634 Sun Nov 9 20:57:40 2025
|
|
2025-11-09T20:57:40Z USER 796 (nc00/sg02) [ModuleForkPass]: build_fdeps finished after 0.389 seconds
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 303mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8721 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:40Z USER 796 (nc00/sg02) [ModuleForkPass]: Running remove_redundancies
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to remove_redundancies: modules=1 functions=1 allocs=2131 blocks=1 instructions=8721 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [RemoveRedundancies]: remove_clobbered_writes
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [RemoveRedundancies]: remove_clobbered_writes: 0
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [RemoveRedundancies]: remove_useless_insts
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [RemoveRedundancies]: remove Useless Instructions: 0
|
|
2025-11-09T20:57:40Z USER 796 (nc00/sg02) [ModuleForkPass]: remove_redundancies finished after 0.030 seconds
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 303mb, ru_maxrss: 306mb (delta=0mb)
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8721 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:40Z USER 796 (nc00/sg02) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=2131 blocks=1 instructions=8721 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB}
|
|
2025-11-09T20:57:40Z INFO 796 (nc00/sg02) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:41Z USER 796 (nc00/sg02) [ModuleForkPass]: anti_dependency_analyzer finished after 0.734 seconds
|
|
2025-11-09T20:57:41Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 315mb, ru_maxrss: 313mb (delta=7mb)
|
|
2025-11-09T20:57:41Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8721 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:41Z USER 796 (nc00/sg02) [ModuleForkPass]: Running tensor_copy_elim
|
|
2025-11-09T20:57:41Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=2131 blocks=1 instructions=8721 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:41Z INFO 796 (nc00/sg02) [TensorCopyElim]: Tensor CP elimination: 0
|
|
2025-11-09T20:57:41Z INFO 796 (nc00/sg02) [TensorCopyElim]: eliminateDeadStore removed 0 instructions
|
|
2025-11-09T20:57:41Z USER 796 (nc00/sg02) [ModuleForkPass]: tensor_copy_elim finished after 0.405 seconds
|
|
2025-11-09T20:57:41Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 311mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:41Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8721 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:41Z USER 796 (nc00/sg02) [ModuleForkPass]: Running dead_code_elim_o0
|
|
2025-11-09T20:57:41Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=2131 blocks=1 instructions=8721 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:41Z USER 796 (nc00/sg02) [ModuleForkPass]: dead_code_elim_o0 finished after 0.091 seconds
|
|
2025-11-09T20:57:41Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 311mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:41Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2131 memory location(s), 1 block(s), and 8721 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:42Z USER 796 [ModuleForkPass]: Compilation status: Total modules: 6, Passed: 6, Failed: 0
|
|
2025-11-09T20:57:42Z USER 796 [BackendPassManager]: mod_parallel_pass finished after 26.036 seconds
|
|
2025-11-09T20:57:42Z INFO 796 [BackendPassManager]: curr_vmrss: 311mb, ru_maxrss: 313mb (delta=25mb)
|
|
2025-11-09T20:57:42Z USER 796 [BackendPassManager]: Running subgraph_parallel_pass
|
|
2025-11-09T20:57:42Z INFO 796 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=6 functions=6 allocs=9698 blocks=6 instructions=29644 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:42Z USER 796 (sg00) [SubgraphForkPass]: Running localize_shared_memory
|
|
2025-11-09T20:57:42Z USER 796 (sg01) [SubgraphForkPass]: Running localize_shared_memory
|
|
2025-11-09T20:57:42Z USER 796 (sg02) [SubgraphForkPass]: Running localize_shared_memory
|
|
2025-11-09T20:57:42Z INFO 796 (sg02) [SubgraphForkPass]: Inputs to localize_shared_memory: modules=2 functions=2 allocs=3880 blocks=2 instructions=16734 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:42Z INFO 796 (sg01) [SubgraphForkPass]: Inputs to localize_shared_memory: modules=2 functions=2 allocs=2907 blocks=2 instructions=7745 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:42Z INFO 796 (sg00) [SubgraphForkPass]: Inputs to localize_shared_memory: modules=2 functions=2 allocs=2911 blocks=2 instructions=5165 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:42Z USER 796 (sg02) [SubgraphForkPass]: localize_shared_memory finished after 0.010 seconds
|
|
2025-11-09T20:57:42Z INFO 796 (sg02) [SubgraphForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:42Z INFO 796 (sg02) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 3880 memory location(s), 2 block(s), and 16734 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:42Z USER 796 (sg02) [SubgraphForkPass]: Running lower_local_collectives
|
|
2025-11-09T20:57:42Z USER 796 (sg00) [SubgraphForkPass]: localize_shared_memory finished after 0.012 seconds
|
|
2025-11-09T20:57:42Z INFO 796 (sg00) [SubgraphForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:42Z INFO 796 (sg02) [SubgraphForkPass]: Inputs to lower_local_collectives: modules=2 functions=2 allocs=3880 blocks=2 instructions=16734 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:42Z USER 796 (sg01) [SubgraphForkPass]: localize_shared_memory finished after 0.012 seconds
|
|
2025-11-09T20:57:42Z INFO 796 (sg01) [SubgraphForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:42Z INFO 796 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 2911 memory location(s), 2 block(s), and 5165 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:42Z USER 796 (sg00) [SubgraphForkPass]: Running lower_local_collectives
|
|
2025-11-09T20:57:42Z INFO 796 (sg00) [SubgraphForkPass]: Inputs to lower_local_collectives: modules=2 functions=2 allocs=2911 blocks=2 instructions=5165 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:42Z INFO 796 (sg01) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 2907 memory location(s), 2 block(s), and 7745 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:42Z USER 796 (sg01) [SubgraphForkPass]: Running lower_local_collectives
|
|
2025-11-09T20:57:42Z INFO 796 (sg01) [SubgraphForkPass]: Inputs to lower_local_collectives: modules=2 functions=2 allocs=2907 blocks=2 instructions=7745 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:42Z USER 796 (sg00) [SubgraphForkPass]: lower_local_collectives finished after 0.014 seconds
|
|
2025-11-09T20:57:42Z INFO 796 (sg00) [SubgraphForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:42Z INFO 796 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 2911 memory location(s), 2 block(s), and 5171 instruction(s). Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:42Z USER 796 (sg00) [SubgraphForkPass]: Running extend_shared_lifetimes
|
|
2025-11-09T20:57:42Z INFO 796 (sg00) [SubgraphForkPass]: Inputs to extend_shared_lifetimes: modules=2 functions=2 allocs=2911 blocks=2 instructions=5171 Max writers: 33 Max Readers: 288
|
|
2025-11-09T20:57:42Z USER 796 (sg02) [SubgraphForkPass]: lower_local_collectives finished after 0.099 seconds
|
|
2025-11-09T20:57:42Z INFO 796 (sg02) [SubgraphForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:42Z INFO 796 (sg02) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 3886 memory location(s), 2 block(s), and 16752 instruction(s). Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:42Z USER 796 (sg02) [SubgraphForkPass]: Running extend_shared_lifetimes
|
|
2025-11-09T20:57:42Z INFO 796 (sg02) [SubgraphForkPass]: Inputs to extend_shared_lifetimes: modules=2 functions=2 allocs=3886 blocks=2 instructions=16752 Max writers: 150 Max Readers: 2918
|
|
2025-11-09T20:57:42Z USER 796 (sg01) [SubgraphForkPass]: lower_local_collectives finished after 0.100 seconds
|
|
2025-11-09T20:57:42Z INFO 796 (sg01) [SubgraphForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:42Z INFO 796 (sg01) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 2907 memory location(s), 2 block(s), and 7749 instruction(s). Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:42Z USER 796 (sg01) [SubgraphForkPass]: Running extend_shared_lifetimes
|
|
2025-11-09T20:57:42Z INFO 796 (sg01) [SubgraphForkPass]: Inputs to extend_shared_lifetimes: modules=2 functions=2 allocs=2907 blocks=2 instructions=7749 Max writers: 33 Max Readers: 448
|
|
2025-11-09T20:57:42Z USER 796 (sg00) [SubgraphForkPass]: extend_shared_lifetimes finished after 0.169 seconds
|
|
2025-11-09T20:57:42Z INFO 796 (sg00) [SubgraphForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:42Z INFO 796 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 2911 memory location(s), 2 block(s), and 5175 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:42Z USER 796 (sg01) [SubgraphForkPass]: extend_shared_lifetimes finished after 0.284 seconds
|
|
2025-11-09T20:57:42Z INFO 796 (sg01) [SubgraphForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:42Z INFO 796 (sg01) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 2907 memory location(s), 2 block(s), and 7753 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:42Z USER 796 (sg02) [SubgraphForkPass]: extend_shared_lifetimes finished after 0.782 seconds
|
|
2025-11-09T20:57:42Z INFO 796 (sg02) [SubgraphForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:42Z INFO 796 (sg02) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 3886 memory location(s), 2 block(s), and 16756 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:42Z USER 796 [SubgraphForkPass]: Compilation status: Total subgraphs: 3, Passed: 3, Failed: 0
|
|
2025-11-09T20:57:42Z USER 796 [BackendPassManager]: subgraph_parallel_pass finished after 0.978 seconds
|
|
2025-11-09T20:57:42Z INFO 796 [BackendPassManager]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:42Z USER 796 [BackendPassManager]: Running mod_parallel_pass
|
|
2025-11-09T20:57:43Z INFO 796 [BackendPassManager]: Inputs to mod_parallel_pass: modules=6 functions=6 allocs=9704 blocks=6 instructions=29684 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:43Z USER 796 (nc00/sg00) [ModuleForkPass]: Running coloring_allocator_dram_shared
|
|
2025-11-09T20:57:43Z USER 796 (nc00/sg02) [ModuleForkPass]: Running coloring_allocator_dram_shared
|
|
2025-11-09T20:57:43Z USER 796 (nc01/sg00) [ModuleForkPass]: Running coloring_allocator_dram_shared
|
|
2025-11-09T20:57:43Z USER 796 (nc00/sg01) [ModuleForkPass]: Running coloring_allocator_dram_shared
|
|
2025-11-09T20:57:43Z USER 796 (nc01/sg01) [ModuleForkPass]: Running coloring_allocator_dram_shared
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to coloring_allocator_dram_shared: modules=1 functions=1 allocs=1456 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to coloring_allocator_dram_shared: modules=1 functions=1 allocs=2134 blocks=1 instructions=8732 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg02) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:43Z USER 796 (nc01/sg02) [ModuleForkPass]: Running coloring_allocator_dram_shared
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to coloring_allocator_dram_shared: modules=1 functions=1 allocs=1455 blocks=1 instructions=2586 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg00) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to coloring_allocator_dram_shared: modules=1 functions=1 allocs=1454 blocks=1 instructions=3878 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to coloring_allocator_dram_shared: modules=1 functions=1 allocs=1453 blocks=1 instructions=3875 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg01) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to coloring_allocator_dram_shared: modules=1 functions=1 allocs=1752 blocks=1 instructions=8024 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg02) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Shared
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: reserved space = 131328 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: spill space = 35651584 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: aligned spill space = 35651584 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: renumber locations
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: size = 10
|
|
2025-11-09T20:57:43Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:43Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: Num intervals 10 Num locations 10
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: lo = 10
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: hi = 0
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: total = 10
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: simplify
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: Fall back to default allocation strategy [Core0 Local, Shared]
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: select ranges
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: CC buffer size limit 524288000
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: allreduce_dram_hwm 27262976
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: Real CC buffer size 27262976
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg01) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Shared
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg01) [DRAM_Allocator]: reserved space = 65536 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg01) [DRAM_Allocator]: spill space = 50331648 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg01) [DRAM_Allocator]: aligned spill space = 50331648 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg01) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg01) [DRAM_Allocator]: Skipping shared tensor allocations on core 1, marking as remoteLocalTarget instead
|
|
2025-11-09T20:57:43Z USER 796 (nc01/sg01) [ModuleForkPass]: coloring_allocator_dram_shared finished after 0.202 seconds
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 311mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3875 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: DRAM hwm after allocation: 35651584
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [DRAM_Allocator]: DRAM allocation successful
|
|
2025-11-09T20:57:43Z USER 796 (nc00/sg00) [ModuleForkPass]: coloring_allocator_dram_shared finished after 0.274 seconds
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 310mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg00) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Shared
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Shared
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg00) [DRAM_Allocator]: reserved space = 131328 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg00) [DRAM_Allocator]: spill space = 35651584 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg00) [DRAM_Allocator]: aligned spill space = 35651584 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg00) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: reserved space = 65536 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: spill space = 50331648 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: aligned spill space = 50331648 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: renumber locations
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: size = 9
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg00) [DRAM_Allocator]: Skipping shared tensor allocations on core 1, marking as remoteLocalTarget instead
|
|
2025-11-09T20:57:43Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:43Z USER 796 (nc01/sg00) [ModuleForkPass]: coloring_allocator_dram_shared finished after 0.312 seconds
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 310mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2586 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:43Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg02) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Shared
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg02) [DRAM_Allocator]: reserved space = 32768 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg02) [DRAM_Allocator]: spill space = 33729154 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg02) [DRAM_Allocator]: aligned spill space = 33771520 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg02) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg02) [DRAM_Allocator]: Skipping shared tensor allocations on core 1, marking as remoteLocalTarget instead
|
|
2025-11-09T20:57:43Z USER 796 (nc01/sg02) [ModuleForkPass]: coloring_allocator_dram_shared finished after 0.504 seconds
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 311mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:43Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8024 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: Num intervals 9 Num locations 9
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: lo = 9
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: hi = 0
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: total = 9
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: simplify
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: Fall back to default allocation strategy [Core0 Local, Shared]
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: select ranges
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: CC buffer size limit 524288000
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: allreduce_dram_hwm 33554432
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: Real CC buffer size 33554432
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: DRAM hwm after allocation: 48234496
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [DRAM_Allocator]: DRAM allocation successful
|
|
2025-11-09T20:57:43Z USER 796 (nc00/sg01) [ModuleForkPass]: coloring_allocator_dram_shared finished after 0.542 seconds
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 311mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3878 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg02) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Shared
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg02) [DRAM_Allocator]: reserved space = 41992 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg02) [DRAM_Allocator]: spill space = 33729154 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg02) [DRAM_Allocator]: aligned spill space = 33771520 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg02) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg02) [DRAM_Allocator]: renumber locations
|
|
2025-11-09T20:57:43Z INFO 796 (nc00/sg02) [DRAM_Allocator]: size = 20
|
|
2025-11-09T20:57:43Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:57:43Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: Num intervals 20 Num locations 20
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: simplify interference graph
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: initialize low and high
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: lo = 20
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: hi = 0
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: total = 20
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: simplify
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: new candidates = 0
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: Already used DRAM hwm: 4096
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: Fall back to default allocation strategy [Core0 Local, Shared]
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: Already used DRAM hwm: 4096
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: select ranges
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: CC buffer size limit 524288000
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: allreduce_dram_hwm 16797696
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: Real CC buffer size 16797696
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: DRAM hwm after allocation: 25350144
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [DRAM_Allocator]: DRAM allocation successful
|
|
2025-11-09T20:57:44Z USER 796 (nc00/sg02) [ModuleForkPass]: coloring_allocator_dram_shared finished after 1.228 seconds
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 311mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8732 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:44Z USER 796 [ModuleForkPass]: Compilation status: Total modules: 6, Passed: 6, Failed: 0
|
|
2025-11-09T20:57:44Z USER 796 [BackendPassManager]: mod_parallel_pass finished after 1.384 seconds
|
|
2025-11-09T20:57:44Z INFO 796 [BackendPassManager]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:44Z USER 796 [BackendPassManager]: Running subgraph_parallel_pass
|
|
2025-11-09T20:57:44Z INFO 796 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=6 functions=6 allocs=9704 blocks=6 instructions=29684 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:44Z USER 796 (sg01) [SubgraphForkPass]: Running sync_shared_allocations
|
|
2025-11-09T20:57:44Z USER 796 (sg02) [SubgraphForkPass]: Running sync_shared_allocations
|
|
2025-11-09T20:57:44Z INFO 796 (sg02) [SubgraphForkPass]: Inputs to sync_shared_allocations: modules=2 functions=2 allocs=3886 blocks=2 instructions=16756 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:44Z INFO 796 (sg01) [SubgraphForkPass]: Inputs to sync_shared_allocations: modules=2 functions=2 allocs=2907 blocks=2 instructions=7753 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:44Z USER 796 (sg00) [SubgraphForkPass]: Running sync_shared_allocations
|
|
2025-11-09T20:57:44Z INFO 796 (sg00) [SubgraphForkPass]: Inputs to sync_shared_allocations: modules=2 functions=2 allocs=2911 blocks=2 instructions=5175 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:44Z USER 796 (sg02) [SubgraphForkPass]: sync_shared_allocations finished after 0.010 seconds
|
|
2025-11-09T20:57:44Z INFO 796 (sg02) [SubgraphForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:44Z INFO 796 (sg02) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 3886 memory location(s), 2 block(s), and 16756 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:44Z USER 796 (sg00) [SubgraphForkPass]: sync_shared_allocations finished after 0.017 seconds
|
|
2025-11-09T20:57:44Z INFO 796 (sg00) [SubgraphForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:44Z INFO 796 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 2911 memory location(s), 2 block(s), and 5175 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:44Z USER 796 (sg01) [SubgraphForkPass]: sync_shared_allocations finished after 0.086 seconds
|
|
2025-11-09T20:57:44Z INFO 796 (sg01) [SubgraphForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:44Z INFO 796 (sg01) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 2907 memory location(s), 2 block(s), and 7753 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:44Z USER 796 [SubgraphForkPass]: Compilation status: Total subgraphs: 3, Passed: 3, Failed: 0
|
|
2025-11-09T20:57:44Z USER 796 [BackendPassManager]: subgraph_parallel_pass finished after 0.110 seconds
|
|
2025-11-09T20:57:44Z INFO 796 [BackendPassManager]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:44Z USER 796 [BackendPassManager]: Running mod_parallel_pass
|
|
2025-11-09T20:57:44Z INFO 796 [BackendPassManager]: Inputs to mod_parallel_pass: modules=6 functions=6 allocs=9704 blocks=6 instructions=29684 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:44Z USER 796 (nc00/sg02) [ModuleForkPass]: Running anti_dependency_analyzer_post_shared_dram
|
|
2025-11-09T20:57:44Z USER 796 (nc00/sg01) [ModuleForkPass]: Running anti_dependency_analyzer_post_shared_dram
|
|
2025-11-09T20:57:44Z USER 796 (nc01/sg00) [ModuleForkPass]: Running anti_dependency_analyzer_post_shared_dram
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to anti_dependency_analyzer_post_shared_dram: modules=1 functions=1 allocs=2134 blocks=1 instructions=8732 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [AntiDependencyAnalyzer]: Analysis types: {DRAM}
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer_post_shared_dram: modules=1 functions=1 allocs=1455 blocks=1 instructions=2586 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM}
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to anti_dependency_analyzer_post_shared_dram: modules=1 functions=1 allocs=1454 blocks=1 instructions=3878 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg01) [AntiDependencyAnalyzer]: Analysis types: {DRAM}
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg01) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:44Z USER 796 (nc01/sg01) [ModuleForkPass]: Running anti_dependency_analyzer_post_shared_dram
|
|
2025-11-09T20:57:44Z USER 796 (nc00/sg00) [ModuleForkPass]: Running anti_dependency_analyzer_post_shared_dram
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to anti_dependency_analyzer_post_shared_dram: modules=1 functions=1 allocs=1453 blocks=1 instructions=3875 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg01) [AntiDependencyAnalyzer]: Analysis types: {DRAM}
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg01) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer_post_shared_dram: modules=1 functions=1 allocs=1456 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM}
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:44Z USER 796 (nc01/sg02) [ModuleForkPass]: Running anti_dependency_analyzer_post_shared_dram
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to anti_dependency_analyzer_post_shared_dram: modules=1 functions=1 allocs=1752 blocks=1 instructions=8024 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg02) [AntiDependencyAnalyzer]: Analysis types: {DRAM}
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg02) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:44Z USER 796 (nc00/sg02) [ModuleForkPass]: anti_dependency_analyzer_post_shared_dram finished after 0.196 seconds
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:44Z USER 796 (nc01/sg00) [ModuleForkPass]: anti_dependency_analyzer_post_shared_dram finished after 0.195 seconds
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8732 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2586 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:44Z USER 796 (nc01/sg01) [ModuleForkPass]: anti_dependency_analyzer_post_shared_dram finished after 0.192 seconds
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3875 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:44Z USER 796 (nc00/sg00) [ModuleForkPass]: anti_dependency_analyzer_post_shared_dram finished after 0.290 seconds
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:44Z USER 796 (nc00/sg01) [ModuleForkPass]: anti_dependency_analyzer_post_shared_dram finished after 0.300 seconds
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:44Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3878 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:44Z USER 796 (nc01/sg02) [ModuleForkPass]: anti_dependency_analyzer_post_shared_dram finished after 0.390 seconds
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:44Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8024 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:44Z USER 796 [ModuleForkPass]: Compilation status: Total modules: 6, Passed: 6, Failed: 0
|
|
2025-11-09T20:57:44Z USER 796 [BackendPassManager]: mod_parallel_pass finished after 0.396 seconds
|
|
2025-11-09T20:57:44Z INFO 796 [BackendPassManager]: curr_vmrss: 309mb, ru_maxrss: 313mb (delta=0mb)
|
|
2025-11-09T20:57:44Z USER 796 [BackendPassManager]: Running nc_parallel_pass
|
|
2025-11-09T20:57:44Z INFO 796 [BackendPassManager]: Inputs to nc_parallel_pass: modules=6 functions=6 allocs=9704 blocks=6 instructions=29684 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:44Z USER 796 (nc01) [CoreForkPass]: Running memory_analysis_after_coloring_allocator_dram_shared
|
|
2025-11-09T20:57:44Z USER 796 (nc00) [CoreForkPass]: Running memory_analysis_after_coloring_allocator_dram_shared
|
|
2025-11-09T20:57:44Z INFO 796 (nc00) [CoreForkPass]: Inputs to memory_analysis_after_coloring_allocator_dram_shared: modules=3 functions=3 allocs=5044 blocks=3 instructions=15199 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:44Z INFO 796 (nc01) [CoreForkPass]: Inputs to memory_analysis_after_coloring_allocator_dram_shared: modules=3 functions=3 allocs=4660 blocks=3 instructions=14485 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:45Z USER 796 (nc00) [CoreForkPass]: memory_analysis_after_coloring_allocator_dram_shared finished after 1.109 seconds
|
|
2025-11-09T20:57:45Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 315mb, ru_maxrss: 314mb (delta=1mb)
|
|
2025-11-09T20:57:45Z INFO 796 (nc00) [CoreForkPass]: Output has 3 module(s), 3 function(s), 5044 memory location(s), 3 block(s), and 15199 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:46Z USER 796 (nc01) [CoreForkPass]: memory_analysis_after_coloring_allocator_dram_shared finished after 1.195 seconds
|
|
2025-11-09T20:57:46Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 314mb, ru_maxrss: 314mb (delta=1mb)
|
|
2025-11-09T20:57:46Z INFO 796 (nc01) [CoreForkPass]: Output has 3 module(s), 3 function(s), 4660 memory location(s), 3 block(s), and 14485 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:46Z USER 796 [CoreForkPass]: Compilation status: Total modules: 2, Passed: 6, Failed: 0
|
|
2025-11-09T20:57:46Z USER 796 [BackendPassManager]: nc_parallel_pass finished after 1.210 seconds
|
|
2025-11-09T20:57:46Z INFO 796 [BackendPassManager]: curr_vmrss: 311mb, ru_maxrss: 314mb (delta=1mb)
|
|
2025-11-09T20:57:46Z USER 796 [BackendPassManager]: Running mod_parallel_pass
|
|
2025-11-09T20:57:46Z INFO 796 [BackendPassManager]: Inputs to mod_parallel_pass: modules=6 functions=6 allocs=9704 blocks=6 instructions=29684 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg00) [ModuleForkPass]: Running prefetch_scheduling_before_sched
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg01) [ModuleForkPass]: Running prefetch_scheduling_before_sched
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg02) [ModuleForkPass]: Running prefetch_scheduling_before_sched
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg01) [ModuleForkPass]: Running prefetch_scheduling_before_sched
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg00) [ModuleForkPass]: Running prefetch_scheduling_before_sched
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to prefetch_scheduling_before_sched: modules=1 functions=1 allocs=1456 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg00) [ModuleForkPass]: prefetch_scheduling_before_sched finished after 0.000 seconds
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 309mb, ru_maxrss: 314mb (delta=0mb)
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to prefetch_scheduling_before_sched: modules=1 functions=1 allocs=1455 blocks=1 instructions=2586 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to prefetch_scheduling_before_sched: modules=1 functions=1 allocs=1454 blocks=1 instructions=3878 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to prefetch_scheduling_before_sched: modules=1 functions=1 allocs=2134 blocks=1 instructions=8732 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg00) [ModuleForkPass]: prefetch_scheduling_before_sched finished after 0.000 seconds
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg01) [ModuleForkPass]: prefetch_scheduling_before_sched finished after 0.001 seconds
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg00) [ModuleForkPass]: Running post_sched
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg02) [ModuleForkPass]: prefetch_scheduling_before_sched finished after 0.001 seconds
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 309mb, ru_maxrss: 314mb (delta=0mb)
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to post_sched: modules=1 functions=1 allocs=1456 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z INFO 796 [PostSched]: Detected modules.size() == 1; running LNC=1 post_sched
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 309mb, ru_maxrss: 314mb (delta=0mb)
|
|
2025-11-09T20:57:46Z INFO 796 [PostSched]: Detected --lnc_aware_scheduler=false; running LNC=1 post_sched
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 309mb, ru_maxrss: 314mb (delta=0mb)
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to prefetch_scheduling_before_sched: modules=1 functions=1 allocs=1453 blocks=1 instructions=3875 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg01) [ModuleForkPass]: prefetch_scheduling_before_sched finished after 0.001 seconds
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2586 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg00) [ModuleForkPass]: Running post_sched
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to post_sched: modules=1 functions=1 allocs=1455 blocks=1 instructions=2586 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z INFO 796 [PostSched]: Detected modules.size() == 1; running LNC=1 post_sched
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3878 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:46Z INFO 796 [PostSched]: Detected --lnc_aware_scheduler=false; running LNC=1 post_sched
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8732 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 309mb, ru_maxrss: 314mb (delta=0mb)
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg01) [ModuleForkPass]: Running post_sched
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg02) [ModuleForkPass]: Running post_sched
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to post_sched: modules=1 functions=1 allocs=1454 blocks=1 instructions=3878 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3875 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:46Z INFO 796 [PostSched]: Detected modules.size() == 1; running LNC=1 post_sched
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg01) [ModuleForkPass]: Running post_sched
|
|
2025-11-09T20:57:46Z INFO 796 [PostSched]: Detected --lnc_aware_scheduler=false; running LNC=1 post_sched
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to post_sched: modules=1 functions=1 allocs=2134 blocks=1 instructions=8732 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:46Z INFO 796 [PostSched]: Detected modules.size() == 1; running LNC=1 post_sched
|
|
2025-11-09T20:57:46Z INFO 796 [PostSched]: Detected --lnc_aware_scheduler=false; running LNC=1 post_sched
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to post_sched: modules=1 functions=1 allocs=1453 blocks=1 instructions=3875 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:46Z INFO 796 [PostSched]: Detected modules.size() == 1; running LNC=1 post_sched
|
|
2025-11-09T20:57:46Z INFO 796 [PostSched]: Detected --lnc_aware_scheduler=false; running LNC=1 post_sched
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg02) [ModuleForkPass]: Running prefetch_scheduling_before_sched
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to prefetch_scheduling_before_sched: modules=1 functions=1 allocs=1752 blocks=1 instructions=8024 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg02) [ModuleForkPass]: prefetch_scheduling_before_sched finished after 0.001 seconds
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 309mb, ru_maxrss: 314mb (delta=0mb)
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8024 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg02) [ModuleForkPass]: Running post_sched
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to post_sched: modules=1 functions=1 allocs=1752 blocks=1 instructions=8024 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:46Z INFO 796 [PostSched]: Detected modules.size() == 1; running LNC=1 post_sched
|
|
2025-11-09T20:57:46Z INFO 796 [PostSched]: Detected --lnc_aware_scheduler=false; running LNC=1 post_sched
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Start PosT ScheD 3 gen3 Sun Nov 9 20:57:46 2025
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Start PosT ScheD 3 gen3 Sun Nov 9 20:57:46 2025
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Start PosT ScheD 3 gen3 Sun Nov 9 20:57:46 2025
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Start PosT ScheD 3 gen3 Sun Nov 9 20:57:46 2025
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Start PosT ScheD 3 gen3 Sun Nov 9 20:57:46 2025
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Start PosT ScheD 3 gen3 Sun Nov 9 20:57:46 2025
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Time-aware hwm post-sched
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Time-aware hwm post-sched
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Time-aware hwm post-sched
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Time-aware hwm post-sched
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Time-aware simulation time: 1129354
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Done PosT ScheD Sun Nov 9 20:57:46 2025
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg00) [ModuleForkPass]: post_sched finished after 0.603 seconds
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 322mb, ru_maxrss: 321mb (delta=7mb)
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg00) [ModuleForkPass]: Running expand_scheduling_units
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to expand_scheduling_units: modules=1 functions=1 allocs=1456 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg00) [ModuleForkPass]: expand_scheduling_units finished after 0.000 seconds
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 320mb, ru_maxrss: 321mb (delta=0mb)
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg00) [ModuleForkPass]: Running dead_code_elim_o0
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=1456 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z USER 796 (nc00/sg00) [ModuleForkPass]: dead_code_elim_o0 finished after 0.082 seconds
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 320mb, ru_maxrss: 321mb (delta=0mb)
|
|
2025-11-09T20:57:46Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Time-aware simulation time: 1104382
|
|
2025-11-09T20:57:46Z INFO 796 [post_scheduler]: Done PosT ScheD Sun Nov 9 20:57:46 2025
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg00) [ModuleForkPass]: post_sched finished after 0.716 seconds
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 320mb, ru_maxrss: 321mb (delta=7mb)
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2586 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg00) [ModuleForkPass]: Running expand_scheduling_units
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to expand_scheduling_units: modules=1 functions=1 allocs=1455 blocks=1 instructions=2586 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg00) [ModuleForkPass]: expand_scheduling_units finished after 0.000 seconds
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 319mb, ru_maxrss: 321mb (delta=0mb)
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2586 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg00) [ModuleForkPass]: Running dead_code_elim_o0
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=1455 blocks=1 instructions=2586 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:46Z USER 796 (nc01/sg00) [ModuleForkPass]: dead_code_elim_o0 finished after 0.082 seconds
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 319mb, ru_maxrss: 321mb (delta=0mb)
|
|
2025-11-09T20:57:46Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2586 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:47Z INFO 796 [post_scheduler]: Time-aware simulation time: 43476939
|
|
2025-11-09T20:57:47Z INFO 796 [post_scheduler]: Time-aware hwm post-sched
|
|
2025-11-09T20:57:47Z INFO 796 [post_scheduler]: Time-aware simulation time: 43272441
|
|
2025-11-09T20:57:47Z INFO 796 [post_scheduler]: Done PosT ScheD Sun Nov 9 20:57:47 2025
|
|
2025-11-09T20:57:47Z USER 796 (nc00/sg01) [ModuleForkPass]: post_sched finished after 1.011 seconds
|
|
2025-11-09T20:57:47Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 320mb, ru_maxrss: 321mb (delta=7mb)
|
|
2025-11-09T20:57:47Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3878 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:47Z INFO 796 [post_scheduler]: Done PosT ScheD Sun Nov 9 20:57:47 2025
|
|
2025-11-09T20:57:47Z USER 796 (nc01/sg01) [ModuleForkPass]: post_sched finished after 1.017 seconds
|
|
2025-11-09T20:57:47Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 317mb, ru_maxrss: 321mb (delta=7mb)
|
|
2025-11-09T20:57:47Z USER 796 (nc00/sg01) [ModuleForkPass]: Running expand_scheduling_units
|
|
2025-11-09T20:57:47Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to expand_scheduling_units: modules=1 functions=1 allocs=1454 blocks=1 instructions=3878 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:47Z USER 796 (nc00/sg01) [ModuleForkPass]: expand_scheduling_units finished after 0.003 seconds
|
|
2025-11-09T20:57:47Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 316mb, ru_maxrss: 321mb (delta=0mb)
|
|
2025-11-09T20:57:47Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3878 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:47Z USER 796 (nc00/sg01) [ModuleForkPass]: Running dead_code_elim_o0
|
|
2025-11-09T20:57:47Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=1454 blocks=1 instructions=3878 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:47Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3875 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:47Z USER 796 (nc01/sg01) [ModuleForkPass]: Running expand_scheduling_units
|
|
2025-11-09T20:57:47Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to expand_scheduling_units: modules=1 functions=1 allocs=1453 blocks=1 instructions=3875 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:47Z USER 796 (nc01/sg01) [ModuleForkPass]: expand_scheduling_units finished after 0.003 seconds
|
|
2025-11-09T20:57:47Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 316mb, ru_maxrss: 321mb (delta=0mb)
|
|
2025-11-09T20:57:47Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3875 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:47Z USER 796 (nc01/sg01) [ModuleForkPass]: Running dead_code_elim_o0
|
|
2025-11-09T20:57:47Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=1453 blocks=1 instructions=3875 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:47Z USER 796 (nc00/sg01) [ModuleForkPass]: dead_code_elim_o0 finished after 0.035 seconds
|
|
2025-11-09T20:57:47Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 316mb, ru_maxrss: 321mb (delta=0mb)
|
|
2025-11-09T20:57:47Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3878 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:47Z USER 796 (nc01/sg01) [ModuleForkPass]: dead_code_elim_o0 finished after 0.096 seconds
|
|
2025-11-09T20:57:47Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 317mb, ru_maxrss: 321mb (delta=0mb)
|
|
2025-11-09T20:57:47Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3875 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:47Z INFO 796 [post_scheduler]: Time-aware hwm post-sched
|
|
2025-11-09T20:57:52Z INFO 796 [post_scheduler]: Time-aware simulation time: 1408087
|
|
2025-11-09T20:57:52Z INFO 796 [post_scheduler]: Time-aware simulation time: 1526096
|
|
2025-11-09T20:57:52Z INFO 796 [post_scheduler]: Done PosT ScheD Sun Nov 9 20:57:52 2025
|
|
2025-11-09T20:57:52Z USER 796 (nc01/sg02) [ModuleForkPass]: post_sched finished after 6.392 seconds
|
|
2025-11-09T20:57:52Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 335mb, ru_maxrss: 334mb (delta=20mb)
|
|
2025-11-09T20:57:52Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8024 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:52Z USER 796 (nc01/sg02) [ModuleForkPass]: Running expand_scheduling_units
|
|
2025-11-09T20:57:52Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to expand_scheduling_units: modules=1 functions=1 allocs=1752 blocks=1 instructions=8024 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:52Z INFO 796 [post_scheduler]: Done PosT ScheD Sun Nov 9 20:57:52 2025
|
|
2025-11-09T20:57:52Z USER 796 (nc01/sg02) [ModuleForkPass]: expand_scheduling_units finished after 0.010 seconds
|
|
2025-11-09T20:57:52Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 330mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:52Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8024 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:52Z USER 796 (nc01/sg02) [ModuleForkPass]: Running dead_code_elim_o0
|
|
2025-11-09T20:57:52Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=1752 blocks=1 instructions=8024 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:52Z USER 796 (nc00/sg02) [ModuleForkPass]: post_sched finished after 6.477 seconds
|
|
2025-11-09T20:57:52Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 329mb, ru_maxrss: 334mb (delta=20mb)
|
|
2025-11-09T20:57:52Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8732 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:52Z USER 796 (nc00/sg02) [ModuleForkPass]: Running expand_scheduling_units
|
|
2025-11-09T20:57:52Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to expand_scheduling_units: modules=1 functions=1 allocs=2134 blocks=1 instructions=8732 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:52Z USER 796 (nc00/sg02) [ModuleForkPass]: expand_scheduling_units finished after 0.014 seconds
|
|
2025-11-09T20:57:52Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 327mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:52Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8732 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:52Z USER 796 (nc00/sg02) [ModuleForkPass]: Running dead_code_elim_o0
|
|
2025-11-09T20:57:52Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=2134 blocks=1 instructions=8732 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:52Z USER 796 (nc01/sg02) [ModuleForkPass]: dead_code_elim_o0 finished after 0.190 seconds
|
|
2025-11-09T20:57:52Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 328mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:52Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:52Z USER 796 (nc00/sg02) [ModuleForkPass]: dead_code_elim_o0 finished after 0.280 seconds
|
|
2025-11-09T20:57:52Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 328mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:52Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8732 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:52Z USER 796 [ModuleForkPass]: Compilation status: Total modules: 6, Passed: 6, Failed: 0
|
|
2025-11-09T20:57:52Z USER 796 [BackendPassManager]: mod_parallel_pass finished after 6.818 seconds
|
|
2025-11-09T20:57:52Z INFO 796 [BackendPassManager]: curr_vmrss: 328mb, ru_maxrss: 334mb (delta=20mb)
|
|
2025-11-09T20:57:52Z USER 796 [BackendPassManager]: Running subgraph_parallel_pass
|
|
2025-11-09T20:57:52Z INFO 796 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=6 functions=6 allocs=9704 blocks=6 instructions=29680 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:52Z USER 796 (sg00) [SubgraphForkPass]: Running localize_shared_memory
|
|
2025-11-09T20:57:52Z INFO 796 (sg00) [SubgraphForkPass]: Inputs to localize_shared_memory: modules=2 functions=2 allocs=2911 blocks=2 instructions=5175 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:52Z USER 796 (sg01) [SubgraphForkPass]: Running localize_shared_memory
|
|
2025-11-09T20:57:52Z USER 796 (sg02) [SubgraphForkPass]: Running localize_shared_memory
|
|
2025-11-09T20:57:52Z INFO 796 (sg02) [SubgraphForkPass]: Inputs to localize_shared_memory: modules=2 functions=2 allocs=3886 blocks=2 instructions=16752 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:52Z INFO 796 (sg01) [SubgraphForkPass]: Inputs to localize_shared_memory: modules=2 functions=2 allocs=2907 blocks=2 instructions=7753 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:52Z USER 796 (sg00) [SubgraphForkPass]: localize_shared_memory finished after 0.013 seconds
|
|
2025-11-09T20:57:52Z INFO 796 (sg00) [SubgraphForkPass]: curr_vmrss: 328mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:52Z INFO 796 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 2911 memory location(s), 2 block(s), and 5175 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:53Z USER 796 (sg02) [SubgraphForkPass]: localize_shared_memory finished after 0.018 seconds
|
|
2025-11-09T20:57:53Z USER 796 (sg01) [SubgraphForkPass]: localize_shared_memory finished after 0.017 seconds
|
|
2025-11-09T20:57:53Z INFO 796 (sg01) [SubgraphForkPass]: curr_vmrss: 328mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:53Z INFO 796 (sg02) [SubgraphForkPass]: curr_vmrss: 328mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:53Z INFO 796 (sg02) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 3886 memory location(s), 2 block(s), and 16752 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:53Z INFO 796 (sg01) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 2907 memory location(s), 2 block(s), and 7753 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:53Z USER 796 [SubgraphForkPass]: Compilation status: Total subgraphs: 3, Passed: 3, Failed: 0
|
|
2025-11-09T20:57:53Z USER 796 [BackendPassManager]: subgraph_parallel_pass finished after 0.169 seconds
|
|
2025-11-09T20:57:53Z INFO 796 [BackendPassManager]: curr_vmrss: 328mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:53Z USER 796 [BackendPassManager]: Running mod_parallel_pass
|
|
2025-11-09T20:57:53Z INFO 796 [BackendPassManager]: Inputs to mod_parallel_pass: modules=6 functions=6 allocs=9704 blocks=6 instructions=29680 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:53Z USER 796 (nc01/sg00) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:53Z USER 796 (nc01/sg02) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:53Z USER 796 (nc00/sg01) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:53Z USER 796 (nc00/sg02) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=1455 blocks=1 instructions=2586 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=2134 blocks=1 instructions=8732 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=1752 blocks=1 instructions=8020 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=1454 blocks=1 instructions=3878 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:53Z USER 796 (nc01/sg01) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=1453 blocks=1 instructions=3875 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:53Z USER 796 (nc00/sg00) [ModuleForkPass]: Running address_rotation_sb
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=1456 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 131 PSUM Banks
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 29 PSUM Banks
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 116 PSUM Banks
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 134 PSUM Banks
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 29 PSUM Banks
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 15 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 124 PSUM Banks
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 15 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 63 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 63 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 35 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 55 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 7 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 8 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 119 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:53Z USER 796 (nc00/sg00) [ModuleForkPass]: address_rotation_sb finished after 0.597 seconds
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 328mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:53Z USER 796 (nc00/sg00) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1456 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB}
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 130 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:53Z USER 796 (nc01/sg00) [ModuleForkPass]: address_rotation_sb finished after 0.612 seconds
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 327mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2586 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:53Z USER 796 (nc01/sg00) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1455 blocks=1 instructions=2586 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB}
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: PSUM Rotation rotated 172 PSUM Banks
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: PSUM Rotation rotated 38 PSUM Banks
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: PSUM Rotation rotated 163 PSUM Banks
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: PSUM Rotation rotated 163 PSUM Banks
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 17 Sb address
|
|
2025-11-09T20:57:53Z USER 796 (nc00/sg00) [ModuleForkPass]: anti_dependency_analyzer finished after 0.296 seconds
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 330mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: PSUM Rotation rotated 38 PSUM Banks
|
|
2025-11-09T20:57:53Z USER 796 (nc00/sg00) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1456 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS}
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 57 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: PSUM Rotation rotated 145 PSUM Banks
|
|
2025-11-09T20:57:53Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 17 Sb address
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 62 Sb address
|
|
2025-11-09T20:57:53Z USER 796 (nc01/sg00) [ModuleForkPass]: anti_dependency_analyzer finished after 0.304 seconds
|
|
2025-11-09T20:57:53Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 329mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2586 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg00) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1455 blocks=1 instructions=2586 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS}
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 57 Sb address
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 53 Sb address
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 109 Sb address
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg01) [ModuleForkPass]: address_rotation_sb finished after 1.015 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 329mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3875 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg01) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1453 blocks=1 instructions=3875 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB}
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg00) [ModuleForkPass]: anti_dependency_analyzer finished after 0.118 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 328mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg00) [ModuleForkPass]: Running dep_opt
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to dep_opt: modules=1 functions=1 allocs=1456 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [build_flow_deps]: Start build fdeps. Invocation: 13Sun Nov 9 20:57:54 2025
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [build_flow_deps]: Allocs: 1456 instructions: 2589
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 111 Sb address
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg01) [ModuleForkPass]: address_rotation_sb finished after 1.107 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 328mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3878 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg01) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1454 blocks=1 instructions=3878 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB}
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [build_flow_deps]: Build fdeps inserted 5828 edges
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [build_flow_deps]: Done build fdeps 5828 Sun Nov 9 20:57:54 2025
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg01) [ModuleForkPass]: anti_dependency_analyzer finished after 0.271 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 331mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3875 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg01) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1453 blocks=1 instructions=3875 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS}
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg00) [ModuleForkPass]: dep_opt finished after 0.213 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 330mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg00) [ModuleForkPass]: Running report_stats
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to report_stats: modules=1 functions=1 allocs=1456 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ReportStats]: Data Movement Statistics: sg0000
|
|
┌─────────────────┬────────────────────────────┬───────┬────────────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
├─────────────────┼────────────────────────────┼───────┼────────────┤
|
|
│ DMACopy │ ExternalInput -> Internal │ 32 │ 4978638848 │
|
|
│ DMACopy │ Internal -> ExternalOutput │ 32 │ 134217728 │
|
|
│ DMACopy │ Internal -> Output │ 1 │ 16777216 │
|
|
│ DMACopy (Spill) │ Internal │ 32 │ 0 │
|
|
│ Load │ Const -> Internal │ 5 │ 57600 │
|
|
│ Load │ ExternalInput -> Internal │ 18 │ 5259780 │
|
|
│ Load │ Internal │ 92 │ 13631488 │
|
|
│ Save │ Internal │ 62 │ 9437184 │
|
|
│ Save │ Internal -> Output │ 19 │ 4718594 │
|
|
└─────────────────┴────────────────────────────┴───────┴────────────┘
|
|
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ 2 │ 5 │
|
|
│ 4 │ 1 │
|
|
│ 32 │ 1 │
|
|
│ 64 │ 3 │
|
|
│ 256 │ 98 │
|
|
│ 512 │ 1 │
|
|
│ 1024 │ 40 │
|
|
│ 2048 │ 46 │
|
|
│ 4096 │ 33 │
|
|
│ 524288 │ 32 │
|
|
│ 8388608 │ 2 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ReportStats]: MM Stats: #MatMults 1157 #MatMult-Transposes 289
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ReportStats]: IO Tensor size combined: 178672132
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ReportStats]: IO Tensor Statistics:
|
|
┌────────────────────┬────────────────┬──────────┬──────────────┐
|
|
│ Largest IO Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├────────────────────┼────────────────┼──────────┼──────────────┤
|
|
│ input60 │ ExternalInput │ bfloat16 │ 155582464 │
|
|
│ input4 │ ExternalInput │ bfloat16 │ 4194304 │
|
|
│ output1 │ ExternalOutput │ bfloat16 │ 4194304 │
|
|
│ input5 │ ExternalInput │ bfloat16 │ 4194304 │
|
|
│ output2 │ ExternalOutput │ bfloat16 │ 4194304 │
|
|
│ input61 │ ExternalInput │ bfloat16 │ 2097152 │
|
|
│ input67 │ ExternalInput │ bfloat16 │ 2097152 │
|
|
│ input62 │ ExternalInput │ bfloat16 │ 1048576 │
|
|
│ input65 │ ExternalInput │ bfloat16 │ 1048576 │
|
|
│ input1 │ ExternalInput │ int32 │ 8192 │
|
|
└────────────────────┴────────────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ReportStats]: Large (Internal) Tensor Statistics:
|
|
┌───────────────────────────┬──────────┬──────────┬──────────────┐
|
|
│ Largest Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├───────────────────────────┼──────────┼──────────┼──────────────┤
|
|
│ intermediate0 │ Output │ bfloat16 │ 8388608 │
|
|
│ intermediate3 │ Output │ bfloat16 │ 8388608 │
|
|
│ dot.4-buffer-2729 │ Internal │ bfloat16 │ 8388608 │
|
|
│ intermediate3-buffer-2731 │ Internal │ bfloat16 │ 8388608 │
|
|
│ all_gather.1_i0 │ Internal │ bfloat16 │ 4194304 │
|
|
│ all_gather.1_i1 │ Internal │ bfloat16 │ 4194304 │
|
|
│ get_tuple_element.1 │ Internal │ bfloat16 │ 2097152 │
|
|
│ reshape.16 │ Internal │ bfloat16 │ 2097152 │
|
|
│ reshape.24 │ Internal │ bfloat16 │ 2097152 │
|
|
│ reshape.29 │ Internal │ bfloat16 │ 2097152 │
|
|
└───────────────────────────┴──────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg00) [ModuleForkPass]: report_stats finished after 0.004 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 330mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg00) [ModuleForkPass]: anti_dependency_analyzer finished after 0.405 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 331mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2586 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg01) [ModuleForkPass]: anti_dependency_analyzer finished after 0.095 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 331mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg00) [ModuleForkPass]: Running dep_opt
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3875 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg01) [ModuleForkPass]: Running dep_opt
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to dep_opt: modules=1 functions=1 allocs=1453 blocks=1 instructions=3875 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [build_flow_deps]: Start build fdeps. Invocation: 14Sun Nov 9 20:57:54 2025
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg01) [ModuleForkPass]: anti_dependency_analyzer finished after 0.292 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 331mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [build_flow_deps]: Allocs: 1453 instructions: 3875
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to dep_opt: modules=1 functions=1 allocs=1455 blocks=1 instructions=2586 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3878 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg01) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1454 blocks=1 instructions=3878 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS}
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [build_flow_deps]: Start build fdeps. Invocation: 15Sun Nov 9 20:57:54 2025
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [build_flow_deps]: Allocs: 1455 instructions: 2586
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg01) [ModuleForkPass]: anti_dependency_analyzer finished after 0.086 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 330mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3878 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg01) [ModuleForkPass]: Running dep_opt
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to dep_opt: modules=1 functions=1 allocs=1454 blocks=1 instructions=3878 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [build_flow_deps]: Start build fdeps. Invocation: 16Sun Nov 9 20:57:54 2025
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [build_flow_deps]: Allocs: 1454 instructions: 3878
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: PSUM Rotation rotated 362 PSUM Banks
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [build_flow_deps]: Build fdeps inserted 10064 edges
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [build_flow_deps]: Done build fdeps 10064 Sun Nov 9 20:57:54 2025
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [build_flow_deps]: Build fdeps inserted 5822 edges
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [build_flow_deps]: Done build fdeps 5822 Sun Nov 9 20:57:54 2025
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [build_flow_deps]: Build fdeps inserted 10061 edges
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [build_flow_deps]: Done build fdeps 10061 Sun Nov 9 20:57:54 2025
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg01) [ModuleForkPass]: dep_opt finished after 0.119 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 330mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3878 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg01) [ModuleForkPass]: Running report_stats
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to report_stats: modules=1 functions=1 allocs=1454 blocks=1 instructions=3878 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ReportStats]: Data Movement Statistics: sg0001
|
|
┌─────────────────┬────────────────────────────┬───────┬───────────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
├─────────────────┼────────────────────────────┼───────┼───────────┤
|
|
│ DMACopy │ Input -> Internal │ 1 │ 12582912 │
|
|
│ DMACopy │ Internal -> ExternalOutput │ 32 │ 134217728 │
|
|
│ DMACopy │ Internal -> Output │ 1 │ 16777216 │
|
|
│ DMACopy (Spill) │ Internal │ 32 │ 0 │
|
|
│ Load │ Const -> Internal │ 3 │ 49152 │
|
|
│ Load │ ExternalInput -> Internal │ 104 │ 38806020 │
|
|
│ Load │ Input -> Internal │ 2 │ 524288 │
|
|
│ Load │ Internal │ 92 │ 13631488 │
|
|
│ Save │ Internal │ 68 │ 12582912 │
|
|
│ Save │ Internal -> Output │ 9 │ 4194306 │
|
|
└─────────────────┴────────────────────────────┴───────┴───────────┘
|
|
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ 2 │ 5 │
|
|
│ 4 │ 1 │
|
|
│ 32 │ 2 │
|
|
│ 64 │ 2 │
|
|
│ 256 │ 97 │
|
|
│ 1024 │ 8 │
|
|
│ 2048 │ 76 │
|
|
│ 4096 │ 87 │
|
|
│ 524288 │ 32 │
|
|
│ 4194304 │ 3 │
|
|
│ 8388608 │ 2 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ReportStats]: MM Stats: #MatMults 2492 #MatMult-Transposes 448
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ReportStats]: IO Tensor size combined: 41951748
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ReportStats]: IO Tensor Statistics:
|
|
┌────────────────────┬────────────────┬──────────┬──────────────┐
|
|
│ Largest IO Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├────────────────────┼────────────────┼──────────┼──────────────┤
|
|
│ input68 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input69 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input71 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input7 │ ExternalInput │ bfloat16 │ 4194304 │
|
|
│ output4 │ ExternalOutput │ bfloat16 │ 4194304 │
|
|
│ input6 │ ExternalInput │ bfloat16 │ 4194304 │
|
|
│ output3 │ ExternalOutput │ bfloat16 │ 4194304 │
|
|
│ input72 │ ExternalInput │ bfloat16 │ 2097152 │
|
|
│ input78 │ ExternalInput │ bfloat16 │ 2097152 │
|
|
│ input76 │ ExternalInput │ bfloat16 │ 1048576 │
|
|
└────────────────────┴────────────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ReportStats]: Large (Internal) Tensor Statistics:
|
|
┌───────────────────────────┬──────────┬──────────┬──────────────┐
|
|
│ Largest Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├───────────────────────────┼──────────┼──────────┼──────────────┤
|
|
│ intermediate3 │ Input │ bfloat16 │ 8388608 │
|
|
│ dot.7-buffer-2421 │ Internal │ bfloat16 │ 8388608 │
|
|
│ dot.11-buffer-2426 │ Internal │ bfloat16 │ 8388608 │
|
|
│ intermediate5 │ Output │ bfloat16 │ 8388608 │
|
|
│ intermediate0 │ Input │ bfloat16 │ 8388608 │
|
|
│ all_reduce.1-buffer-2423 │ Internal │ bfloat16 │ 8388608 │
|
|
│ intermediate6-buffer-2428 │ Internal │ bfloat16 │ 8388608 │
|
|
│ intermediate6 │ Output │ bfloat16 │ 8388608 │
|
|
│ add.4 │ Internal │ bfloat16 │ 8388608 │
|
|
│ reshape.60 │ Internal │ bfloat16 │ 2097152 │
|
|
└───────────────────────────┴──────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:57:54Z USER 796 (nc00/sg01) [ModuleForkPass]: report_stats finished after 0.003 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 330mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3878 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg00) [ModuleForkPass]: dep_opt finished after 0.218 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 330mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2586 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg00) [ModuleForkPass]: Running report_stats
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to report_stats: modules=1 functions=1 allocs=1455 blocks=1 instructions=2586 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ReportStats]: Data Movement Statistics: sg0000
|
|
┌─────────────────┬────────────────────────────┬───────┬────────────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
├─────────────────┼────────────────────────────┼───────┼────────────┤
|
|
│ DMACopy │ ExternalInput -> Internal │ 32 │ 4978638848 │
|
|
│ DMACopy │ Internal -> ExternalOutput │ 32 │ 134217728 │
|
|
│ DMACopy (Spill) │ Internal │ 32 │ 0 │
|
|
│ Load │ Const -> Internal │ 5 │ 57600 │
|
|
│ Load │ ExternalInput -> Internal │ 18 │ 5259780 │
|
|
│ Load │ Internal │ 92 │ 13631488 │
|
|
│ Save │ Internal │ 62 │ 9437184 │
|
|
│ Save │ Internal -> Output │ 18 │ 4718592 │
|
|
└─────────────────┴────────────────────────────┴───────┴────────────┘
|
|
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ 2 │ 4 │
|
|
│ 4 │ 1 │
|
|
│ 32 │ 1 │
|
|
│ 64 │ 3 │
|
|
│ 256 │ 98 │
|
|
│ 512 │ 1 │
|
|
│ 1024 │ 40 │
|
|
│ 2048 │ 46 │
|
|
│ 4096 │ 33 │
|
|
│ 524288 │ 32 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg01) [ModuleForkPass]: dep_opt finished after 0.220 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ReportStats]: MM Stats: #MatMults 1157 #MatMult-Transposes 289
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 330mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3875 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg01) [ModuleForkPass]: Running report_stats
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to report_stats: modules=1 functions=1 allocs=1453 blocks=1 instructions=3875 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ReportStats]: IO Tensor size combined: 178672132
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ReportStats]: IO Tensor Statistics:
|
|
┌────────────────────┬────────────────┬──────────┬──────────────┐
|
|
│ Largest IO Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├────────────────────┼────────────────┼──────────┼──────────────┤
|
|
│ input60 │ ExternalInput │ bfloat16 │ 155582464 │
|
|
│ input4 │ ExternalInput │ bfloat16 │ 4194304 │
|
|
│ output1 │ ExternalOutput │ bfloat16 │ 4194304 │
|
|
│ input5 │ ExternalInput │ bfloat16 │ 4194304 │
|
|
│ output2 │ ExternalOutput │ bfloat16 │ 4194304 │
|
|
│ input61 │ ExternalInput │ bfloat16 │ 2097152 │
|
|
│ input67 │ ExternalInput │ bfloat16 │ 2097152 │
|
|
│ input62 │ ExternalInput │ bfloat16 │ 1048576 │
|
|
│ input65 │ ExternalInput │ bfloat16 │ 1048576 │
|
|
│ input1 │ ExternalInput │ int32 │ 8192 │
|
|
└────────────────────┴────────────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ReportStats]: Large (Internal) Tensor Statistics:
|
|
┌───────────────────────────┬──────────┬──────────┬──────────────┐
|
|
│ Largest Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├───────────────────────────┼──────────┼──────────┼──────────────┤
|
|
│ intermediate0 │ Output │ bfloat16 │ 8388608 │
|
|
│ intermediate3 │ Output │ bfloat16 │ 8388608 │
|
|
│ dot.4-buffer-2729 │ Internal │ bfloat16 │ 8388608 │
|
|
│ intermediate3-buffer-2731 │ Internal │ bfloat16 │ 8388608 │
|
|
│ all_gather.1_i0 │ Internal │ bfloat16 │ 4194304 │
|
|
│ all_gather.1_i1 │ Internal │ bfloat16 │ 4194304 │
|
|
│ get_tuple_element.1 │ Internal │ bfloat16 │ 2097152 │
|
|
│ reshape.16 │ Internal │ bfloat16 │ 2097152 │
|
|
│ reshape.24 │ Internal │ bfloat16 │ 2097152 │
|
|
│ reshape.29 │ Internal │ bfloat16 │ 2097152 │
|
|
└───────────────────────────┴──────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg00) [ModuleForkPass]: report_stats finished after 0.004 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 330mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2586 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ReportStats]: Data Movement Statistics: sg0001
|
|
┌─────────────────┬────────────────────────────┬───────┬───────────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
├─────────────────┼────────────────────────────┼───────┼───────────┤
|
|
│ DMACopy │ Input -> Internal │ 1 │ 12582912 │
|
|
│ DMACopy │ Internal -> ExternalOutput │ 32 │ 134217728 │
|
|
│ DMACopy (Spill) │ Internal │ 32 │ 0 │
|
|
│ Load │ Const -> Internal │ 3 │ 49152 │
|
|
│ Load │ ExternalInput -> Internal │ 104 │ 38806020 │
|
|
│ Load │ Input -> Internal │ 2 │ 524288 │
|
|
│ Load │ Internal │ 92 │ 13631488 │
|
|
│ Save │ Internal │ 68 │ 12582912 │
|
|
│ Save │ Internal -> Output │ 8 │ 4194304 │
|
|
└─────────────────┴────────────────────────────┴───────┴───────────┘
|
|
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ 2 │ 4 │
|
|
│ 4 │ 1 │
|
|
│ 32 │ 2 │
|
|
│ 64 │ 2 │
|
|
│ 256 │ 97 │
|
|
│ 1024 │ 8 │
|
|
│ 2048 │ 76 │
|
|
│ 4096 │ 87 │
|
|
│ 524288 │ 32 │
|
|
│ 4194304 │ 3 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ReportStats]: MM Stats: #MatMults 2492 #MatMult-Transposes 448
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ReportStats]: IO Tensor size combined: 41951748
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ReportStats]: IO Tensor Statistics:
|
|
┌────────────────────┬────────────────┬──────────┬──────────────┐
|
|
│ Largest IO Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├────────────────────┼────────────────┼──────────┼──────────────┤
|
|
│ input68 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input69 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input71 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input7 │ ExternalInput │ bfloat16 │ 4194304 │
|
|
│ output4 │ ExternalOutput │ bfloat16 │ 4194304 │
|
|
│ input6 │ ExternalInput │ bfloat16 │ 4194304 │
|
|
│ output3 │ ExternalOutput │ bfloat16 │ 4194304 │
|
|
│ input72 │ ExternalInput │ bfloat16 │ 2097152 │
|
|
│ input78 │ ExternalInput │ bfloat16 │ 2097152 │
|
|
│ input76 │ ExternalInput │ bfloat16 │ 1048576 │
|
|
└────────────────────┴────────────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ReportStats]: Large (Internal) Tensor Statistics:
|
|
┌───────────────────────────┬──────────┬──────────┬──────────────┐
|
|
│ Largest Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├───────────────────────────┼──────────┼──────────┼──────────────┤
|
|
│ intermediate3 │ Input │ bfloat16 │ 8388608 │
|
|
│ dot.7-buffer-2421 │ Internal │ bfloat16 │ 8388608 │
|
|
│ dot.11-buffer-2426 │ Internal │ bfloat16 │ 8388608 │
|
|
│ intermediate5 │ Output │ bfloat16 │ 8388608 │
|
|
│ intermediate0 │ Input │ bfloat16 │ 8388608 │
|
|
│ all_reduce.1-buffer-2423 │ Internal │ bfloat16 │ 8388608 │
|
|
│ intermediate6-buffer-2428 │ Internal │ bfloat16 │ 8388608 │
|
|
│ intermediate6 │ Output │ bfloat16 │ 8388608 │
|
|
│ add.4 │ Internal │ bfloat16 │ 8388608 │
|
|
│ reshape.60 │ Internal │ bfloat16 │ 2097152 │
|
|
└───────────────────────────┴──────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:57:54Z USER 796 (nc01/sg01) [ModuleForkPass]: report_stats finished after 0.005 seconds
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 330mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3875 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: PSUM Rotation rotated 10 PSUM Banks
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: PSUM Rotation rotated 149 PSUM Banks
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 4 Sb address
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 1 Sb address
|
|
2025-11-09T20:57:54Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 22 Sb address
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 4 Sb address
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: PSUM Rotation rotated 432 PSUM Banks
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 42 Sb address
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:55Z USER 796 (nc01/sg02) [ModuleForkPass]: address_rotation_sb finished after 2.018 seconds
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 331mb, ru_maxrss: 334mb (delta=0mb)
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:55Z USER 796 (nc01/sg02) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1752 blocks=1 instructions=8020 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB}
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: PSUM Rotation rotated 10 PSUM Banks
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: PSUM Rotation rotated 211 PSUM Banks
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 7 Sb address
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 5 Sb address
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 43 Sb address
|
|
2025-11-09T20:57:55Z USER 796 (nc01/sg02) [ModuleForkPass]: anti_dependency_analyzer finished after 0.497 seconds
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 339mb, ru_maxrss: 338mb (delta=4mb)
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:55Z USER 796 (nc01/sg02) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=1752 blocks=1 instructions=8020 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS}
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 3 Sb address
|
|
2025-11-09T20:57:55Z USER 796 (nc01/sg02) [ModuleForkPass]: anti_dependency_analyzer finished after 0.070 seconds
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 336mb, ru_maxrss: 338mb (delta=0mb)
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:55Z USER 796 (nc01/sg02) [ModuleForkPass]: Running dep_opt
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to dep_opt: modules=1 functions=1 allocs=1752 blocks=1 instructions=8020 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [build_flow_deps]: Start build fdeps. Invocation: 17Sun Nov 9 20:57:55 2025
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 62 Sb address
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [build_flow_deps]: Allocs: 1752 instructions: 8020
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address
|
|
2025-11-09T20:57:55Z USER 796 (nc00/sg02) [ModuleForkPass]: address_rotation_sb finished after 2.628 seconds
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 335mb, ru_maxrss: 338mb (delta=4mb)
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8732 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:55Z USER 796 (nc00/sg02) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=2134 blocks=1 instructions=8732 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB}
|
|
2025-11-09T20:57:55Z INFO 796 (nc00/sg02) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [build_flow_deps]: Build fdeps inserted 20935 edges
|
|
2025-11-09T20:57:55Z INFO 796 (nc01/sg02) [build_flow_deps]: Done build fdeps 20935 Sun Nov 9 20:57:55 2025
|
|
2025-11-09T20:57:56Z USER 796 (nc01/sg02) [ModuleForkPass]: dep_opt finished after 0.421 seconds
|
|
2025-11-09T20:57:56Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 339mb, ru_maxrss: 338mb (delta=0mb)
|
|
2025-11-09T20:57:56Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:56Z USER 796 (nc01/sg02) [ModuleForkPass]: Running report_stats
|
|
2025-11-09T20:57:56Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to report_stats: modules=1 functions=1 allocs=1752 blocks=1 instructions=8020 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:56Z INFO 796 (nc01/sg02) [ReportStats]: Data Movement Statistics: sg0002
|
|
┌─────────────┬───────────────────────────┬───────┬───────────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
├─────────────┼───────────────────────────┼───────┼───────────┤
|
|
│ DMACopy │ Input -> Internal │ 1 │ 12582912 │
|
|
│ DMACopy │ Internal │ 2 │ 8388608 │
|
|
│ Load │ Const -> Internal │ 1 │ 32768 │
|
|
│ Load │ ExternalInput -> Internal │ 243 │ 111362060 │
|
|
│ Load │ Internal │ 24 │ 8391814 │
|
|
│ Save │ Internal │ 168 │ 8465728 │
|
|
└─────────────┴───────────────────────────┴───────┴───────────┘
|
|
|
|
2025-11-09T20:57:56Z INFO 796 (nc01/sg02) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ 2 │ 2 │
|
|
│ 4 │ 4 │
|
|
│ 32 │ 2 │
|
|
│ 128 │ 2 │
|
|
│ 192 │ 1 │
|
|
│ 256 │ 1 │
|
|
│ 512 │ 154 │
|
|
│ 1024 │ 1 │
|
|
│ 2048 │ 46 │
|
|
│ 4096 │ 224 │
|
|
│ 4194304 │ 3 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:57:56Z INFO 796 (nc01/sg02) [ReportStats]: MM Stats: #MatMults 6518 #MatMult-Transposes 2918
|
|
2025-11-09T20:57:56Z INFO 796 (nc01/sg02) [ReportStats]: IO Tensor size combined: 174473232
|
|
2025-11-09T20:57:56Z INFO 796 (nc01/sg02) [ReportStats]: IO Tensor Statistics:
|
|
┌────────────────────┬────────────────┬──────────┬──────────────┐
|
|
│ Largest IO Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├────────────────────┼────────────────┼──────────┼──────────────┤
|
|
│ input369 │ ExternalInput │ bfloat16 │ 155582464 │
|
|
│ input365 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input368 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input366 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input1 │ ExternalInput │ int32 │ 8192 │
|
|
│ input370 │ ExternalInput │ bfloat16 │ 4096 │
|
|
│ input367 │ ExternalInput │ bfloat16 │ 4096 │
|
|
│ input3 │ ExternalInput │ float32 │ 12 │
|
|
│ output0 │ ExternalOutput │ int32 │ 4 │
|
|
└────────────────────┴────────────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:57:56Z INFO 796 (nc01/sg02) [ReportStats]: Large (Internal) Tensor Statistics:
|
|
┌────────────────────────────────┬──────────┬──────────┬──────────────┐
|
|
│ Largest Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├────────────────────────────────┼──────────┼──────────┼──────────────┤
|
|
│ convert.53 │ Internal │ bfloat16 │ 8388608 │
|
|
│ all_reduce.3-buffer-2029 │ Internal │ bfloat16 │ 8388608 │
|
|
│ intermediate84 │ Input │ bfloat16 │ 8388608 │
|
|
│ dot.14-buffer-2027 │ Internal │ bfloat16 │ 8388608 │
|
|
│ intermediate83 │ Input │ bfloat16 │ 8388608 │
|
|
│ add.9 │ Internal │ bfloat16 │ 8388608 │
|
|
│ DynamicDMAScratchLoc │ Internal │ uint8 │ 2097152 │
|
|
│ add.9_pftranspose_990-t1596_i7 │ Internal │ bfloat16 │ 1048576 │
|
|
│ add.9_pftranspose_990-t1596_i6 │ Internal │ bfloat16 │ 1048576 │
|
|
│ add.9_pftranspose_990-t1596_i5 │ Internal │ bfloat16 │ 1048576 │
|
|
└────────────────────────────────┴──────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:57:56Z USER 796 (nc01/sg02) [ModuleForkPass]: report_stats finished after 0.100 seconds
|
|
2025-11-09T20:57:56Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 341mb, ru_maxrss: 340mb (delta=1mb)
|
|
2025-11-09T20:57:56Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8020 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:56Z USER 796 (nc00/sg02) [ModuleForkPass]: anti_dependency_analyzer finished after 0.669 seconds
|
|
2025-11-09T20:57:56Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 342mb, ru_maxrss: 341mb (delta=3mb)
|
|
2025-11-09T20:57:56Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8732 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:56Z USER 796 (nc00/sg02) [ModuleForkPass]: Running anti_dependency_analyzer
|
|
2025-11-09T20:57:56Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=2134 blocks=1 instructions=8732 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:56Z INFO 796 (nc00/sg02) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS}
|
|
2025-11-09T20:57:56Z INFO 796 (nc00/sg02) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824
|
|
2025-11-09T20:57:56Z USER 796 (nc00/sg02) [ModuleForkPass]: anti_dependency_analyzer finished after 0.197 seconds
|
|
2025-11-09T20:57:56Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 338mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:56Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8732 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:56Z USER 796 (nc00/sg02) [ModuleForkPass]: Running dep_opt
|
|
2025-11-09T20:57:56Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to dep_opt: modules=1 functions=1 allocs=2134 blocks=1 instructions=8732 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:56Z INFO 796 (nc00/sg02) [build_flow_deps]: Start build fdeps. Invocation: 18Sun Nov 9 20:57:56 2025
|
|
2025-11-09T20:57:56Z INFO 796 (nc00/sg02) [build_flow_deps]: Allocs: 2134 instructions: 8732
|
|
2025-11-09T20:57:56Z INFO 796 (nc00/sg02) [build_flow_deps]: Build fdeps inserted 31107 edges
|
|
2025-11-09T20:57:56Z INFO 796 (nc00/sg02) [build_flow_deps]: Done build fdeps 31107 Sun Nov 9 20:57:56 2025
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: dep_opt finished after 0.478 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8732 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: Running report_stats
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to report_stats: modules=1 functions=1 allocs=2134 blocks=1 instructions=8732 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ReportStats]: Data Movement Statistics: sg0002
|
|
┌─────────────┬────────────────────────────┬───────┬───────────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
├─────────────┼────────────────────────────┼───────┼───────────┤
|
|
│ DMACopy │ Input -> Internal │ 1 │ 12582912 │
|
|
│ DMACopy │ Internal │ 6 │ 8396800 │
|
|
│ Load │ Const -> Internal │ 8 │ 201096 │
|
|
│ Load │ ExternalInput -> Internal │ 244 │ 111366156 │
|
|
│ Load │ Internal │ 36 │ 8561158 │
|
|
│ Save │ Internal │ 184 │ 8483139 │
|
|
│ Save │ Internal -> ExternalOutput │ 1 │ 4 │
|
|
└─────────────┴────────────────────────────┴───────┴───────────┘
|
|
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ 1 │ 1 │
|
|
│ 2 │ 3 │
|
|
│ 4 │ 9 │
|
|
│ 8 │ 2 │
|
|
│ 32 │ 9 │
|
|
│ 128 │ 6 │
|
|
│ 192 │ 1 │
|
|
│ 256 │ 1 │
|
|
│ 512 │ 154 │
|
|
│ 1024 │ 17 │
|
|
│ 2048 │ 46 │
|
|
│ 4096 │ 225 │
|
|
│ 4748 │ 2 │
|
|
│ 4194304 │ 3 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ReportStats]: MM Stats: #MatMults 6642 #MatMult-Transposes 2918
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ReportStats]: IO Tensor size combined: 174473232
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ReportStats]: IO Tensor Statistics:
|
|
┌────────────────────┬────────────────┬──────────┬──────────────┐
|
|
│ Largest IO Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├────────────────────┼────────────────┼──────────┼──────────────┤
|
|
│ input369 │ ExternalInput │ bfloat16 │ 155582464 │
|
|
│ input365 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input368 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input366 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input1 │ ExternalInput │ int32 │ 8192 │
|
|
│ input370 │ ExternalInput │ bfloat16 │ 4096 │
|
|
│ input367 │ ExternalInput │ bfloat16 │ 4096 │
|
|
│ input3 │ ExternalInput │ float32 │ 12 │
|
|
│ output0 │ ExternalOutput │ int32 │ 4 │
|
|
└────────────────────┴────────────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ReportStats]: Large (Internal) Tensor Statistics:
|
|
┌──────────────────────────┬──────────┬──────────┬──────────────┐
|
|
│ Largest Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├──────────────────────────┼──────────┼──────────┼──────────────┤
|
|
│ add.9 │ Internal │ bfloat16 │ 8388608 │
|
|
│ convert.53 │ Internal │ bfloat16 │ 8388608 │
|
|
│ intermediate84 │ Input │ bfloat16 │ 8388608 │
|
|
│ dot.14-buffer-2027 │ Internal │ bfloat16 │ 8388608 │
|
|
│ intermediate83 │ Input │ bfloat16 │ 8388608 │
|
|
│ all_reduce.3-buffer-2029 │ Internal │ bfloat16 │ 8388608 │
|
|
│ DynamicDMAScratchLoc │ Internal │ uint8 │ 2097152 │
|
|
│ -t3023 │ Internal │ float32 │ 1048576 │
|
|
│ -t3017 │ Internal │ float32 │ 1048576 │
|
|
│ -t3012 │ Internal │ float32 │ 1048576 │
|
|
└──────────────────────────┴──────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: report_stats finished after 0.009 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8732 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 [ModuleForkPass]: Compilation status: Total modules: 6, Passed: 6, Failed: 0
|
|
2025-11-09T20:57:57Z USER 796 [BackendPassManager]: mod_parallel_pass finished after 4.013 seconds
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=7mb)
|
|
2025-11-09T20:57:57Z USER 796 [BackendPassManager]: Running assign_trigger_engine
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: Inputs to assign_trigger_engine: modules=6 functions=6 allocs=9704 blocks=6 instructions=29680 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [AssignTriggerEngine]: Assigned trigger engine for 79 DMA instructions. Moved 17 DMA instructions to CC's engines.
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [AssignTriggerEngine]: Assigned trigger engine for 78 DMA instructions. Moved 16 DMA instructions to CC's engines.
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [AssignTriggerEngine]: Assigned trigger engine for 77 DMA instructions. Moved 9 DMA instructions to CC's engines.
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [AssignTriggerEngine]: Assigned trigger engine for 76 DMA instructions. Moved 8 DMA instructions to CC's engines.
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [AssignTriggerEngine]: Assigned trigger engine for 195 DMA instructions. Moved 11 DMA instructions to CC's engines.
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [AssignTriggerEngine]: Assigned trigger engine for 177 DMA instructions. Moved 9 DMA instructions to CC's engines.
|
|
2025-11-09T20:57:57Z INFO 796 [AssignTriggerEngine]: Limiting IO queue to SP only
|
|
2025-11-09T20:57:57Z USER 796 [BackendPassManager]: assign_trigger_engine finished after 0.134 seconds
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: Output has 6 module(s), 6 function(s), 9704 memory location(s), 6 block(s), and 29680 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 [BackendPassManager]: Running mod_parallel_pass
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: Inputs to mod_parallel_pass: modules=6 functions=6 allocs=9704 blocks=6 instructions=29680 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg00) [ModuleForkPass]: Running sync_before_global_cc
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to sync_before_global_cc: modules=1 functions=1 allocs=1456 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: Running sync_before_global_cc
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg00) [ModuleForkPass]: Running sync_before_global_cc
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to sync_before_global_cc: modules=1 functions=1 allocs=2134 blocks=1 instructions=8732 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to sync_before_global_cc: modules=1 functions=1 allocs=1455 blocks=1 instructions=2586 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg02) [ModuleForkPass]: Running sync_before_global_cc
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to sync_before_global_cc: modules=1 functions=1 allocs=1752 blocks=1 instructions=8020 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg01) [ModuleForkPass]: Running sync_before_global_cc
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to sync_before_global_cc: modules=1 functions=1 allocs=1454 blocks=1 instructions=3878 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg01) [ModuleForkPass]: Running sync_before_global_cc
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to sync_before_global_cc: modules=1 functions=1 allocs=1453 blocks=1 instructions=3875 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg00) [ModuleForkPass]: sync_before_global_cc finished after 0.005 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg00) [ModuleForkPass]: sync_before_global_cc finished after 0.004 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2592 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg01) [ModuleForkPass]: sync_before_global_cc finished after 0.010 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3880 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg01) [ModuleForkPass]: sync_before_global_cc finished after 0.012 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3877 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: sync_before_global_cc finished after 0.019 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg02) [ModuleForkPass]: sync_before_global_cc finished after 0.018 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8735 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8023 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 [ModuleForkPass]: Compilation status: Total modules: 6, Passed: 6, Failed: 0
|
|
2025-11-09T20:57:57Z USER 796 [BackendPassManager]: mod_parallel_pass finished after 0.025 seconds
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z USER 796 [BackendPassManager]: Running assign_hwdge_engine
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: Inputs to assign_hwdge_engine: modules=6 functions=6 allocs=9704 blocks=6 instructions=29696 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 [BackendPassManager]: assign_hwdge_engine finished after 0.076 seconds
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: Output has 6 module(s), 6 function(s), 9704 memory location(s), 6 block(s), and 29696 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 [BackendPassManager]: Running mod_parallel_pass
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: Inputs to mod_parallel_pass: modules=6 functions=6 allocs=9704 blocks=6 instructions=29696 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: Running alloc_queues
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg00) [ModuleForkPass]: Running alloc_queues
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg02) [ModuleForkPass]: Running alloc_queues
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg01) [ModuleForkPass]: Running alloc_queues
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg00) [ModuleForkPass]: Running alloc_queues
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to alloc_queues: modules=1 functions=1 allocs=1752 blocks=1 instructions=8023 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to alloc_queues: modules=1 functions=1 allocs=1454 blocks=1 instructions=3880 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to alloc_queues: modules=1 functions=1 allocs=1456 blocks=1 instructions=2592 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to alloc_queues: modules=1 functions=1 allocs=2134 blocks=1 instructions=8735 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to alloc_queues: modules=1 functions=1 allocs=1455 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg01) [ModuleForkPass]: Running alloc_queues
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to alloc_queues: modules=1 functions=1 allocs=1453 blocks=1 instructions=3877 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [AllocQueues]: Alloc Queue info:
|
|
┌───────────────────┬────────────────┬────────────┬────────────┬──────────────────┐
|
|
│ Name │ DMAQueue::Type │ Engine │ Num Queues │ Num instructions │
|
|
├───────────────────┼────────────────┼────────────┼────────────┼──────────────────┤
|
|
│ qSPIO0 │ input │ SP │ 16 │ 3 │
|
|
│ qSPSpillReload0 │ data │ SP │ 16 │ 1 │
|
|
│ qPoolSpillReload0 │ data │ Pool │ 16 │ 32 │
|
|
│ qSPDynamicHW │ dynamic │ SP │ 16 │ 96 │
|
|
│ qPoolDynamic │ dynamic │ Pool │ 16 │ 99 │
|
|
│ qActDynamicHW │ dynamic │ Activation │ 16 │ 62 │
|
|
└───────────────────┴────────────────┴────────────┴────────────┴──────────────────┘
|
|
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg00) [ModuleForkPass]: alloc_queues finished after 0.003 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2592 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg00) [ModuleForkPass]: Running chain_dma_transposes
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to chain_dma_transposes: modules=1 functions=1 allocs=1456 blocks=1 instructions=2592 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [AllocQueues]: Alloc Queue info:
|
|
┌───────────────────┬────────────────┬────────────┬────────────┬──────────────────┐
|
|
│ Name │ DMAQueue::Type │ Engine │ Num Queues │ Num instructions │
|
|
├───────────────────┼────────────────┼────────────┼────────────┼──────────────────┤
|
|
│ qSPIO0 │ input │ SP │ 16 │ 2 │
|
|
│ qSPSpillReload0 │ data │ SP │ 16 │ 1 │
|
|
│ qPoolSpillReload0 │ data │ Pool │ 16 │ 32 │
|
|
│ qSPDynamicHW │ dynamic │ SP │ 16 │ 96 │
|
|
│ qPoolDynamic │ dynamic │ Pool │ 16 │ 98 │
|
|
│ qActDynamicHW │ dynamic │ Activation │ 16 │ 62 │
|
|
└───────────────────┴────────────────┴────────────┴────────────┴──────────────────┘
|
|
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg00) [ModuleForkPass]: alloc_queues finished after 0.004 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [AllocQueues]: Alloc Queue info:
|
|
┌───────────────────┬────────────────┬────────────┬────────────┬──────────────────┐
|
|
│ Name │ DMAQueue::Type │ Engine │ Num Queues │ Num instructions │
|
|
├───────────────────┼────────────────┼────────────┼────────────┼──────────────────┤
|
|
│ qSPIO0 │ input │ SP │ 16 │ 3 │
|
|
│ qPoolSpillReload0 │ data │ Pool │ 16 │ 32 │
|
|
│ qSPDynamicHW │ dynamic │ SP │ 16 │ 95 │
|
|
│ qPoolDynamic │ dynamic │ Pool │ 16 │ 146 │
|
|
│ qActDynamicHW │ dynamic │ Activation │ 16 │ 68 │
|
|
└───────────────────┴────────────────┴────────────┴────────────┴──────────────────┘
|
|
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg01) [ModuleForkPass]: alloc_queues finished after 0.004 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [AllocQueues]: Alloc Queue info:
|
|
┌───────────────────┬────────────────┬────────────┬────────────┬──────────────────┐
|
|
│ Name │ DMAQueue::Type │ Engine │ Num Queues │ Num instructions │
|
|
├───────────────────┼────────────────┼────────────┼────────────┼──────────────────┤
|
|
│ qSPIO0 │ input │ SP │ 16 │ 2 │
|
|
│ qPoolSpillReload0 │ data │ Pool │ 16 │ 32 │
|
|
│ qSPDynamicHW │ dynamic │ SP │ 16 │ 95 │
|
|
│ qPoolDynamic │ dynamic │ Pool │ 16 │ 145 │
|
|
│ qActDynamicHW │ dynamic │ Activation │ 16 │ 68 │
|
|
└───────────────────┴────────────────┴────────────┴────────────┴──────────────────┘
|
|
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg01) [ModuleForkPass]: alloc_queues finished after 0.004 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3880 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg01) [ModuleForkPass]: Running chain_dma_transposes
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to chain_dma_transposes: modules=1 functions=1 allocs=1454 blocks=1 instructions=3880 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3877 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg00) [ModuleForkPass]: Running chain_dma_transposes
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg00) [ModuleForkPass]: chain_dma_transposes finished after 0.003 seconds
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg01) [ModuleForkPass]: Running chain_dma_transposes
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to chain_dma_transposes: modules=1 functions=1 allocs=1455 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to chain_dma_transposes: modules=1 functions=1 allocs=1453 blocks=1 instructions=3877 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2592 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [AllocQueues]: Alloc Queue info:
|
|
┌───────────────────┬────────────────┬────────────┬────────────┬──────────────────┐
|
|
│ Name │ DMAQueue::Type │ Engine │ Num Queues │ Num instructions │
|
|
├───────────────────┼────────────────┼────────────┼────────────┼──────────────────┤
|
|
│ qSPIO0 │ input │ SP │ 16 │ 6 │
|
|
│ qSPSpillReload0 │ data │ SP │ 16 │ 7 │
|
|
│ qPoolSpillReload0 │ data │ Pool │ 16 │ 3 │
|
|
│ qDVESpillReload0 │ data │ DVE │ 16 │ 106 │
|
|
│ qActSpillReload0 │ data │ Activation │ 16 │ 45 │
|
|
│ qSPDynamicHW │ dynamic │ SP │ 16 │ 17 │
|
|
│ qPoolDynamic │ dynamic │ Pool │ 16 │ 239 │
|
|
│ qActDynamicHW │ dynamic │ Activation │ 16 │ 16 │
|
|
└───────────────────┴────────────────┴────────────┴────────────┴──────────────────┘
|
|
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg02) [ModuleForkPass]: alloc_queues finished after 0.008 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8023 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg01) [ModuleForkPass]: chain_dma_transposes finished after 0.004 seconds
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg02) [ModuleForkPass]: Running chain_dma_transposes
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3880 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to chain_dma_transposes: modules=1 functions=1 allocs=1752 blocks=1 instructions=8023 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg00) [ModuleForkPass]: chain_dma_transposes finished after 0.003 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg01) [ModuleForkPass]: chain_dma_transposes finished after 0.004 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3877 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [AllocQueues]: Alloc Queue info:
|
|
┌───────────────────┬────────────────┬────────────┬────────────┬──────────────────┐
|
|
│ Name │ DMAQueue::Type │ Engine │ Num Queues │ Num instructions │
|
|
├───────────────────┼────────────────┼────────────┼────────────┼──────────────────┤
|
|
│ qSPIO0 │ input │ SP │ 16 │ 8 │
|
|
│ qDVESpillReload0 │ data │ DVE │ 16 │ 114 │
|
|
│ qSPSpillReload0 │ data │ SP │ 16 │ 22 │
|
|
│ qPoolSpillReload0 │ data │ Pool │ 16 │ 10 │
|
|
│ qActSpillReload0 │ data │ Activation │ 16 │ 47 │
|
|
│ qSPDynamicHW │ dynamic │ SP │ 16 │ 22 │
|
|
│ qPoolDynamic │ dynamic │ Pool │ 16 │ 241 │
|
|
│ qActDynamicHW │ dynamic │ Activation │ 16 │ 16 │
|
|
└───────────────────┴────────────────┴────────────┴────────────┴──────────────────┘
|
|
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: alloc_queues finished after 0.012 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8735 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: Running chain_dma_transposes
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to chain_dma_transposes: modules=1 functions=1 allocs=2134 blocks=1 instructions=8735 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg02) [ModuleForkPass]: chain_dma_transposes finished after 0.009 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8023 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: chain_dma_transposes finished after 0.009 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8735 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 [ModuleForkPass]: Compilation status: Total modules: 6, Passed: 6, Failed: 0
|
|
2025-11-09T20:57:57Z USER 796 [BackendPassManager]: mod_parallel_pass finished after 0.024 seconds
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z USER 796 [BackendPassManager]: Running nc_parallel_pass
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: Inputs to nc_parallel_pass: modules=6 functions=6 allocs=9704 blocks=6 instructions=29696 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc01) [CoreForkPass]: Running insert_dma_switch_queue_instance
|
|
2025-11-09T20:57:57Z USER 796 (nc00) [CoreForkPass]: Running insert_dma_switch_queue_instance
|
|
2025-11-09T20:57:57Z INFO 796 (nc01) [CoreForkPass]: Inputs to insert_dma_switch_queue_instance: modules=3 functions=3 allocs=4660 blocks=3 instructions=14489 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc01) [CoreForkPass]: insert_dma_switch_queue_instance finished after 0.001 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00) [CoreForkPass]: Inputs to insert_dma_switch_queue_instance: modules=3 functions=3 allocs=5044 blocks=3 instructions=15207 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc00) [CoreForkPass]: insert_dma_switch_queue_instance finished after 0.001 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01) [CoreForkPass]: Output has 3 module(s), 3 function(s), 4660 memory location(s), 3 block(s), and 14489 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z INFO 796 (nc00) [CoreForkPass]: Output has 3 module(s), 3 function(s), 5044 memory location(s), 3 block(s), and 15207 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 [CoreForkPass]: Compilation status: Total modules: 2, Passed: 6, Failed: 0
|
|
2025-11-09T20:57:57Z USER 796 [BackendPassManager]: nc_parallel_pass finished after 0.003 seconds
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z USER 796 [BackendPassManager]: Running mod_parallel_pass
|
|
2025-11-09T20:57:57Z INFO 796 [BackendPassManager]: Inputs to mod_parallel_pass: modules=6 functions=6 allocs=9704 blocks=6 instructions=29696 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg01) [ModuleForkPass]: Running prefetch_scheduling_after_sched
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg02) [ModuleForkPass]: Running prefetch_scheduling_after_sched
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg01) [ModuleForkPass]: Running prefetch_scheduling_after_sched
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg00) [ModuleForkPass]: Running prefetch_scheduling_after_sched
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to prefetch_scheduling_after_sched: modules=1 functions=1 allocs=1453 blocks=1 instructions=3877 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to prefetch_scheduling_after_sched: modules=1 functions=1 allocs=1752 blocks=1 instructions=8023 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to prefetch_scheduling_after_sched: modules=1 functions=1 allocs=1454 blocks=1 instructions=3880 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to prefetch_scheduling_after_sched: modules=1 functions=1 allocs=1455 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg02) [ModuleForkPass]: prefetch_scheduling_after_sched finished after 0.000 seconds
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg01) [ModuleForkPass]: prefetch_scheduling_after_sched finished after 0.000 seconds
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg00) [ModuleForkPass]: prefetch_scheduling_after_sched finished after 0.000 seconds
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg01) [ModuleForkPass]: prefetch_scheduling_after_sched finished after 0.000 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3880 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3877 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg01) [ModuleForkPass]: Running lower_control
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg00) [ModuleForkPass]: Running lower_control
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8023 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg01) [ModuleForkPass]: Running lower_control
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg02) [ModuleForkPass]: Running lower_control
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to lower_control: modules=1 functions=1 allocs=1455 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to lower_control: modules=1 functions=1 allocs=1454 blocks=1 instructions=3880 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to lower_control: modules=1 functions=1 allocs=1453 blocks=1 instructions=3877 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to lower_control: modules=1 functions=1 allocs=1752 blocks=1 instructions=8023 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg00) [ModuleForkPass]: Running prefetch_scheduling_after_sched
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: Running prefetch_scheduling_after_sched
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to prefetch_scheduling_after_sched: modules=1 functions=1 allocs=1456 blocks=1 instructions=2592 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to prefetch_scheduling_after_sched: modules=1 functions=1 allocs=2134 blocks=1 instructions=8735 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg00) [ModuleForkPass]: prefetch_scheduling_after_sched finished after 0.061 seconds
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: prefetch_scheduling_after_sched finished after 0.000 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2592 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8735 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg00) [ModuleForkPass]: Running lower_control
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: Running lower_control
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to lower_control: modules=1 functions=1 allocs=1456 blocks=1 instructions=2592 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to lower_control: modules=1 functions=1 allocs=2134 blocks=1 instructions=8735 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [LowerControl]: EraseInterBbDeps removed 0 inter-BB deps
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [LowerControl]: EraseInterBbDeps removed 0 inter-BB deps
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [LowerControl]: EraseInterBbDeps removed 0 inter-BB deps
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [LowerControl]: EraseInterBbDeps removed 0 inter-BB deps
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg00) [ModuleForkPass]: lower_control finished after 0.037 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2592 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg00) [ModuleForkPass]: Running dep_reduction
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: Inputs to dep_reduction: modules=1 functions=1 allocs=1456 blocks=1 instructions=2592 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [DepReduction]: Start Dependency Reduction
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [DepReduction]: Cacheing dependencies for debug info
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg00) [ModuleForkPass]: lower_control finished after 0.100 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [LowerControl]: EraseInterBbDeps removed 0 inter-BB deps
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg00) [ModuleForkPass]: Running dep_reduction
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: Inputs to dep_reduction: modules=1 functions=1 allocs=1455 blocks=1 instructions=2589 Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [DepReduction]: Start Dependency Reduction
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [DepReduction]: Cacheing dependencies for debug info
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg01) [ModuleForkPass]: lower_control finished after 0.165 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3880 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg01) [ModuleForkPass]: Running dep_reduction
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [ModuleForkPass]: Inputs to dep_reduction: modules=1 functions=1 allocs=1454 blocks=1 instructions=3880 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [DepReduction]: Start Dependency Reduction
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [DepReduction]: Cacheing dependencies for debug info
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg01) [ModuleForkPass]: lower_control finished after 0.174 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3877 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg01) [ModuleForkPass]: Running dep_reduction
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: Inputs to dep_reduction: modules=1 functions=1 allocs=1453 blocks=1 instructions=3877 Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [DepReduction]: Start Dependency Reduction
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [DepReduction]: Cacheing dependencies for debug info
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [DepReduction]: Processing async instrs...
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [DepReduction]: Processing secondary edges per engine...
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [DepReduction]: Processing async instrs...
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [DepReduction]: Processing secondary edges per engine...
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [DepReduction]: Processing secondary edges per engine, Done. Num edges removed 2598
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [LowerControl]: EraseInterBbDeps removed 0 inter-BB deps
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [DepReduction]: Processing redundant descendants, Done. Num edges removed 2841
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [DepReduction]: Processing async instrs, Done. Num edges removed 2841
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [DepReduction]: Processing secondary edges per engine, Done. Num edges removed 2583
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg02) [ModuleForkPass]: lower_control finished after 0.264 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 337mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8023 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg02) [ModuleForkPass]: Running dep_reduction
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [ModuleForkPass]: Inputs to dep_reduction: modules=1 functions=1 allocs=1752 blocks=1 instructions=8023 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [DepReduction]: Start Dependency Reduction
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [DepReduction]: Cacheing dependencies for debug info
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [DepReduction]: Processing redundant descendants, Done. Num edges removed 2828
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [DepReduction]: Processing async instrs, Done. Num edges removed 2828
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: lower_control finished after 0.217 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 338mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8735 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg02) [ModuleForkPass]: Running dep_reduction
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [ModuleForkPass]: Inputs to dep_reduction: modules=1 functions=1 allocs=2134 blocks=1 instructions=8735 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [DepReduction]: Start Dependency Reduction
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [DepReduction]: Cacheing dependencies for debug info
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [DepReduction]: Processing async instrs...
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [DepReduction]: Processing secondary edges per engine...
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [DepReduction]: Processing async instrs...
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [DepReduction]: Processing secondary edges per engine...
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [DepReduction]: Num Async removed: 0
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [DepReduction]: Finished dependency reduction: 10683 removed, new total 1447
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [DepReduction]: Finished Dependency Reduction
|
|
2025-11-09T20:57:57Z USER 796 (nc00/sg00) [ModuleForkPass]: dep_reduction finished after 0.197 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 338mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1456 memory location(s), 1 block(s), and 2592 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [DepReduction]: Processing secondary edges per engine, Done. Num edges removed 3949
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [DepReduction]: Processing redundant descendants, Done. Num edges removed 4249
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [DepReduction]: Processing async instrs, Done. Num edges removed 4249
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [DepReduction]: Processing secondary edges per engine, Done. Num edges removed 3978
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [DepReduction]: Num Async removed: 0
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [DepReduction]: Finished dependency reduction: 10722 removed, new total 1441
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [DepReduction]: Finished Dependency Reduction
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg00) [ModuleForkPass]: dep_reduction finished after 0.233 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 339mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1455 memory location(s), 1 block(s), and 2589 instruction(s). Max writers: 34 Max Readers: 288
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [DepReduction]: Processing async instrs...
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [DepReduction]: Processing secondary edges per engine...
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [DepReduction]: Processing redundant descendants, Done. Num edges removed 4287
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg01) [DepReduction]: Processing async instrs, Done. Num edges removed 4287
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [DepReduction]: Processing secondary edges per engine, Done. Num edges removed 7092
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [DepReduction]: Num Async removed: 0
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [DepReduction]: Finished dependency reduction: 20444 removed, new total 1554
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [DepReduction]: Finished Dependency Reduction
|
|
2025-11-09T20:57:57Z USER 796 (nc01/sg01) [ModuleForkPass]: dep_reduction finished after 0.406 seconds
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: curr_vmrss: 341mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1453 memory location(s), 1 block(s), and 3877 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [DepReduction]: Processing async instrs...
|
|
2025-11-09T20:57:57Z INFO 796 (nc00/sg02) [DepReduction]: Processing secondary edges per engine...
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [DepReduction]: Processing redundant descendants, Done. Num edges removed 7528
|
|
2025-11-09T20:57:57Z INFO 796 (nc01/sg02) [DepReduction]: Processing async instrs, Done. Num edges removed 7528
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sg01) [DepReduction]: Num Async removed: 0
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sg01) [DepReduction]: Finished dependency reduction: 20763 removed, new total 1567
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sg01) [DepReduction]: Finished Dependency Reduction
|
|
2025-11-09T20:57:58Z USER 796 (nc00/sg01) [ModuleForkPass]: dep_reduction finished after 0.500 seconds
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sg01) [ModuleForkPass]: curr_vmrss: 341mb, ru_maxrss: 341mb (delta=0mb)
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sg01) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1454 memory location(s), 1 block(s), and 3880 instruction(s). Max writers: 34 Max Readers: 448
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sg02) [DepReduction]: Processing secondary edges per engine, Done. Num edges removed 7615
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sg02) [DepReduction]: Processing redundant descendants, Done. Num edges removed 8265
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sg02) [DepReduction]: Processing async instrs, Done. Num edges removed 8265
|
|
2025-11-09T20:57:58Z INFO 796 (nc01/sg02) [DepReduction]: Num Async removed: 0
|
|
2025-11-09T20:57:58Z INFO 796 (nc01/sg02) [DepReduction]: Finished dependency reduction: 37514 removed, new total 2168
|
|
2025-11-09T20:57:58Z INFO 796 (nc01/sg02) [DepReduction]: Finished Dependency Reduction
|
|
2025-11-09T20:57:58Z USER 796 (nc01/sg02) [ModuleForkPass]: dep_reduction finished after 0.629 seconds
|
|
2025-11-09T20:57:58Z INFO 796 (nc01/sg02) [ModuleForkPass]: curr_vmrss: 344mb, ru_maxrss: 343mb (delta=2mb)
|
|
2025-11-09T20:57:58Z INFO 796 (nc01/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 1752 memory location(s), 1 block(s), and 8023 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sg02) [DepReduction]: Num Async removed: 0
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sg02) [DepReduction]: Finished dependency reduction: 52257 removed, new total 2971
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sg02) [DepReduction]: Finished Dependency Reduction
|
|
2025-11-09T20:57:58Z USER 796 (nc00/sg02) [ModuleForkPass]: dep_reduction finished after 0.737 seconds
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sg02) [ModuleForkPass]: curr_vmrss: 344mb, ru_maxrss: 343mb (delta=2mb)
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sg02) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 2134 memory location(s), 1 block(s), and 8735 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:58Z USER 796 [ModuleForkPass]: Compilation status: Total modules: 6, Passed: 6, Failed: 0
|
|
2025-11-09T20:57:58Z USER 796 [BackendPassManager]: mod_parallel_pass finished after 1.063 seconds
|
|
2025-11-09T20:57:58Z INFO 796 [BackendPassManager]: curr_vmrss: 343mb, ru_maxrss: 343mb (delta=2mb)
|
|
2025-11-09T20:57:58Z USER 796 [BackendPassManager]: Running nc_parallel_pass
|
|
2025-11-09T20:57:58Z INFO 796 [BackendPassManager]: Inputs to nc_parallel_pass: modules=6 functions=6 allocs=9704 blocks=6 instructions=29696 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:58Z USER 796 (nc01) [CoreForkPass]: Running bir_linker
|
|
2025-11-09T20:57:58Z USER 796 (nc00) [CoreForkPass]: Running bir_linker
|
|
2025-11-09T20:57:58Z INFO 796 (nc01) [CoreForkPass]: Inputs to bir_linker: modules=3 functions=3 allocs=4660 blocks=3 instructions=14489 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:58Z INFO 796 (nc01/sgLnk) [BirLinker]: bir_linker cwd:
|
|
2025-11-09T20:57:58Z INFO 796 (nc00) [CoreForkPass]: Inputs to bir_linker: modules=3 functions=3 allocs=5044 blocks=3 instructions=15207 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sgLnk) [BirLinker]: bir_linker cwd:
|
|
2025-11-09T20:57:58Z INFO 796 (nc01/sgLnk) [BirLinker]: Num intermediates 86
|
|
2025-11-09T20:57:58Z INFO 796 (nc01/sgLnk) [BirLinker]: Num Module Definitions 3
|
|
2025-11-09T20:57:58Z INFO 796 (nc01/sgLnk) [BirLinker]: Linking to a call-graph structure
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sgLnk) [BirLinker]: Num intermediates 86
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sgLnk) [BirLinker]: Num Module Definitions 3
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sgLnk) [BirLinker]: Linking to a call-graph structure
|
|
2025-11-09T20:57:58Z INFO 796 (nc00/sgLnk) [BirLinker]: Added a new SpillReload Que qSPPIOParam0
|
|
2025-11-09T20:58:00Z INFO 796 (nc01/sgLnk) [BirLinker]: tensor_map verification successful.
|
|
2025-11-09T20:58:00Z INFO 796 (nc01/sgLnk) [BirLinker]: Writing updated tensor_map /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/neuronxcc-u_vl19it/nc01/sgLnk/sg00/tensor_map.json
|
|
2025-11-09T20:58:00Z INFO 796 (nc01/sgLnk) [BirLinker]: PostLink Stats: #MatMults 74959 #MatMult-Transposes 15303
|
|
2025-11-09T20:58:00Z INFO 796 (nc01/sgLnk) [BirLinker]: Total Intermediate MMTs 432 #out: 0 #inp: 432 #symmetric: 0
|
|
2025-11-09T20:58:00Z INFO 796 (nc01/sgLnk) [BirLinker]: Total Intermediate IOs with MMTs: 2 #out: 0 #inp: 2 #both: 0
|
|
2025-11-09T20:58:00Z INFO 796 (nc01/sgLnk) [BirLinker]: releasing pre-link modules
|
|
2025-11-09T20:58:00Z INFO 796 (nc00/sgLnk) [BirLinker]: tensor_map verification successful.
|
|
2025-11-09T20:58:00Z INFO 796 (nc00/sgLnk) [BirLinker]: Writing updated tensor_map /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/neuronxcc-u_vl19it/nc00/sgLnk/sg00/tensor_map.json
|
|
2025-11-09T20:58:00Z INFO 796 (nc00/sgLnk) [BirLinker]: PostLink Stats: #MatMults 75083 #MatMult-Transposes 15303
|
|
2025-11-09T20:58:00Z INFO 796 (nc00/sgLnk) [BirLinker]: Total Intermediate MMTs 432 #out: 0 #inp: 432 #symmetric: 0
|
|
2025-11-09T20:58:00Z INFO 796 (nc00/sgLnk) [BirLinker]: Total Intermediate IOs with MMTs: 2 #out: 0 #inp: 2 #both: 0
|
|
2025-11-09T20:58:00Z INFO 796 (nc00/sgLnk) [BirLinker]: releasing pre-link modules
|
|
2025-11-09T20:58:01Z INFO 796 (nc01/sgLnk) [BirLinker]: linking Done.
|
|
2025-11-09T20:58:01Z USER 796 (nc01) [CoreForkPass]: bir_linker finished after 3.423 seconds
|
|
2025-11-09T20:58:01Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 510mb, ru_maxrss: 509mb (delta=166mb)
|
|
2025-11-09T20:58:01Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14531 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:01Z USER 796 (nc01) [CoreForkPass]: Running postlnk_dma_report
|
|
2025-11-09T20:58:01Z INFO 796 (nc01) [CoreForkPass]: Inputs to postlnk_dma_report: modules=1 functions=4 allocs=5174 blocks=4 instructions=14531 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DMAReport]: DMA Report: Bytes loaded or saved 231145178, 67.5297% input load, 3.85597% output write, 28.6143% spill/reload
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: postlnk_dma_report finished after 0.063 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14531 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: Running report_stats
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Inputs to report_stats: modules=1 functions=4 allocs=5174 blocks=4 instructions=14531 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ReportStats]: Data Movement Statistics: main
|
|
┌─────────────┬──────┬───────┬───────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
└─────────────┴──────┴───────┴───────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ReportStats]: Data Movement Statistics: sg0000
|
|
┌─────────────────┬────────────────────────────┬───────┬────────────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
├─────────────────┼────────────────────────────┼───────┼────────────┤
|
|
│ DMACopy │ ExternalInput -> Internal │ 32 │ 4978638848 │
|
|
│ DMACopy │ Internal -> ExternalOutput │ 32 │ 134217728 │
|
|
│ DMACopy (Spill) │ Internal │ 32 │ 0 │
|
|
│ Load │ Const -> Internal │ 5 │ 57600 │
|
|
│ Load │ ExternalInput -> Internal │ 18 │ 5259780 │
|
|
│ Load │ Internal │ 92 │ 13631488 │
|
|
│ Save │ Internal │ 62 │ 9437184 │
|
|
│ Save │ Internal -> Output │ 18 │ 4718592 │
|
|
└─────────────────┴────────────────────────────┴───────┴────────────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ 2 │ 4 │
|
|
│ 4 │ 1 │
|
|
│ 32 │ 1 │
|
|
│ 64 │ 3 │
|
|
│ 256 │ 98 │
|
|
│ 512 │ 1 │
|
|
│ 1024 │ 40 │
|
|
│ 2048 │ 46 │
|
|
│ 4096 │ 33 │
|
|
│ 524288 │ 32 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ReportStats]: Data Movement Statistics: sg0001
|
|
┌─────────────────┬────────────────────────────┬───────┬───────────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
├─────────────────┼────────────────────────────┼───────┼───────────┤
|
|
│ DMACopy │ Input -> Internal │ 1 │ 12582912 │
|
|
│ DMACopy │ Internal -> ExternalOutput │ 32 │ 134217728 │
|
|
│ DMACopy (Spill) │ Internal │ 32 │ 0 │
|
|
│ Load │ Const -> Internal │ 3 │ 49152 │
|
|
│ Load │ ExternalInput -> Internal │ 104 │ 38806020 │
|
|
│ Load │ Input -> Internal │ 2 │ 524288 │
|
|
│ Load │ Internal │ 92 │ 13631488 │
|
|
│ Save │ Internal │ 68 │ 12582912 │
|
|
│ Save │ Internal -> Output │ 8 │ 4194304 │
|
|
└─────────────────┴────────────────────────────┴───────┴───────────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ 2 │ 4 │
|
|
│ 4 │ 1 │
|
|
│ 32 │ 2 │
|
|
│ 64 │ 2 │
|
|
│ 256 │ 97 │
|
|
│ 1024 │ 8 │
|
|
│ 2048 │ 76 │
|
|
│ 4096 │ 87 │
|
|
│ 524288 │ 32 │
|
|
│ 4194304 │ 3 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ReportStats]: Data Movement Statistics: sg0002
|
|
┌─────────────┬───────────────────────────┬───────┬───────────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
├─────────────┼───────────────────────────┼───────┼───────────┤
|
|
│ DMACopy │ Input -> Internal │ 1 │ 12582912 │
|
|
│ DMACopy │ Internal │ 2 │ 8388608 │
|
|
│ Load │ Const -> Internal │ 1 │ 32768 │
|
|
│ Load │ ExternalInput -> Internal │ 243 │ 111362060 │
|
|
│ Load │ Internal │ 24 │ 8391814 │
|
|
│ Save │ Internal │ 168 │ 8465728 │
|
|
└─────────────┴───────────────────────────┴───────┴───────────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ 2 │ 2 │
|
|
│ 4 │ 4 │
|
|
│ 32 │ 2 │
|
|
│ 128 │ 2 │
|
|
│ 192 │ 1 │
|
|
│ 256 │ 1 │
|
|
│ 512 │ 154 │
|
|
│ 1024 │ 1 │
|
|
│ 2048 │ 46 │
|
|
│ 4096 │ 224 │
|
|
│ 4194304 │ 3 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ReportStats]: MM Stats: #MatMults 10167 #MatMult-Transposes 3655
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ReportStats]: IO Tensor size combined: 1880931372
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ReportStats]: IO Tensor Statistics:
|
|
┌────────────────────┬───────────────┬──────────┬──────────────┐
|
|
│ Largest IO Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├────────────────────┼───────────────┼──────────┼──────────────┤
|
|
│ input60_sg0000 │ ExternalInput │ bfloat16 │ 155582464 │
|
|
│ input369_sg0002 │ ExternalInput │ bfloat16 │ 155582464 │
|
|
│ input60 │ ExternalInput │ bfloat16 │ 155582464 │
|
|
│ input369 │ ExternalInput │ bfloat16 │ 155582464 │
|
|
│ input126 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input115 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input104 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input137 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input93 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input159 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
└────────────────────┴───────────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ReportStats]: Large (Internal) Tensor Statistics:
|
|
┌─────────────────┬───────────────────┬──────────┬──────────────┐
|
|
│ Largest Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├─────────────────┼───────────────────┼──────────┼──────────────┤
|
|
│ intermediate3 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate0 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate20 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate11 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate5 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate14 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate26 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate23 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate17 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate8 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
└─────────────────┴───────────────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: report_stats finished after 0.028 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14531 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: Running coloring_allocator_dram_post_lnk
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Inputs to coloring_allocator_dram_post_lnk: modules=1 functions=4 allocs=5174 blocks=4 instructions=14531 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: allocating spills in DRAM post_link mode for address space Local
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: reserved space = 0 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: spill space = 0 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: aligned spill space = 0 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: renumber locations
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: size = 0
|
|
2025-11-09T20:58:02Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:58:02Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: Num intervals 0 Num locations 0
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: simplify interference graph
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: initialize low and high
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: lo = 0
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: hi = 0
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: total = 0
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: simplify
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: new candidates = 0
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: Already used DRAM hwm: 48234496
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: select ranges
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: CC buffer size limit 524288000
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: allreduce_dram_hwm 48234496
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: Real CC buffer size 48234496
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: DRAM hwm after allocation: 48234496
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: DRAM allocation successful
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: coloring_allocator_dram_post_lnk finished after 0.171 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14531 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: Running coloring_allocator_dram_shared_post_lnk
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Inputs to coloring_allocator_dram_shared_post_lnk: modules=1 functions=4 allocs=5174 blocks=4 instructions=14531 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: allocating spills in DRAM post_link mode for address space Shared
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: reserved space = 0 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: spill space = 470810680 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: aligned spill space = 470925312 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [DRAM_Allocator]: Skipping shared tensor allocations on core 1, marking as remoteLocalTarget instead
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: coloring_allocator_dram_shared_post_lnk finished after 0.098 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14531 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [BirLinker]: linking Done.
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: bir_linker finished after 4.000 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=166mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15249 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: Running postlnk_dma_report
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Inputs to postlnk_dma_report: modules=1 functions=4 allocs=5558 blocks=4 instructions=15249 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DMAReport]: DMA Report: Bytes loaded or saved 231504365, 67.4994% input load, 3.84999% output write, 28.6506% spill/reload
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: postlnk_dma_report finished after 0.013 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15249 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: Running report_stats
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Inputs to report_stats: modules=1 functions=4 allocs=5558 blocks=4 instructions=15249 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ReportStats]: Data Movement Statistics: main
|
|
┌─────────────┬──────┬───────┬───────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
└─────────────┴──────┴───────┴───────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ReportStats]: Data Movement Statistics: sg0000
|
|
┌─────────────────┬────────────────────────────┬───────┬────────────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
├─────────────────┼────────────────────────────┼───────┼────────────┤
|
|
│ DMACopy │ ExternalInput -> Internal │ 32 │ 4978638848 │
|
|
│ DMACopy │ Internal -> ExternalOutput │ 32 │ 134217728 │
|
|
│ DMACopy │ Internal -> Output │ 1 │ 16777216 │
|
|
│ DMACopy (Spill) │ Internal │ 32 │ 0 │
|
|
│ Load │ Const -> Internal │ 5 │ 57600 │
|
|
│ Load │ ExternalInput -> Internal │ 18 │ 5259780 │
|
|
│ Load │ Internal │ 92 │ 13631488 │
|
|
│ Save │ Internal │ 62 │ 9437184 │
|
|
│ Save │ Internal -> Output │ 19 │ 4718594 │
|
|
└─────────────────┴────────────────────────────┴───────┴────────────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ 2 │ 5 │
|
|
│ 4 │ 1 │
|
|
│ 32 │ 1 │
|
|
│ 64 │ 3 │
|
|
│ 256 │ 98 │
|
|
│ 512 │ 1 │
|
|
│ 1024 │ 40 │
|
|
│ 2048 │ 46 │
|
|
│ 4096 │ 33 │
|
|
│ 524288 │ 32 │
|
|
│ 8388608 │ 2 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ReportStats]: Data Movement Statistics: sg0001
|
|
┌─────────────────┬────────────────────────────┬───────┬───────────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
├─────────────────┼────────────────────────────┼───────┼───────────┤
|
|
│ DMACopy │ Input -> Internal │ 1 │ 12582912 │
|
|
│ DMACopy │ Internal -> ExternalOutput │ 32 │ 134217728 │
|
|
│ DMACopy │ Internal -> Output │ 1 │ 16777216 │
|
|
│ DMACopy (Spill) │ Internal │ 32 │ 0 │
|
|
│ Load │ Const -> Internal │ 3 │ 49152 │
|
|
│ Load │ ExternalInput -> Internal │ 104 │ 38806020 │
|
|
│ Load │ Input -> Internal │ 2 │ 524288 │
|
|
│ Load │ Internal │ 92 │ 13631488 │
|
|
│ Save │ Internal │ 68 │ 12582912 │
|
|
│ Save │ Internal -> Output │ 9 │ 4194306 │
|
|
└─────────────────┴────────────────────────────┴───────┴───────────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ 2 │ 5 │
|
|
│ 4 │ 1 │
|
|
│ 32 │ 2 │
|
|
│ 64 │ 2 │
|
|
│ 256 │ 97 │
|
|
│ 1024 │ 8 │
|
|
│ 2048 │ 76 │
|
|
│ 4096 │ 87 │
|
|
│ 524288 │ 32 │
|
|
│ 4194304 │ 3 │
|
|
│ 8388608 │ 2 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ReportStats]: Data Movement Statistics: sg0002
|
|
┌─────────────┬────────────────────────────┬───────┬───────────┐
|
|
│ Instruction │ Kind │ Count │ Bytes │
|
|
├─────────────┼────────────────────────────┼───────┼───────────┤
|
|
│ DMACopy │ Input -> Internal │ 1 │ 12582912 │
|
|
│ DMACopy │ Internal │ 6 │ 8396800 │
|
|
│ Load │ Const -> Internal │ 8 │ 201096 │
|
|
│ Load │ ExternalInput -> Internal │ 244 │ 111366156 │
|
|
│ Load │ Internal │ 36 │ 8561158 │
|
|
│ Save │ Internal │ 184 │ 8483139 │
|
|
│ Save │ Internal -> ExternalOutput │ 1 │ 4 │
|
|
└─────────────┴────────────────────────────┴───────┴───────────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ReportStats]:
|
|
┌─────────────────────┬───────┐
|
|
│ Bytes per partition │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ 1 │ 1 │
|
|
│ 2 │ 3 │
|
|
│ 4 │ 9 │
|
|
│ 8 │ 2 │
|
|
│ 32 │ 9 │
|
|
│ 128 │ 6 │
|
|
│ 192 │ 1 │
|
|
│ 256 │ 1 │
|
|
│ 512 │ 154 │
|
|
│ 1024 │ 17 │
|
|
│ 2048 │ 46 │
|
|
│ 4096 │ 225 │
|
|
│ 4748 │ 2 │
|
|
│ 4194304 │ 3 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ReportStats]: MM Stats: #MatMults 10291 #MatMult-Transposes 3655
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ReportStats]: IO Tensor size combined: 1880931372
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ReportStats]: IO Tensor Statistics:
|
|
┌────────────────────┬───────────────┬──────────┬──────────────┐
|
|
│ Largest IO Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├────────────────────┼───────────────┼──────────┼──────────────┤
|
|
│ input60_sg0000 │ ExternalInput │ bfloat16 │ 155582464 │
|
|
│ input369_sg0002 │ ExternalInput │ bfloat16 │ 155582464 │
|
|
│ input60 │ ExternalInput │ bfloat16 │ 155582464 │
|
|
│ input369 │ ExternalInput │ bfloat16 │ 155582464 │
|
|
│ input126 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input115 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input104 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input137 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input93 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
│ input159 │ ExternalInput │ bfloat16 │ 6291456 │
|
|
└────────────────────┴───────────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ReportStats]: Large (Internal) Tensor Statistics:
|
|
┌─────────────────┬───────────────────┬──────────┬──────────────┐
|
|
│ Largest Tensors │ Kind │ Src Type │ Size (Bytes) │
|
|
├─────────────────┼───────────────────┼──────────┼──────────────┤
|
|
│ intermediate3 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate0 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate20 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate11 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate5 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate14 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate26 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate23 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate17 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
│ intermediate8 │ InternalInterface │ bfloat16 │ 8388608 │
|
|
└─────────────────┴───────────────────┴──────────┴──────────────┘
|
|
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: report_stats finished after 0.021 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15249 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: Running coloring_allocator_dram_post_lnk
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Inputs to coloring_allocator_dram_post_lnk: modules=1 functions=4 allocs=5558 blocks=4 instructions=15249 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: allocating spills in DRAM post_link mode for address space Local
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: reserved space = 0 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: spill space = 0 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: aligned spill space = 0 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: renumber locations
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: size = 0
|
|
2025-11-09T20:58:02Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:58:02Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: Num intervals 0 Num locations 0
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: simplify interference graph
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: initialize low and high
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: lo = 0
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: hi = 0
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: total = 0
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: simplify
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: new candidates = 0
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: Already used DRAM hwm: 48234496
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: select ranges
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: CC buffer size limit 524288000
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: allreduce_dram_hwm 48234496
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: Real CC buffer size 48234496
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: DRAM hwm after allocation: 48234496
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: DRAM allocation successful
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: coloring_allocator_dram_post_lnk finished after 0.080 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15249 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: Running coloring_allocator_dram_shared_post_lnk
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Inputs to coloring_allocator_dram_shared_post_lnk: modules=1 functions=4 allocs=5558 blocks=4 instructions=15249 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: allocating spills in DRAM post_link mode for address space Shared
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: reserved space = 0 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: spill space = 470810680 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: aligned spill space = 470925312 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: dram space = 107374182400 bytes
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: renumber locations
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: size = 86
|
|
2025-11-09T20:58:02Z INFO 796 []: find first defs for local
|
|
2025-11-09T20:58:02Z INFO 796 []: find first defs for global
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: Num intervals 86 Num locations 86
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: IntervalTree Build Done
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: info.neighbors init Done
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: IntervalTree readback Done
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: simplify interference graph
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: initialize low and high
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: lo = 86
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: hi = 0
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: total = 86
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: simplify
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: new candidates = 0
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: Already used DRAM hwm: 48234496
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: select ranges
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: CC buffer size limit 524288000
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: allreduce_dram_hwm 48234496
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: Real CC buffer size 48234496
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: DRAM hwm after allocation: 82849792
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [DRAM_Allocator]: DRAM allocation successful
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: coloring_allocator_dram_shared_post_lnk finished after 0.065 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15249 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 [CoreForkPass]: Compilation status: Total modules: 2, Passed: 6, Failed: 0
|
|
2025-11-09T20:58:02Z USER 796 [BackendPassManager]: nc_parallel_pass finished after 4.205 seconds
|
|
2025-11-09T20:58:02Z INFO 796 [BackendPassManager]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=166mb)
|
|
2025-11-09T20:58:02Z USER 796 [BackendPassManager]: Running subgraph_parallel_pass
|
|
2025-11-09T20:58:02Z INFO 796 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=2 functions=8 allocs=10732 blocks=8 instructions=29780 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (sg00) [SubgraphForkPass]: Running sync_shared_allocations
|
|
2025-11-09T20:58:02Z INFO 796 (sg00) [SubgraphForkPass]: Inputs to sync_shared_allocations: modules=2 functions=8 allocs=10732 blocks=8 instructions=29780 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (sg00) [SubgraphForkPass]: sync_shared_allocations finished after 0.004 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (sg00) [SubgraphForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (sg00) [SubgraphForkPass]: Output has 2 module(s), 8 function(s), 10732 memory location(s), 8 block(s), and 29780 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 [SubgraphForkPass]: Compilation status: Total subgraphs: 1, Passed: 1, Failed: 0
|
|
2025-11-09T20:58:02Z USER 796 [BackendPassManager]: subgraph_parallel_pass finished after 0.009 seconds
|
|
2025-11-09T20:58:02Z INFO 796 [BackendPassManager]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z USER 796 [BackendPassManager]: Running nc_parallel_pass
|
|
2025-11-09T20:58:02Z INFO 796 [BackendPassManager]: Inputs to nc_parallel_pass: modules=2 functions=8 allocs=10732 blocks=8 instructions=29780 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: Running memory_analysis_after_coloring_allocator_dram_post_lnk
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: Running memory_analysis_after_coloring_allocator_dram_post_lnk
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Inputs to memory_analysis_after_coloring_allocator_dram_post_lnk: modules=1 functions=4 allocs=5558 blocks=4 instructions=15249 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Inputs to memory_analysis_after_coloring_allocator_dram_post_lnk: modules=1 functions=4 allocs=5174 blocks=4 instructions=14531 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: memory_analysis_after_coloring_allocator_dram_post_lnk finished after 0.100 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15249 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: Running lower_dynamic_dma
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Inputs to lower_dynamic_dma: modules=1 functions=4 allocs=5558 blocks=4 instructions=15249 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: lower_dynamic_dma finished after 0.011 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15249 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: Running legalize_dynamic_dma
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Inputs to legalize_dynamic_dma: modules=1 functions=4 allocs=5558 blocks=4 instructions=15249 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: memory_analysis_after_coloring_allocator_dram_post_lnk finished after 0.116 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14531 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: Running lower_dynamic_dma
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Inputs to lower_dynamic_dma: modules=1 functions=4 allocs=5174 blocks=4 instructions=14531 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [LegalizeDynamicDMA]: Legalize Dynamic DMA scanned 1 DGE instructions
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [LegalizeDynamicDMA]: After Legalize Dynamic DMA, 1 DGE instructions were scanned
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [LegalizeDynamicDMA]:
|
|
┌───────────┬───────────────────────────────┬────────────────────────────┐
|
|
│ Sub-Pass │ Illegal Instructions Detected │ New Instructions Generated │
|
|
├───────────┼───────────────────────────────┼────────────────────────────┤
|
|
│ Peeling │ 0 │ 0 │
|
|
│ Unrolling │ 0 │ 0 │
|
|
│ Splitting │ 0 │ 0 │
|
|
└───────────┴───────────────────────────────┴────────────────────────────┘
|
|
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: legalize_dynamic_dma finished after 0.015 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15249 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: Running optimize_queue_switch
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Inputs to optimize_queue_switch: modules=1 functions=4 allocs=5558 blocks=4 instructions=15249 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc00/sgLnk) [OptimizeQueueSwitch]: Optimize queue switch has replaced 7 total SQI Instructions with RQI
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: optimize_queue_switch finished after 0.003 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15256 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc00) [CoreForkPass]: Running lower_dma
|
|
2025-11-09T20:58:02Z INFO 796 (nc00) [CoreForkPass]: Inputs to lower_dma: modules=1 functions=4 allocs=5558 blocks=4 instructions=15256 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: lower_dynamic_dma finished after 0.017 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14531 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: Running legalize_dynamic_dma
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Inputs to legalize_dynamic_dma: modules=1 functions=4 allocs=5174 blocks=4 instructions=14531 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [LegalizeDynamicDMA]: Legalize Dynamic DMA scanned 1 DGE instructions
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [LegalizeDynamicDMA]: After Legalize Dynamic DMA, 1 DGE instructions were scanned
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [LegalizeDynamicDMA]:
|
|
┌───────────┬───────────────────────────────┬────────────────────────────┐
|
|
│ Sub-Pass │ Illegal Instructions Detected │ New Instructions Generated │
|
|
├───────────┼───────────────────────────────┼────────────────────────────┤
|
|
│ Peeling │ 0 │ 0 │
|
|
│ Unrolling │ 0 │ 0 │
|
|
│ Splitting │ 0 │ 0 │
|
|
└───────────┴───────────────────────────────┴────────────────────────────┘
|
|
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: legalize_dynamic_dma finished after 0.052 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14531 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: Running optimize_queue_switch
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Inputs to optimize_queue_switch: modules=1 functions=4 allocs=5174 blocks=4 instructions=14531 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z INFO 796 (nc01/sgLnk) [OptimizeQueueSwitch]: Optimize queue switch has replaced 7 total SQI Instructions with RQI
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: optimize_queue_switch finished after 0.004 seconds
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14538 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:02Z USER 796 (nc01) [CoreForkPass]: Running lower_dma
|
|
2025-11-09T20:58:02Z INFO 796 (nc01) [CoreForkPass]: Inputs to lower_dma: modules=1 functions=4 allocs=5174 blocks=4 instructions=14538 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [LowerDMA]: lower_dma metrics start
|
|
IO
|
|
Copy (DGE/DMA)
|
|
128 partition : 3152/3152 (100% DGE)
|
|
power-of-2 partition : 3181/3244 (98.058% DGE)
|
|
> 3 dimensional : 0/0
|
|
non-integer desc size : 0/0
|
|
total : 3182/3245 (98.0585% DGE)
|
|
Cast (DGE/DMA)
|
|
128 partition : 57/57 (100% DGE)
|
|
power-of-2 partition : 169/170 (99.4118% DGE)
|
|
> 3 dimensional : 0/0
|
|
non-integer desc size : 0/0
|
|
total : 169/170 (99.4118% DGE)
|
|
Spill/Reload
|
|
Copy (DGE/DMA)
|
|
128 partition : 4597/4597 (100% DGE)
|
|
power-of-2 partition : 4597/4788 (96.0109% DGE)
|
|
> 3 dimensional : 0/0
|
|
non-integer desc size : 0/0
|
|
total : 4597/4788 (96.0109% DGE)
|
|
Cast (DGE/DMA)
|
|
128 partition : 0/0
|
|
power-of-2 partition : 0/2 (0% DGE)
|
|
> 3 dimensional : 0/0
|
|
non-integer desc size : 0/0
|
|
total : 0/2 (0% DGE)
|
|
CopyMode
|
|
CCE : 29
|
|
Transpose : 896
|
|
Replicate : 0
|
|
Dynamic (DGE/DMA)
|
|
scalar : 1/1 (100% DGE)
|
|
vector : 930/930 (100% DGE)
|
|
Opcode
|
|
ReadVarAddr : 0
|
|
IndirectLoad : 0
|
|
IndirectSave : 0
|
|
IndirectSaveAccumulate : 0
|
|
DstReduceDGE : 0
|
|
lower_dma metrics end
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: lower_dma finished after 0.263 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15256 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: Running expand_all_engine
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Inputs to expand_all_engine: modules=1 functions=4 allocs=5558 blocks=4 instructions=15256 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: expand_all_engine finished after 0.078 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15256 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: Running alloc_semaphores
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Inputs to alloc_semaphores: modules=1 functions=4 allocs=5558 blocks=4 instructions=15256 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z INFO 796 (nc01/sgLnk) [LowerDMA]: lower_dma metrics start
|
|
IO
|
|
Copy (DGE/DMA)
|
|
128 partition : 3152/3152 (100% DGE)
|
|
power-of-2 partition : 3153/3186 (98.9642% DGE)
|
|
> 3 dimensional : 0/0
|
|
non-integer desc size : 0/0
|
|
total : 3154/3187 (98.9645% DGE)
|
|
Cast (DGE/DMA)
|
|
128 partition : 57/57 (100% DGE)
|
|
power-of-2 partition : 169/170 (99.4118% DGE)
|
|
> 3 dimensional : 0/0
|
|
non-integer desc size : 0/0
|
|
total : 169/170 (99.4118% DGE)
|
|
Spill/Reload
|
|
Copy (DGE/DMA)
|
|
128 partition : 4592/4592 (100% DGE)
|
|
power-of-2 partition : 4592/4753 (96.6127% DGE)
|
|
> 3 dimensional : 0/0
|
|
non-integer desc size : 0/0
|
|
total : 4592/4753 (96.6127% DGE)
|
|
Cast (DGE/DMA)
|
|
128 partition : 0/0
|
|
power-of-2 partition : 0/0
|
|
> 3 dimensional : 0/0
|
|
non-integer desc size : 0/0
|
|
total : 0/0
|
|
CopyMode
|
|
CCE : 29
|
|
Transpose : 896
|
|
Replicate : 0
|
|
Dynamic (DGE/DMA)
|
|
scalar : 1/1 (100% DGE)
|
|
vector : 928/928 (100% DGE)
|
|
Opcode
|
|
ReadVarAddr : 0
|
|
IndirectLoad : 0
|
|
IndirectSave : 0
|
|
IndirectSaveAccumulate : 0
|
|
DstReduceDGE : 0
|
|
lower_dma metrics end
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: lower_dma finished after 0.306 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14538 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: Running expand_all_engine
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Inputs to expand_all_engine: modules=1 functions=4 allocs=5174 blocks=4 instructions=14538 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: expand_all_engine finished after 0.109 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14538 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: Running alloc_semaphores
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Inputs to alloc_semaphores: modules=1 functions=4 allocs=5174 blocks=4 instructions=14538 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: alloc_semaphores finished after 0.144 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15256 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: Running expand_inst_late
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Inputs to expand_inst_late: modules=1 functions=4 allocs=5558 blocks=4 instructions=15256 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: alloc_semaphores finished after 0.200 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14538 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: Running expand_inst_late
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Inputs to expand_inst_late: modules=1 functions=4 allocs=5174 blocks=4 instructions=14538 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: expand_inst_late finished after 0.357 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15425 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: Running seq_inst_opt
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Inputs to seq_inst_opt: modules=1 functions=4 allocs=5558 blocks=4 instructions=15425 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [SeqInstOpt]: Removing 0 unnecessary InstRegisterMove instruction(s) from Block1
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [SeqInstOpt]: Removing 94 unnecessary InstRegisterMove instruction(s) from Block1
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [SeqInstOpt]: Removing 63 unnecessary InstRegisterMove instruction(s) from Block1
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [SeqInstOpt]: Removing 1 unnecessary InstRegisterMove instruction(s) from Block1
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: seq_inst_opt finished after 0.020 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 15267 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: Running lower_sync
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Inputs to lower_sync: modules=1 functions=4 allocs=5558 blocks=4 instructions=15267 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: lower_sync finished after 0.064 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 16315 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: Running lower_act
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Inputs to lower_act: modules=1 functions=4 allocs=5558 blocks=4 instructions=16315 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: lower_act finished after 0.026 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 16333 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: Running lower_dve
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Inputs to lower_dve: modules=1 functions=4 allocs=5558 blocks=4 instructions=16333 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [LowerDVE]: Loading DVE opcodes table dve_info.json from /opt/conda/lib/python3.11/site-packages/neuronxcc/dve/dve_bin_gen3/dve_info.json
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: expand_inst_late finished after 0.312 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 407mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14705 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: Running seq_inst_opt
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Inputs to seq_inst_opt: modules=1 functions=4 allocs=5174 blocks=4 instructions=14705 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z INFO 796 (nc01/sgLnk) [SeqInstOpt]: Removing 0 unnecessary InstRegisterMove instruction(s) from Block1
|
|
2025-11-09T20:58:03Z INFO 796 (nc01/sgLnk) [SeqInstOpt]: Removing 94 unnecessary InstRegisterMove instruction(s) from Block1
|
|
2025-11-09T20:58:03Z INFO 796 (nc01/sgLnk) [SeqInstOpt]: Removing 63 unnecessary InstRegisterMove instruction(s) from Block1
|
|
2025-11-09T20:58:03Z INFO 796 (nc01/sgLnk) [SeqInstOpt]: Removing 0 unnecessary InstRegisterMove instruction(s) from Block1
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: seq_inst_opt finished after 0.047 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 409mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 14548 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: Running lower_sync
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Inputs to lower_sync: modules=1 functions=4 allocs=5174 blocks=4 instructions=14548 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: lower_sync finished after 0.036 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 410mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 15437 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: Running lower_act
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Inputs to lower_act: modules=1 functions=4 allocs=5174 blocks=4 instructions=15437 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: lower_act finished after 0.053 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 410mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 15454 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc01) [CoreForkPass]: Running lower_dve
|
|
2025-11-09T20:58:03Z INFO 796 (nc01) [CoreForkPass]: Inputs to lower_dve: modules=1 functions=4 allocs=5174 blocks=4 instructions=15454 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z INFO 796 (nc01/sgLnk) [LowerDVE]: Loading DVE opcodes table dve_info.json from /opt/conda/lib/python3.11/site-packages/neuronxcc/dve/dve_bin_gen3/dve_info.json
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: lower_dve finished after 0.192 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 411mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 16333 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: Running lower_ap
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Inputs to lower_ap: modules=1 functions=4 allocs=5558 blocks=4 instructions=16333 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: lower_ap finished after 0.024 seconds
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 411mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 16333 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z USER 796 (nc00) [CoreForkPass]: Running coloring_allocator_reg
|
|
2025-11-09T20:58:03Z INFO 796 (nc00) [CoreForkPass]: Inputs to coloring_allocator_reg: modules=1 functions=4 allocs=5558 blocks=4 instructions=16333 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [REG_Allocator]: allocating REG
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [REG_Allocator]: main loop iteration 1
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [REG_Allocator]: allocating REG
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [REG_Allocator]: main loop iteration 1
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [REG_Allocator]: renumber registers
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [REG_Allocator]: size = 4
|
|
2025-11-09T20:58:03Z INFO 796 []: find first defs for local reg
|
|
2025-11-09T20:58:03Z INFO 796 []: find first defs for global reg
|
|
2025-11-09T20:58:03Z INFO 796 (nc00/sgLnk) [REG_Allocator]: live range analysis
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: find costs
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: simplify interference graph
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: initialize low and high
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: lo = 4
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: hi = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: inf = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: total = 4
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: simplify
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: new candidates = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: select ranges
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: no more spills
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: REG score = 0 (lower is better)
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: Spilling from REG cost about 0 cycles
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: 0% REG utilization after allocation
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: allocating REG
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: main loop iteration 1
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: renumber registers
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: size = 3
|
|
2025-11-09T20:58:04Z INFO 796 []: find first defs for local reg
|
|
2025-11-09T20:58:04Z INFO 796 []: find first defs for global reg
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: live range analysis
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: find costs
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: simplify interference graph
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: initialize low and high
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: lo = 3
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: hi = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: inf = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: total = 3
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: simplify
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: new candidates = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: select ranges
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: no more spills
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: REG score = 0 (lower is better)
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: Spilling from REG cost about 0 cycles
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: 0% REG utilization after allocation
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: allocating REG
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: main loop iteration 1
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: renumber registers
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: size = 5
|
|
2025-11-09T20:58:04Z INFO 796 []: find first defs for local reg
|
|
2025-11-09T20:58:04Z INFO 796 []: find first defs for global reg
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: live range analysis
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: find costs
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: simplify interference graph
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: initialize low and high
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: lo = 5
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: hi = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: inf = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: total = 5
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: simplify
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: new candidates = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: select ranges
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: no more spills
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: REG score = 0 (lower is better)
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: Spilling from REG cost about 0 cycles
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [REG_Allocator]: 0% REG utilization after allocation
|
|
2025-11-09T20:58:04Z USER 796 (nc00) [CoreForkPass]: coloring_allocator_reg finished after 0.176 seconds
|
|
2025-11-09T20:58:04Z INFO 796 (nc00) [CoreForkPass]: curr_vmrss: 412mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:04Z INFO 796 (nc00) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 16333 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 (nc01) [CoreForkPass]: lower_dve finished after 0.249 seconds
|
|
2025-11-09T20:58:04Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 412mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:04Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 15454 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 (nc01) [CoreForkPass]: Running lower_ap
|
|
2025-11-09T20:58:04Z INFO 796 (nc01) [CoreForkPass]: Inputs to lower_ap: modules=1 functions=4 allocs=5174 blocks=4 instructions=15454 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 (nc01) [CoreForkPass]: lower_ap finished after 0.069 seconds
|
|
2025-11-09T20:58:04Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 412mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:04Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 15454 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 (nc01) [CoreForkPass]: Running coloring_allocator_reg
|
|
2025-11-09T20:58:04Z INFO 796 (nc01) [CoreForkPass]: Inputs to coloring_allocator_reg: modules=1 functions=4 allocs=5174 blocks=4 instructions=15454 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: allocating REG
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: main loop iteration 1
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: allocating REG
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: main loop iteration 1
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: renumber registers
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: size = 4
|
|
2025-11-09T20:58:04Z INFO 796 []: find first defs for local reg
|
|
2025-11-09T20:58:04Z INFO 796 []: find first defs for global reg
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: live range analysis
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: find costs
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: simplify interference graph
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: initialize low and high
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: lo = 4
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: hi = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: inf = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: total = 4
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: simplify
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: new candidates = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: select ranges
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: no more spills
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: REG score = 0 (lower is better)
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: Spilling from REG cost about 0 cycles
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: 0% REG utilization after allocation
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: allocating REG
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: main loop iteration 1
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: renumber registers
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: size = 3
|
|
2025-11-09T20:58:04Z INFO 796 []: find first defs for local reg
|
|
2025-11-09T20:58:04Z INFO 796 []: find first defs for global reg
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: live range analysis
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: find costs
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: simplify interference graph
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: initialize low and high
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: lo = 3
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: hi = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: inf = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: total = 3
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: simplify
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: new candidates = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: select ranges
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: no more spills
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: REG score = 0 (lower is better)
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: Spilling from REG cost about 0 cycles
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: 0% REG utilization after allocation
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: Allocating functions
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [ColoringAllocator::Rep]: linearize and check
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: allocating REG
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: main loop iteration 1
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: renumber registers
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: size = 4
|
|
2025-11-09T20:58:04Z INFO 796 []: find first defs for local reg
|
|
2025-11-09T20:58:04Z INFO 796 []: find first defs for global reg
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: live range analysis
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: find costs
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: simplify interference graph
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: initialize low and high
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: lo = 4
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: hi = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: inf = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: total = 4
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: simplify
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: new candidates = 0
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: select ranges
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: no more spills
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: REG score = 0 (lower is better)
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: Spilling from REG cost about 0 cycles
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [REG_Allocator]: 0% REG utilization after allocation
|
|
2025-11-09T20:58:04Z USER 796 (nc01) [CoreForkPass]: coloring_allocator_reg finished after 0.132 seconds
|
|
2025-11-09T20:58:04Z INFO 796 (nc01) [CoreForkPass]: curr_vmrss: 412mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:04Z INFO 796 (nc01) [CoreForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 15454 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 [CoreForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0
|
|
2025-11-09T20:58:04Z USER 796 [BackendPassManager]: nc_parallel_pass finished after 1.780 seconds
|
|
2025-11-09T20:58:04Z INFO 796 [BackendPassManager]: curr_vmrss: 412mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:04Z USER 796 [BackendPassManager]: Running vnc_remote_addr_map
|
|
2025-11-09T20:58:04Z INFO 796 [BackendPassManager]: Inputs to vnc_remote_addr_map: modules=2 functions=8 allocs=10732 blocks=8 instructions=31787 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 [BackendPassManager]: vnc_remote_addr_map finished after 0.008 seconds
|
|
2025-11-09T20:58:04Z INFO 796 [BackendPassManager]: curr_vmrss: 412mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:04Z INFO 796 [BackendPassManager]: Output has 2 module(s), 8 function(s), 10732 memory location(s), 8 block(s), and 31787 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 [BackendPassManager]: Running vnc_link
|
|
2025-11-09T20:58:04Z INFO 796 [BackendPassManager]: Inputs to vnc_link: modules=2 functions=8 allocs=10732 blocks=8 instructions=31787 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z INFO 796 [VncLink]: Found 0 remote updates
|
|
2025-11-09T20:58:04Z USER 796 [BackendPassManager]: vnc_link finished after 0.002 seconds
|
|
2025-11-09T20:58:04Z INFO 796 [BackendPassManager]: curr_vmrss: 412mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:04Z INFO 796 [BackendPassManager]: Output has 2 module(s), 8 function(s), 10732 memory location(s), 8 block(s), and 31787 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 [BackendPassManager]: Running mod_parallel_pass
|
|
2025-11-09T20:58:04Z INFO 796 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=8 allocs=10732 blocks=8 instructions=31787 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 (nc00/sgLnk) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=4 allocs=5558 blocks=4 instructions=16333 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 (nc01/sgLnk) [ModuleForkPass]: Running birverifier
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=4 allocs=5174 blocks=4 instructions=15454 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 (nc01/sgLnk) [ModuleForkPass]: birverifier finished after 0.304 seconds
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [ModuleForkPass]: curr_vmrss: 412mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:04Z INFO 796 (nc01/sgLnk) [ModuleForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 15454 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 (nc00/sgLnk) [ModuleForkPass]: birverifier finished after 0.499 seconds
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [ModuleForkPass]: curr_vmrss: 412mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:04Z INFO 796 (nc00/sgLnk) [ModuleForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 16333 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0
|
|
2025-11-09T20:58:04Z USER 796 [BackendPassManager]: mod_parallel_pass finished after 0.504 seconds
|
|
2025-11-09T20:58:04Z INFO 796 [BackendPassManager]: curr_vmrss: 412mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:04Z USER 796 [BackendPassManager]: Running subgraph_parallel_pass
|
|
2025-11-09T20:58:04Z INFO 796 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=2 functions=8 allocs=10732 blocks=8 instructions=31787 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:04Z USER 796 (sg00) [SubgraphForkPass]: Running lnc_verifier
|
|
2025-11-09T20:58:04Z INFO 796 (sg00) [SubgraphForkPass]: Inputs to lnc_verifier: modules=2 functions=8 allocs=10732 blocks=8 instructions=31787 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:05Z USER 796 (sg00) [SubgraphForkPass]: lnc_verifier finished after 0.045 seconds
|
|
2025-11-09T20:58:05Z INFO 796 (sg00) [SubgraphForkPass]: curr_vmrss: 412mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:05Z INFO 796 (sg00) [SubgraphForkPass]: Output has 2 module(s), 8 function(s), 10732 memory location(s), 8 block(s), and 31787 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:05Z USER 796 [SubgraphForkPass]: Compilation status: Total subgraphs: 1, Passed: 1, Failed: 0
|
|
2025-11-09T20:58:05Z USER 796 [BackendPassManager]: subgraph_parallel_pass finished after 0.052 seconds
|
|
2025-11-09T20:58:05Z INFO 796 [BackendPassManager]: curr_vmrss: 412mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:05Z USER 796 [BackendPassManager]: Running mod_parallel_pass
|
|
2025-11-09T20:58:05Z INFO 796 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=8 allocs=10732 blocks=8 instructions=31787 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:05Z USER 796 (nc00/sgLnk) [ModuleForkPass]: Running codegen
|
|
2025-11-09T20:58:05Z USER 796 (nc01/sgLnk) [ModuleForkPass]: Running codegen
|
|
2025-11-09T20:58:05Z INFO 796 (nc00/sgLnk) [ModuleForkPass]: Inputs to codegen: modules=1 functions=4 allocs=5558 blocks=4 instructions=16333 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:05Z INFO 796 (nc01/sgLnk) [ModuleForkPass]: Inputs to codegen: modules=1 functions=4 allocs=5174 blocks=4 instructions=15454 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:05Z INFO 796 (nc01/sgLnk) [Codegen]: Total un-allocated DRAM tensors by kind:
|
|
2025-11-09T20:58:05Z INFO 796 (nc01/sgLnk) [Codegen]:
|
|
┌────────────────┬─────────────┐
|
|
│ TensorKind │ Size (GB) │
|
|
├────────────────┼─────────────┤
|
|
│ ExternalInput │ 0.946291 │
|
|
│ ExternalOutput │ 0.21875 │
|
|
│ Const │ 0.000362996 │
|
|
└────────────────┴─────────────┘
|
|
|
|
2025-11-09T20:58:05Z INFO 796 (nc00/sgLnk) [Codegen]: Total un-allocated DRAM tensors by kind:
|
|
2025-11-09T20:58:05Z INFO 796 (nc00/sgLnk) [Codegen]:
|
|
┌────────────────┬─────────────┐
|
|
│ TensorKind │ Size (GB) │
|
|
├────────────────┼─────────────┤
|
|
│ ExternalInput │ 0.946291 │
|
|
│ ExternalOutput │ 0.21875 │
|
|
│ Const │ 0.000366818 │
|
|
└────────────────┴─────────────┘
|
|
|
|
2025-11-09T20:58:05Z INFO 796 (nc01/sgLnk) [Codegen]: Instruction Stats:
|
|
2025-11-09T20:58:05Z INFO 796 (nc01/sgLnk) [Codegen]:
|
|
┌─────────────────────┬───────┐
|
|
│ Opcode │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ MATMUL │ 10359 │
|
|
│ LDWEIGHTS │ 10289 │
|
|
│ EVENT_SEMAPHORE │ 889 │
|
|
│ UNKNOWN(0xd4) │ 836 │
|
|
│ ACTIVATE │ 779 │
|
|
│ TENSOR_TENSOR │ 649 │
|
|
│ CAST │ 566 │
|
|
│ COPY │ 487 │
|
|
│ PSEUDO_DMA_TRIGGER │ 236 │
|
|
│ UNKNOWN(0x9a) │ 160 │
|
|
│ UNKNOWN(0x9b) │ 160 │
|
|
│ TENSOR_SCALAR_ADDR │ 159 │
|
|
│ UNKNOWN(0xd3) │ 145 │
|
|
│ UNKNOWN(0xda) │ 105 │
|
|
│ MEMSET │ 95 │
|
|
│ TENSOR_REDUCE │ 72 │
|
|
│ UNKNOWN(0x92) │ 68 │
|
|
│ TENSOR_SCALAR │ 67 │
|
|
│ RECIPROCAL │ 65 │
|
|
│ UNKNOWN(0x24) │ 64 │
|
|
│ UNKNOWN(0xd8) │ 53 │
|
|
│ PSEUDO_BRANCH_LABEL │ 20 │
|
|
│ ACT_TABLE_LOAD │ 17 │
|
|
│ LOAD_MASK_SELECT │ 16 │
|
|
│ STREAM_SHUFFLE │ 16 │
|
|
│ UNKNOWN(0xd2) │ 15 │
|
|
│ UNKNOWN(0xd9) │ 8 │
|
|
│ PSEUDO_DMA_REARM │ 7 │
|
|
│ UNKNOWN(0xcf) │ 7 │
|
|
│ MOVE │ 7 │
|
|
│ UNKNOWN(0xe8) │ 6 │
|
|
│ IOTA │ 3 │
|
|
│ ALU_OP │ 2 │
|
|
│ PSEUDO_TENSOR_LOAD │ 1 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:58:05Z INFO 796 (nc01/sgLnk) [Codegen]:
|
|
┌────────────┬───────┐
|
|
│ Engine │ Count │
|
|
├────────────┼───────┤
|
|
│ Unassigned │ 0 │
|
|
│ GPSIMD │ 1386 │
|
|
│ Scalar │ 2167 │
|
|
│ Tensor │ 20806 │
|
|
│ SyncDMA │ 0 │
|
|
│ Vector │ 1803 │
|
|
│ Sync │ 286 │
|
|
│ All │ 0 │
|
|
└────────────┴───────┘
|
|
|
|
2025-11-09T20:58:05Z USER 796 (nc01/sgLnk) [Codegen]: isa_gen finished after 0.858 seconds
|
|
2025-11-09T20:58:05Z INFO 796 (nc01/sgLnk) [Codegen]: Number of DMA descriptors on each queue instance:
|
|
┌───────────────────────────┬────────────────┐
|
|
│ Queue Instance │ RT Descriptors │
|
|
├───────────────────────────┼────────────────┤
|
|
│ qActSpillReload0_defId_2 │ 90 │
|
|
│ qDVESpillReload0_defId_2 │ 212 │
|
|
│ qPoolSpillReload0_defId_0 │ 81920 │
|
|
│ qPoolSpillReload0_defId_1 │ 81920 │
|
|
│ qPoolSpillReload0_defId_2 │ 7 │
|
|
│ qSPIO0 │ 86084 │
|
|
│ qSPSpillReload0_defId_0 │ 2 │
|
|
│ qSPSpillReload0_defId_2 │ 14 │
|
|
└───────────────────────────┴────────────────┘
|
|
|
|
Total descriptors: 250249 (0.003729 GB)
|
|
2025-11-09T20:58:05Z INFO 796 (nc01/sgLnk) [Codegen]: Number of DMA engines used by each queue:
|
|
┌───────────────────┬──────────────────────┐
|
|
│ Queue │ DMA Engines │
|
|
├───────────────────┼──────────────────────┤
|
|
│ qSPDynamicHW │ 16 │
|
|
│ qPoolDynamic │ 16 │
|
|
│ qSPSpillReload0 │ 16 │
|
|
│ qSPIO0 │ 16 │
|
|
│ qActDynamicHW │ 16 │
|
|
│ qPoolSpillReload0 │ 16 │
|
|
│ qDVESpillReload0 │ 16 │
|
|
│ qActSpillReload0 │ 16 │
|
|
├───────────────────┼──────────────────────┤
|
|
│ TOTAL │ 128 (must be <= 176) │
|
|
└───────────────────┴──────────────────────┘
|
|
|
|
2025-11-09T20:58:05Z INFO 796 (nc01/sgLnk) [Codegen]: Tensors with largest descriptor count:
|
|
┌───────────────────────────────────────────────────────┬───────────────┬──────────┬──────────────────┐
|
|
│ Tensor Name │ Kind │ Src Type │ Descriptor Count │
|
|
├───────────────────────────────────────────────────────┼───────────────┼──────────┼──────────────────┤
|
|
│ I-2442-0_b0_grp_13_s0_tile0_exp_tp_sbuf_sg0001 │ Internal │ bfloat16 │ 16 │
|
|
│ I-2442-0_b1_grp_13_s0_tile0_exp_tp_sbuf_sg0001 │ Internal │ bfloat16 │ 16 │
|
|
│ I-2442-0_grp_15_sec_0_mhlo_exponential_6_b0_i0_sg0001 │ Internal │ bfloat16 │ 16 │
|
|
│ I-2744-0_grp_13_sec_0_mhlo_exponential_6_b1_i0_sg0000 │ Internal │ bfloat16 │ 16 │
|
|
│ I-2442-0_grp_15_sec_0_mhlo_exponential_6_b1_i0_sg0001 │ Internal │ bfloat16 │ 16 │
|
|
│ I-2744-0_grp_13_sec_0_mhlo_exponential_6_b0_i0_sg0000 │ Internal │ bfloat16 │ 16 │
|
|
│ add.4_sg0001 │ Internal │ bfloat16 │ 27 │
|
|
│ compare.2.1721_sg0001 │ Internal │ int32 │ 27 │
|
|
│ input2 │ ExternalInput │ int32 │ 28 │
|
|
│ convert.55_sg0002 │ Internal │ float32 │ 149 │
|
|
└───────────────────────────────────────────────────────┴───────────────┴──────────┴──────────────────┘
|
|
|
|
2025-11-09T20:58:06Z USER 796 (nc01/sgLnk) [Codegen]: dma_desc_gen finished after 0.160 seconds
|
|
2025-11-09T20:58:06Z INFO 796 (nc01/sgLnk) [Codegen]: Generating debug info
|
|
2025-11-09T20:58:06Z INFO 796 (nc00/sgLnk) [Codegen]: Instruction Stats:
|
|
2025-11-09T20:58:06Z INFO 796 (nc00/sgLnk) [Codegen]:
|
|
┌─────────────────────┬───────┐
|
|
│ Opcode │ Count │
|
|
├─────────────────────┼───────┤
|
|
│ MATMUL │ 10607 │
|
|
│ LDWEIGHTS │ 10525 │
|
|
│ EVENT_SEMAPHORE │ 1048 │
|
|
│ UNKNOWN(0xd4) │ 845 │
|
|
│ ACTIVATE │ 786 │
|
|
│ TENSOR_TENSOR │ 651 │
|
|
│ COPY │ 615 │
|
|
│ CAST │ 566 │
|
|
│ PSEUDO_DMA_TRIGGER │ 272 │
|
|
│ GATHER │ 193 │
|
|
│ POOL_BUFFER_LOAD │ 193 │
|
|
│ UNKNOWN(0x9b) │ 160 │
|
|
│ UNKNOWN(0x9a) │ 160 │
|
|
│ TENSOR_SCALAR_ADDR │ 159 │
|
|
│ UNKNOWN(0xd3) │ 145 │
|
|
│ DVE_READ_INDICES │ 128 │
|
|
│ MAX8 │ 128 │
|
|
│ MATCH_VALUE_LOAD │ 128 │
|
|
│ MATCH_REPLACE8 │ 128 │
|
|
│ MEMSET │ 109 │
|
|
│ UNKNOWN(0xda) │ 107 │
|
|
│ TENSOR_REDUCE │ 77 │
|
|
│ TENSOR_SCALAR │ 69 │
|
|
│ UNKNOWN(0x92) │ 68 │
|
|
│ RECIPROCAL │ 67 │
|
|
│ UNKNOWN(0x24) │ 64 │
|
|
│ UNKNOWN(0xd8) │ 53 │
|
|
│ PSEUDO_BRANCH_LABEL │ 20 │
|
|
│ ACT_TABLE_LOAD │ 18 │
|
|
│ STREAM_SHUFFLE │ 16 │
|
|
│ LOAD_MASK_SELECT │ 16 │
|
|
│ UNKNOWN(0xd2) │ 15 │
|
|
│ MOVE │ 8 │
|
|
│ UNKNOWN(0xd9) │ 8 │
|
|
│ PSEUDO_DMA_REARM │ 7 │
|
|
│ UNKNOWN(0xcf) │ 7 │
|
|
│ UNKNOWN(0xe8) │ 6 │
|
|
│ IOTA │ 3 │
|
|
│ UNKNOWN(0xe5) │ 2 │
|
|
│ ALU_OP │ 2 │
|
|
│ PSEUDO_TENSOR_LOAD │ 1 │
|
|
│ TENSOR_SCALAR │ 1 │
|
|
│ RNG │ 1 │
|
|
└─────────────────────┴───────┘
|
|
|
|
2025-11-09T20:58:06Z INFO 796 (nc00/sgLnk) [Codegen]:
|
|
┌────────────┬───────┐
|
|
│ Engine │ Count │
|
|
├────────────┼───────┤
|
|
│ Unassigned │ 0 │
|
|
│ GPSIMD │ 1838 │
|
|
│ Scalar │ 2319 │
|
|
│ Tensor │ 21291 │
|
|
│ SyncDMA │ 0 │
|
|
│ Vector │ 2435 │
|
|
│ Sync │ 319 │
|
|
│ All │ 0 │
|
|
└────────────┴───────┘
|
|
|
|
2025-11-09T20:58:06Z USER 796 (nc00/sgLnk) [Codegen]: isa_gen finished after 1.296 seconds
|
|
2025-11-09T20:58:06Z INFO 796 (nc00/sgLnk) [Codegen]: Number of DMA descriptors on each queue instance:
|
|
┌───────────────────────────┬────────────────┐
|
|
│ Queue Instance │ RT Descriptors │
|
|
├───────────────────────────┼────────────────┤
|
|
│ qActSpillReload0_defId_2 │ 94 │
|
|
│ qDVESpillReload0_defId_2 │ 352 │
|
|
│ qPoolSpillReload0_defId_0 │ 81920 │
|
|
│ qPoolSpillReload0_defId_1 │ 81920 │
|
|
│ qPoolSpillReload0_defId_2 │ 207 │
|
|
│ qSPIO0 │ 86088 │
|
|
│ qSPPIOParam0 │ 56 │
|
|
│ qSPSpillReload0_defId_0 │ 2 │
|
|
│ qSPSpillReload0_defId_2 │ 354 │
|
|
└───────────────────────────┴────────────────┘
|
|
|
|
Total descriptors: 250993 (0.00374009 GB)
|
|
2025-11-09T20:58:06Z INFO 796 (nc00/sgLnk) [Codegen]: Number of DMA engines used by each queue:
|
|
┌───────────────────┬──────────────────────┐
|
|
│ Queue │ DMA Engines │
|
|
├───────────────────┼──────────────────────┤
|
|
│ qSPDynamicHW │ 16 │
|
|
│ qPoolDynamic │ 16 │
|
|
│ qSPSpillReload0 │ 16 │
|
|
│ qSPIO0 │ 16 │
|
|
│ qActDynamicHW │ 16 │
|
|
│ qPoolSpillReload0 │ 16 │
|
|
│ qDVESpillReload0 │ 16 │
|
|
│ qActSpillReload0 │ 16 │
|
|
│ qSPPIOParam0 │ 16 │
|
|
├───────────────────┼──────────────────────┤
|
|
│ TOTAL │ 144 (must be <= 176) │
|
|
└───────────────────┴──────────────────────┘
|
|
|
|
2025-11-09T20:58:06Z INFO 796 (nc00/sgLnk) [Codegen]: Tensors with largest descriptor count:
|
|
┌───────────────────────────────────────────────────────┬───────────────┬──────────┬──────────────────┐
|
|
│ Tensor Name │ Kind │ Src Type │ Descriptor Count │
|
|
├───────────────────────────────────────────────────────┼───────────────┼──────────┼──────────────────┤
|
|
│ I-2744-0_b0_grp_15_s0_tile0_exp_tp_sbuf_sg0000 │ Internal │ bfloat16 │ 16 │
|
|
│ I-2744-0_grp_14_sec_0_mhlo_exponential_6_b1_i0_sg0000 │ Internal │ bfloat16 │ 16 │
|
|
│ I-2744-0_b0_grp_13_s0_tile0_exp_tp_sbuf_sg0000 │ Internal │ bfloat16 │ 16 │
|
|
│ I-2744-0_b1_grp_15_s0_tile0_exp_tp_sbuf_sg0000 │ Internal │ bfloat16 │ 16 │
|
|
│ I-2442-0_b1_grp_13_s0_tile0_exp_tp_sbuf_sg0001 │ Internal │ bfloat16 │ 16 │
|
|
│ compare.2.1721_sg0001 │ Internal │ int32 │ 27 │
|
|
│ all-reduce.465.2443_sg0001 │ Internal │ bfloat16 │ 27 │
|
|
│ add.4_sg0001 │ Internal │ bfloat16 │ 27 │
|
|
│ input2 │ ExternalInput │ int32 │ 28 │
|
|
│ convert.55_sg0002 │ Internal │ float32 │ 150 │
|
|
└───────────────────────────────────────────────────────┴───────────────┴──────────┴──────────────────┘
|
|
|
|
2025-11-09T20:58:06Z USER 796 (nc00/sgLnk) [Codegen]: dma_desc_gen finished after 0.149 seconds
|
|
2025-11-09T20:58:06Z INFO 796 (nc00/sgLnk) [Codegen]: Generating debug info
|
|
2025-11-09T20:58:06Z USER 796 (nc01/sgLnk) [Codegen]: debug_info_gen finished after 0.440 seconds
|
|
2025-11-09T20:58:06Z USER 796 (nc01/sgLnk) [ModuleForkPass]: codegen finished after 1.557 seconds
|
|
2025-11-09T20:58:06Z INFO 796 (nc01/sgLnk) [ModuleForkPass]: curr_vmrss: 426mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:06Z INFO 796 (nc01/sgLnk) [ModuleForkPass]: Output has 1 module(s), 4 function(s), 5174 memory location(s), 4 block(s), and 15454 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:06Z USER 796 (nc00/sgLnk) [Codegen]: debug_info_gen finished after 0.191 seconds
|
|
2025-11-09T20:58:06Z USER 796 (nc00/sgLnk) [ModuleForkPass]: codegen finished after 1.688 seconds
|
|
2025-11-09T20:58:06Z INFO 796 (nc00/sgLnk) [ModuleForkPass]: curr_vmrss: 427mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:06Z INFO 796 (nc00/sgLnk) [ModuleForkPass]: Output has 1 module(s), 4 function(s), 5558 memory location(s), 4 block(s), and 16333 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:06Z USER 796 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0
|
|
2025-11-09T20:58:06Z USER 796 [BackendPassManager]: mod_parallel_pass finished after 1.703 seconds
|
|
2025-11-09T20:58:06Z INFO 796 [BackendPassManager]: curr_vmrss: 427mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:06Z USER 796 [BackendPassManager]: Running hbm_usage
|
|
2025-11-09T20:58:06Z INFO 796 [BackendPassManager]: Inputs to hbm_usage: modules=2 functions=8 allocs=10732 blocks=8 instructions=31787 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:06Z INFO 796 (nc00/sgLnk) [HBMUsage]:
|
|
┌───────────────┬──────────┬───────────────────┐
|
|
│ DMA Ring Type │ I/O Size │ Spill/Reload Size │
|
|
├───────────────┼──────────┼───────────────────┤
|
|
│ Copy │ 1.125KB │ 16.594KB │
|
|
│ CCE │ 1.312MB │ 48.000B │
|
|
│ Transpose │ 0.000B │ 2.500MB │
|
|
│ Replicate │ 0.000B │ 0.000B │
|
|
│ Overhead │ 16.000KB │ 71.500KB │
|
|
└───────────────┴──────────┴───────────────────┘
|
|
|
|
2025-11-09T20:58:06Z INFO 796 (nc00/sgLnk) [HBMUsage]:
|
|
┌─────────────────────┬───────────┐
|
|
│ DRAM Memory Usage │ Size │
|
|
├─────────────────────┼───────────┤
|
|
│ Total: │ 1.248GB │
|
|
│ Model Code │ 1.721MB │
|
|
│ Model Constants │ 384.637KB │
|
|
│ Unallocated Tensors │ 1.165GB │
|
|
│ Allocated Tensors │ 79.008MB │
|
|
│ DMA Ring IO │ 1.329MB │
|
|
│ DMA Ring Spill │ 2.586MB │
|
|
└─────────────────────┴───────────┘
|
|
|
|
2025-11-09T20:58:06Z INFO 796 (nc01/sgLnk) [HBMUsage]:
|
|
┌───────────────┬──────────┬───────────────────┐
|
|
│ DMA Ring Type │ I/O Size │ Spill/Reload Size │
|
|
├───────────────┼──────────┼───────────────────┤
|
|
│ Copy │ 1.062KB │ 5.031KB │
|
|
│ CCE │ 1.312MB │ 48.000B │
|
|
│ Transpose │ 0.000B │ 2.500MB │
|
|
│ Replicate │ 0.000B │ 0.000B │
|
|
│ Overhead │ 15.500KB │ 56.500KB │
|
|
└───────────────┴──────────┴───────────────────┘
|
|
|
|
2025-11-09T20:58:06Z INFO 796 (nc01/sgLnk) [HBMUsage]:
|
|
┌─────────────────────┬───────────┐
|
|
│ DRAM Memory Usage │ Size │
|
|
├─────────────────────┼───────────┤
|
|
│ Total: │ 1.216GB │
|
|
│ Model Code │ 1.614MB │
|
|
│ Model Constants │ 380.629KB │
|
|
│ Unallocated Tensors │ 1.165GB │
|
|
│ Allocated Tensors │ 46.000MB │
|
|
│ DMA Ring IO │ 1.329MB │
|
|
│ DMA Ring Spill │ 2.560MB │
|
|
└─────────────────────┴───────────┘
|
|
|
|
2025-11-09T20:58:06Z INFO 796 [HBMUsage]: Total estimated HBM usage is: 1.298GB
|
|
2025-11-09T20:58:06Z USER 796 [BackendPassManager]: hbm_usage finished after 0.031 seconds
|
|
2025-11-09T20:58:06Z INFO 796 [BackendPassManager]: curr_vmrss: 427mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:06Z INFO 796 [BackendPassManager]: Output has 2 module(s), 8 function(s), 10732 memory location(s), 8 block(s), and 31787 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:06Z USER 796 [BackendPassManager]: Running neff_packager
|
|
2025-11-09T20:58:06Z INFO 796 [BackendPassManager]: Inputs to neff_packager: modules=2 functions=8 allocs=10732 blocks=8 instructions=31787 Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0000_constant.7_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0000_constant.9-1804_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0000_constant.3-1725-1806_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0000_constant.2-1735-1808_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0000_identity_2022_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0000_identity_2009_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0001_constant.15_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0001_constant.12-1516-1606_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0001_constant.11-1526-1608_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0001_identity_1742_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0002_constant.24_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0002_constant.25_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0002_constant.26_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0002_constant.28_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0002_constant.29_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0002_constant.27-1126-1347_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0002_identity_1549_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: Const File de-dup saved 0 KB of memory footprint
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0000_constant.7_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0000_constant.9-1804_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0000_constant.3-1725-1806_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0000_constant.2-1735-1808_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0000_identity_2022_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0000_identity_2009_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0001_constant.15_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0001_constant.12-1516-1606_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0001_constant.11-1526-1608_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0001_identity_1742_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0002_constant.26_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0002_constant.28_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0002_constant.29_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: FileDeDuper file not found value_sg0002_identity_1549_CRSM.npy
|
|
2025-11-09T20:58:06Z INFO 796 [NeffPackager]: Const File de-dup saved 0 KB of memory footprint
|
|
2025-11-09T20:58:06Z WARNING 796 [NeffFileWriter]: writeKelp missing file /local/p4clients/pkgbuild-const/workspace/build/KaenaCompiler/KaenaCompiler-2.x.207535.0/AL2_x86_64/DEV.STD.PTHREAD/build/private/_skbuild/linux-x86_64-3.11/cmake-build/neuronxcc/walrus/neff_packager/MetricMetadata.json
|
|
2025-11-09T20:58:06Z WARNING 796 [NeffFileWriter]: writeKelp missing file /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/neuronxcc-u_vl19it/metrics.json
|
|
2025-11-09T20:58:07Z INFO 796 [NeffFileWriter]: Neff will be written to: /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/model.MODULE_e6b44ff520e6c4333666+e9aa1481.neff
|
|
2025-11-09T20:58:07Z INFO 796 [NeffFileWriter]: IR signature: 20d0cb3efc9f680e28ea03ebe132a0a5 for neff artifacts
|
|
2025-11-09T20:58:07Z USER 796 [BackendPassManager]: neff_packager finished after 0.631 seconds
|
|
2025-11-09T20:58:07Z INFO 796 [BackendPassManager]: curr_vmrss: 427mb, ru_maxrss: 509mb (delta=0mb)
|
|
2025-11-09T20:58:07Z INFO 796 [BackendPassManager]: Output has 2 module(s), 8 function(s), 10732 memory location(s), 8 block(s), and 31787 instruction(s). Max writers: 151 Max Readers: 2918
|
|
2025-11-09T20:58:07Z INFO 796 [BackendDriver]: HBM scratchpad usage summary (post-allocation):
|
|
┌──────┬───────────┬────────────────────────────────────────────────────────────┬─────────────┐
|
|
│ Core │ Subgraph │ Description │ Value │
|
|
├──────┼───────────┼────────────────────────────────────────────────────────────┼─────────────┤
|
|
│ nc00 │ sg00 │ Peak scratchpad usage: local │ 0.000000 GB │
|
|
│ nc00 │ sg00 │ Peak scratchpad usage: local and shared │ 0.033203 GB │
|
|
│ nc00 │ sg00 │ Total size of allocated tensors: local │ 0.000000 GB │
|
|
│ nc00 │ sg00 │ Total size of allocated tensors: shared │ 0.033203 GB │
|
|
│ nc00 │ sg01 │ Peak scratchpad usage: local │ 0.000000 GB │
|
|
│ nc00 │ sg01 │ Peak scratchpad usage: local and shared │ 0.044922 GB │
|
|
│ nc00 │ sg01 │ Total size of allocated tensors: local │ 0.000000 GB │
|
|
│ nc00 │ sg01 │ Total size of allocated tensors: shared │ 0.046875 GB │
|
|
│ nc00 │ sg02 │ Peak scratchpad usage: local │ 0.000004 GB │
|
|
│ nc00 │ sg02 │ Peak scratchpad usage: local and shared │ 0.023609 GB │
|
|
│ nc00 │ sg02 │ Total size of allocated tensors: local │ 0.000019 GB │
|
|
│ nc00 │ sg02 │ Total size of allocated tensors: shared │ 0.031452 GB │
|
|
│ nc00 │ Max │ Peak scratchpad usage: local │ 0.000004 GB │
|
|
│ nc00 │ Max │ Peak scratchpad usage: local and shared │ 0.044922 GB │
|
|
│ nc00 │ Post-link │ Peak scratchpad usage after intermediate tensor allocation │ 0.077160 GB │
|
|
│ nc00 │ Post-link │ Total size of allocated intermediate tensors │ 0.438583 GB │
|
|
├──────┼───────────┼────────────────────────────────────────────────────────────┼─────────────┤
|
|
│ nc01 │ sg00 │ Peak scratchpad usage: local │ 0.000000 GB │
|
|
│ nc01 │ sg00 │ Total size of allocated tensors: local │ 0.000000 GB │
|
|
│ nc01 │ sg01 │ Peak scratchpad usage: local │ 0.000000 GB │
|
|
│ nc01 │ sg01 │ Total size of allocated tensors: local │ 0.000000 GB │
|
|
│ nc01 │ sg02 │ Peak scratchpad usage: local │ 0.000000 GB │
|
|
│ nc01 │ sg02 │ Total size of allocated tensors: local │ 0.000000 GB │
|
|
│ nc01 │ Max │ Peak scratchpad usage: local │ 0.000000 GB │
|
|
├──────┼───────────┼────────────────────────────────────────────────────────────┼─────────────┤
|
|
│ Max │ Max │ Peak scratchpad usage │ 0.077160 GB │
|
|
│ Max │ Max │ Peak scratchpad usage (page-aligned) │ 0.500000 GB │
|
|
└──────┴───────────┴────────────────────────────────────────────────────────────┴─────────────┘
|
|
|
|
2025-11-09T20:58:07Z INFO 796 [BackendDriver]: Largest tensors at peak scratchpad usage, core=nc00, subgraph=sg00, addr_space=shared (complete data located at nc00/sg00/memory_analysis_after_coloring_allocator_dram_shared_DRAM_Shared_hwm_allocations.csv):
|
|
┌────────────────────────────────────────────────────────────────┬──────────┬───────────────┬─────────────┐
|
|
│ Tensor Name │ Type │ # Sub-tensors │ Total Size │
|
|
├────────────────────────────────────────────────────────────────┼──────────┼───────────────┼─────────────┤
|
|
│ dot.4 │ bfloat16 │ 1 │ 8.000000 MB │
|
|
│ intermediate3 │ bfloat16 │ 1 │ 8.000000 MB │
|
|
│ get_tuple_element.1 │ bfloat16 │ 1 │ 2.000000 MB │
|
|
└────────────────────────────────────────────────────────────────┴──────────┴───────────────┴─────────────┘
|
|
|
|
2025-11-09T20:58:07Z INFO 796 [BackendDriver]: Largest tensors at peak scratchpad usage, core=nc00, subgraph=sg02, addr_space=shared (complete data located at nc00/sg02/memory_analysis_after_coloring_allocator_dram_shared_DRAM_Shared_hwm_allocations.csv):
|
|
┌────────────────────────────────────────────────────────────────┬──────────┬───────────────┬─────────────┐
|
|
│ Tensor Name │ Type │ # Sub-tensors │ Total Size │
|
|
├────────────────────────────────────────────────────────────────┼──────────┼───────────────┼─────────────┤
|
|
│ add.4 │ bfloat16 │ 1 │ 0.000001 MB │
|
|
└────────────────────────────────────────────────────────────────┴──────────┴───────────────┴─────────────┘
|
|
|
|
2025-11-09T20:58:07Z INFO 796 [BackendDriver]: Largest intermediate tensors at peak scratchpad usage, core=nc00 (complete data located at nc00//sgLnk/sg00/memory_analysis_after_coloring_allocator_dram_post_lnk_DRAM_Shared_hwm_allocations.csv):
|
|
┌────────────────────────────────────────────────────────────────┬──────────┬───────────────┬─────────────┐
|
|
│ Tensor Name │ Type │ # Sub-tensors │ Total Size │
|
|
├────────────────────────────────────────────────────────────────┼──────────┼───────────────┼─────────────┤
|
|
│ intermediate0 │ bfloat16 │ 1 │ 8.000000 MB │
|
|
│ intermediate3 │ bfloat16 │ 1 │ 8.000000 MB │
|
|
│ intermediate5 │ bfloat16 │ 1 │ 8.000000 MB │
|
|
│ intermediate6 │ bfloat16 │ 1 │ 8.000000 MB │
|
|
│ intermediate1 │ bfloat16 │ 1 │ 0.500000 MB │
|
|
│ intermediate2 │ bfloat16 │ 1 │ 0.500000 MB │
|
|
│ intermediate4 │ bfloat16 │ 1 │ 0.003906 MB │
|
|
│ intermediate7 │ bfloat16 │ 1 │ 0.003906 MB │
|
|
└────────────────────────────────────────────────────────────────┴──────────┴───────────────┴─────────────┘
|
|
|
|
2025-11-09T20:58:07Z INFO 796 [BackendDriver]: Largest intermediate tensors at peak scratchpad usage, core=nc01 (complete data located at nc01//sgLnk/sg00/memory_analysis_after_coloring_allocator_dram_post_lnk_DRAM_Shared_hwm_allocations.csv):
|
|
┌────────────────────────────────────────────────────────────────┬──────────┬───────────────┬─────────────┐
|
|
│ Tensor Name │ Type │ # Sub-tensors │ Total Size │
|
|
├────────────────────────────────────────────────────────────────┼──────────┼───────────────┼─────────────┤
|
|
│ intermediate0 │ bfloat16 │ 1 │ 8.000000 MB │
|
|
│ intermediate3 │ bfloat16 │ 1 │ 8.000000 MB │
|
|
│ intermediate5 │ bfloat16 │ 1 │ 8.000000 MB │
|
|
│ intermediate6 │ bfloat16 │ 1 │ 8.000000 MB │
|
|
│ intermediate1 │ bfloat16 │ 1 │ 0.500000 MB │
|
|
│ intermediate2 │ bfloat16 │ 1 │ 0.500000 MB │
|
|
│ intermediate4 │ bfloat16 │ 1 │ 0.003906 MB │
|
|
│ intermediate7 │ bfloat16 │ 1 │ 0.003906 MB │
|
|
└────────────────────────────────────────────────────────────────┴──────────┴───────────────┴─────────────┘
|
|
|
|
2025-11-09T20:58:07Z INFO 796 [BackendDriver]: Backend completed successfully, tearing down.
|
|
2025-11-09T20:58:08Z INFO 550 [job.WalrusDriver.0]: VNCBackend: completed successfully.
|
|
2025-11-09T20:58:08Z INFO 550 [pipeline.Pipeline.0]: Finished job job.WalrusDriver.0
|
|
2025-11-09T20:58:08Z INFO 550 [pipeline.Pipeline.0]: Starting job job.BIRLinker.0
|
|
2025-11-09T20:58:08Z INFO 550 [job.BIRLinker.0]: Replay this job by calling: /opt/conda/bin/neuronx-cc compile --framework XLA --state '{"model": ["/models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/model.MODULE_e6b44ff520e6c4333666+e9aa1481.hlo_module.pb"], "tensormap": "tensor_map.json", "bir": "walrus_bir.out.json", "lorean_sg_key": null, "input_name_map": null, "output_name_map": null, "constant_tensors": null, "cached_wavegraph": "walrus_bir.out.json", "state_dir": "/models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/neuronxcc-u_vl19it/nc00/sg00", "state_id": "nc00/sg00"}' --pipeline BIRLinker
|
|
2025-11-09T20:58:08Z INFO 550 [job.BIRLinker.0]: BIRLinker cwd: /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/neuronxcc-u_vl19it
|
|
2025-11-09T20:58:08Z INFO 550 [job.BIRLinker.0]: Linking already done.
|
|
2025-11-09T20:58:08Z INFO 550 [pipeline.Pipeline.0]: Finished job job.BIRLinker.0
|
|
2025-11-09T20:58:08Z INFO 550 [pipeline.Pipeline.0]: Starting job job.Kelper.0
|
|
2025-11-09T20:58:08Z INFO 550 [job.Kelper.0]: Skipping neff generation which was already performed by neff_packager
|
|
2025-11-09T20:58:08Z INFO 550 [pipeline.Pipeline.0]: Finished job job.Kelper.0
|
|
2025-11-09T20:58:08Z INFO 550 [pipeline.Pipeline.0]: Starting job job.NeffWrapper.0
|
|
2025-11-09T20:58:08Z INFO 550 [job.NeffWrapper.0]: Job NeffWrapper len(in_states) 1
|
|
2025-11-09T20:58:08Z INFO 550 [job.NeffWrapper.0]: Processing input #0
|
|
2025-11-09T20:58:08Z INFO 550 [job.NeffWrapper.0]: Start NeffWrapper
|
|
2025-11-09T20:58:08Z INFO 550 [job.NeffWrapper.0]: Executing: /opt/conda/lib/python3.11/site-packages/neuronxcc/starfish/bin/hlo-neff-wrapper --hlo /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/model.MODULE_e6b44ff520e6c4333666+e9aa1481.hlo_module.pb --neff /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/model.MODULE_e6b44ff520e6c4333666+e9aa1481.neff --io_transposes /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/neuronxcc-u_vl19it/io_transposes.json --output /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/wrapped_neff.hlo --netlist /models/Qwen3-1.7B-compiled/context_encoding_model/_tp0_bk4/neuronxcc-u_vl19it/hlo_netlist.json
|
|
2025-11-09T20:58:08Z INFO 550 [job.NeffWrapper.0]: There are no io transposes nor zero-sized parameters. Output will not be produced.
|
|
Hlo neff wrapper finished successfully. Have a wonderful day :D
|
|
|
|
2025-11-09T20:58:08Z INFO 550 [job.NeffWrapper.0]: Job #0 finished
|
|
2025-11-09T20:58:08Z INFO 550 [pipeline.Pipeline.0]: Finished job job.NeffWrapper.0
|
|
2025-11-09T20:58:08Z INFO 550 [pipeline.Pipeline.0]: Finished pipeline Pipeline
|
|
2025-11-09T20:58:08Z INFO 550 [pipeline.Pipeline.0]: Job #0 finished
|
|
2025-11-09T20:58:09Z INFO 373 [root]: Subcommand returned with exitcode=0
|