2025-11-09T20:53:13Z INFO 240 [root]: /opt/conda/bin/neuronx-cc compile --framework=XLA /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/model.MODULE_5e3d0ce8963512f9ea2d+937cd7a2.hlo_module.pb --output /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/model.MODULE_5e3d0ce8963512f9ea2d+937cd7a2.neff --target=trn2 --auto-cast=none --model-type=transformer '--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --vectorize-strided-dma' --lnc=2 -O2 --internal-hlo2tensorizer-options=--verify-hlo=true --logfile=/models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/log-neuron-cc.txt --enable-internal-neff-wrapper --verbose=35 2025-11-09T20:53:18Z INFO 240 [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 2025-11-09T20:53:18Z INFO 252 [root]: XLA detected 2025-11-09T20:53:18Z INFO 252 [root]: Pipeline: HLOToTensorizer Frontend StaticIOTranspose WalrusDriver BIRLinker Kelper NeffWrapper 2025-11-09T20:53:19Z INFO 252 [root]: Intermediate files stored in /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/neuronxcc-sij89sjf, output in /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0 2025-11-09T20:53:19Z INFO 252 [pipeline.Pipeline.0]: Job Pipeline len(in_states) 1 2025-11-09T20:53:19Z INFO 252 [pipeline.Pipeline.0]: Processing input #0 2025-11-09T20:53:19Z INFO 252 [pipeline.Pipeline.0]: Running pipeline Pipeline.0 2025-11-09T20:53:19Z INFO 252 [pipeline.Pipeline.0]: Starting job job.HLOToTensorizer.0 2025-11-09T20:53:19Z INFO 252 [job.HLOToTensorizer.0]: Job HLOToTensorizer len(in_states) 1 2025-11-09T20:53:19Z INFO 252 [job.HLOToTensorizer.0]: Processing input #0 2025-11-09T20:53:19Z INFO 252 [job.HLOToTensorizer.0]: Executing: /opt/conda/lib/python3.11/site-packages/neuronxcc/starfish/bin/hlo2penguin --input /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/model.MODULE_5e3d0ce8963512f9ea2d+937cd7a2.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/token_generation_model/_tp0_bk0/log-neuron-cc.txt --logfile-verbose=info --layers-per-module=1 --emit-tensor-level-dropout-ops --verify-hlo=true --native-to-custom-softmax --partitioner-opts='--transformer' 2025-11-09T20:53:19Z INFO 252 [job.HLOToTensorizer.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 divide dot exponential gather get-tuple-element iota maximum multiply negate parameter reduce reshape rng scatter select sine slice subtract transpose tuple 2025-11-09 20:53:19.555465: W hilo/hlo2penguin/utils/DumpDebugInfo.cc:88] Could not open file debug_info_hlo_partitions.json 2025-11-09 20:53:19.558920: W hilo/hlo2penguin/utils/DumpDebugInfo.cc:52] Truncating long HLO operator name %tuple.10713 = tuple(%reshape.3670, %scatter.9941, %scatter.9956, %scatter.9969, %scatter.9984, %scatter.9997, %scatter.10012, %scatter.10025, %scatter.10040, %scatter.10053, %scatter.10068, %scatter.10081, %scatter.10096, %scatter.10109, %scatter.10124, %scatter.10137, %scatter.10152, %scatter.10165, %scatter.10180, %scatter.10193, %scatter.10208, %scatter.10221, %scatter.10236, %scatter.10249, %scatter.10264, %scatter.10277, %scatter.10292, %scatter.10305, %scatter.10320, %scatter.10333, %scatter.10348... to 512 characters in the compiler's debug metadata Transposable weight idxs: 60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280,281,282,283,284,285,286,287,288,289,290,291,292,293,294,295,296,297,298,299,300,301,302,303,304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,324,325,326,327,328,329,330,331,332,333,334,335,336,337,338,339,340,341,342,343,344,345,346,347,348,349,350,351,352,353,354,355,356,357,358,359,360,361,362,363,364,365,366,367,368,369,370 Invoking RemoveOptimizationBarriers pass 2025-11-09T20:53:19Z INFO 252 [job.HLOToTensorizer.0]: IR signature: c8a90da2a2dcd8d50cbaa0fe53245f9dffa411f954726e1cdf2314cb66a774f9 for sg0000/HLOToTensorizer 2025-11-09T20:53:19Z INFO 252 [job.HLOToTensorizer.0]: Job #0 finished 2025-11-09T20:53:19Z INFO 252 [pipeline.Pipeline.0]: Finished job job.HLOToTensorizer.0 2025-11-09T20:53:19Z INFO 252 [pipeline.Pipeline.0]: Starting job job.Frontend.0 2025-11-09T20:53:19Z INFO 252 [job.Frontend.0]: Job Frontend len(in_states) 1 2025-11-09T20:53:19Z INFO 252 [job.Frontend.0]: Processing input #0 2025-11-09T20:53:19Z INFO 252 [job.Frontend.0]: Start model loading 2025-11-09T20:53:19Z INFO 252 [job.Frontend.0]: Start tensorization 2025-11-09T20:53:20Z INFO 252 [job.Frontend.0]: Num jobs: 1 2025-11-09T20:53:20Z USER 252 [root/Tensorizer/Tensorizer]: Running Tensorizer 2025-11-09T20:53:20Z INFO 252 [Tensorizer]: Frontend did not find netlist info. Switching to flat flow. 2025-11-09T20:53:20Z INFO 252 [Tensorizer]: Building model from Penguin script "penguin.py"... 2025-11-09T20:53:21Z INFO 252 [Tensorizer]: Tensorizer options: --enable-ccop-compute-overlap --cc-pipeline-tiling-factor=1 --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 --keep-remat-dma-transpose --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 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/DoNothing]: Running DoNothing 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/DoNothing]: Finished (changed=True) 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/DoNothing]: DoNothing finished after 0.000 seconds 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/LegalizeOpLevelAlias]: Running LegalizeOpLevelAlias 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/LegalizeOpLevelAlias]: Finished (changed=False) 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/LegalizeOpLevelAlias]: LegalizeOpLevelAlias finished after 0.023 seconds 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/OptimizeAliasedCopyChain]: Running OptimizeAliasedCopyChain 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/OptimizeAliasedCopyChain]: Finished (changed=False) 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/OptimizeAliasedCopyChain]: OptimizeAliasedCopyChain finished after 0.011 seconds 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/AliasDependencyInduction]: Running AliasDependencyInduction 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/AliasDependencyInduction]: Finished (changed=True) 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/AliasDependencyInduction]: AliasDependencyInduction finished after 0.041 seconds 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/TransformConvOp]: Running TransformConvOp 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/TransformConvOp]: Finished (changed=False) 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/TransformConvOp]: TransformConvOp finished after 0.057 seconds 2025-11-09T20:53:21Z INFO 252 [sg0000/Tensorizer/LowerTensorOp]: Running LowerTensorOp 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/LowerTensorOp]: Finished (changed=True) 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/LowerTensorOp]: LowerTensorOp finished after 0.389 seconds 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/AliasDependencyReset]: Running AliasDependencyReset 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/AliasDependencyElimination]: Running AliasDependencyElimination 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/AliasDependencyElimination]: Finished (changed=True) 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/AliasDependencyElimination]: AliasDependencyElimination finished after 0.003 seconds 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/AliasDependencyInduction]: Running AliasDependencyInduction 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/AliasDependencyInduction]: Finished (changed=True) 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/AliasDependencyInduction]: AliasDependencyInduction finished after 0.205 seconds 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/AliasDependencyReset]: AliasDependencyReset finished after 0.211 seconds 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/LegalizeCCOpLayout]: Running LegalizeCCOpLayout 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/LegalizeCCOpLayout]: Finished (changed=False) 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/LegalizeCCOpLayout]: LegalizeCCOpLayout finished after 0.052 seconds 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/TensorOpSimplifier]: Running TensorOpSimplifier 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/TensorOpSimplifier]: Finished (changed=True) 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/TensorOpSimplifier]: TensorOpSimplifier finished after 0.153 seconds 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/CanonicalizeIR]: Running CanonicalizeIR 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/CanonicalizeIR]: Finished (changed=True) 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/CanonicalizeIR]: CanonicalizeIR finished after 0.049 seconds 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/ResolveComplicatePredicates]: Running ResolveComplicatePredicates 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/ResolveComplicatePredicates]: Finished (changed=False) 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/ResolveComplicatePredicates]: ResolveComplicatePredicates finished after 0.035 seconds 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/AffinePredicateResolution]: Running AffinePredicateResolution 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/AffinePredicateResolution]: Finished (changed=False) 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/AffinePredicateResolution]: AffinePredicateResolution finished after 0.035 seconds 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/EliminateDivs]: Running EliminateDivs 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/EliminateDivs]: Finished (changed=False) 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/EliminateDivs]: EliminateDivs finished after 0.111 seconds 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/PerfectLoopNest]: Running PerfectLoopNest 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/PerfectLoopNest]: Finished (changed=False) 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/PerfectLoopNest]: PerfectLoopNest finished after 0.035 seconds 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier 2025-11-09T20:53:22Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_0 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.191 seconds 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_1 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_1 finished after 0.209 seconds 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_2 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_2 finished after 0.108 seconds 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/Simplifier]: Finished (changed=True) 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier finished after 0.509 seconds 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/GenericAccessSimplifier]: Finished (changed=False) 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.035 seconds 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/TCTransform]: Running TCTransform 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/TCTransform]: Finished (changed=False) 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/TCTransform]: TCTransform finished after 0.038 seconds 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/CommuteConcat]: Running CommuteConcat 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/CommuteConcat]: Running CommuteConcat_iteration_0 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/CommuteConcat]: CommuteConcat_iteration_0 finished after 0.039 seconds 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/CommuteConcat]: Finished (changed=False) 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/CommuteConcat]: CommuteConcat finished after 0.039 seconds 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/ExpandBatchNorm]: Running ExpandBatchNorm 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/ExpandBatchNorm]: Finished (changed=False) 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/ExpandBatchNorm]: ExpandBatchNorm finished after 0.049 seconds 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/TCTransform]: Running TCTransform 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/TCTransform]: Finished (changed=False) 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/TCTransform]: TCTransform finished after 0.039 seconds 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/GenericAccessSimplifier]: Finished (changed=False) 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.035 seconds 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/TensorOpTransform]: Running TensorOpTransform 2025-11-09T20:53:23Z INFO 252 [sg0000/Tensorizer/TensorOpTransform]: Running TensorOpTransform_iteration_0 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/TensorOpTransform]: TensorOpTransform_iteration_0 finished after 0.749 seconds 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/TensorOpTransform]: Running TensorOpTransform_iteration_1 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/TensorOpTransform]: TensorOpTransform_iteration_1 finished after 0.078 seconds 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/TensorOpTransform]: Finished (changed=True) 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/TensorOpTransform]: TensorOpTransform finished after 0.828 seconds 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/LateLowerTensorOp]: Running LateLowerTensorOp 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/LateLowerTensorOp]: Finished (changed=True) 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/LateLowerTensorOp]: LateLowerTensorOp finished after 0.224 seconds 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/AliasDependencyReset]: Running AliasDependencyReset 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/AliasDependencyElimination]: Running AliasDependencyElimination 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/AliasDependencyElimination]: Finished (changed=True) 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/AliasDependencyElimination]: AliasDependencyElimination finished after 0.004 seconds 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/AliasDependencyInduction]: Running AliasDependencyInduction 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/AliasDependencyInduction]: Finished (changed=True) 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/AliasDependencyInduction]: AliasDependencyInduction finished after 0.298 seconds 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/AliasDependencyReset]: AliasDependencyReset finished after 0.305 seconds 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/MemcpyElimination]: Running MemcpyElimination 2025-11-09T20:53:24Z INFO 252 [sg0000/Tensorizer/MemcpyElimination]: Running MemcpyElimination_iteration_0 2025-11-09T20:53:28Z INFO 252 [sg0000/Tensorizer/MemcpyElimination]: MemcpyElimination_iteration_0 finished after 3.182 seconds 2025-11-09T20:53:28Z INFO 252 [sg0000/Tensorizer/MemcpyElimination]: Running MemcpyElimination_iteration_1 2025-11-09T20:53:28Z INFO 252 [sg0000/Tensorizer/MemcpyElimination]: MemcpyElimination_iteration_1 finished after 0.129 seconds 2025-11-09T20:53:28Z INFO 252 [sg0000/Tensorizer/MemcpyElimination]: Finished (changed=True) 2025-11-09T20:53:28Z INFO 252 [sg0000/Tensorizer/MemcpyElimination]: MemcpyElimination finished after 3.313 seconds 2025-11-09T20:53:28Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion 2025-11-09T20:53:28Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0 2025-11-09T20:53:28Z INFO 252 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.439 seconds 2025-11-09T20:53:28Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_1 2025-11-09T20:53:28Z INFO 252 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_1 finished after 0.213 seconds 2025-11-09T20:53:28Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_2 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_2 finished after 0.157 seconds 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.305 seconds 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_1 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_1 finished after 0.364 seconds 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Finished (changed=True) 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/LoopFusion]: LoopFusion finished after 1.485 seconds 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/Rematerialization]: Running Rematerialization 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/Rematerialization]: Finished (changed=True) 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/Rematerialization]: Rematerialization finished after 0.141 seconds 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_0 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.116 seconds 2025-11-09T20:53:29Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_1 2025-11-09T20:53:30Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_1 finished after 0.078 seconds 2025-11-09T20:53:30Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_2 2025-11-09T20:53:30Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_2 finished after 0.078 seconds 2025-11-09T20:53:30Z INFO 252 [sg0000/Tensorizer/Simplifier]: Finished (changed=True) 2025-11-09T20:53:30Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier finished after 0.273 seconds 2025-11-09T20:53:30Z INFO 252 [sg0000/Tensorizer/Delinearization]: Running Delinearization 2025-11-09T20:53:30Z INFO 252 [sg0000/Tensorizer/Delinearization]: Finished (changed=True) 2025-11-09T20:53:30Z INFO 252 [sg0000/Tensorizer/Delinearization]: Delinearization finished after 0.432 seconds 2025-11-09T20:53:30Z INFO 252 [sg0000/Tensorizer/DeadStoreElimination]: Running DeadStoreElimination 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/DeadStoreElimination]: Finished (changed=False) 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/DeadStoreElimination]: DeadStoreElimination finished after 1.100 seconds 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_0 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.085 seconds 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/Simplifier]: Finished (changed=False) 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier finished after 0.086 seconds 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/LICM]: Running LICM 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/LICM]: Finished (changed=True) 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/LICM]: LICM finished after 0.067 seconds 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/Delinearization]: Running Delinearization 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/Delinearization]: Finished (changed=False) 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/Delinearization]: Delinearization finished after 0.097 seconds 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion 2025-11-09T20:53:31Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.318 seconds 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_1 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_1 finished after 0.092 seconds 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.189 seconds 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Finished (changed=True) 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/LoopFusion]: LoopFusion finished after 0.605 seconds 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/SimplifySlice]: Running SimplifySlice 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/SimplifySlice]: Finished (changed=False) 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/SimplifySlice]: SimplifySlice finished after 0.023 seconds 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/LICM]: Running LICM 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/LICM]: Finished (changed=True) 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/LICM]: LICM finished after 0.045 seconds 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_0 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.080 seconds 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_1 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_1 finished after 0.078 seconds 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/Simplifier]: Finished (changed=True) 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier finished after 0.158 seconds 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/ValueNumbering]: Running ValueNumbering 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/ValueNumbering]: Finished (changed=True) 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/ValueNumbering]: ValueNumbering finished after 0.087 seconds 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/LICM]: Running LICM 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/LICM]: Finished (changed=False) 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/LICM]: LICM finished after 0.042 seconds 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/PadElimination]: Running PadElimination 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/PadElimination]: Finished (changed=False) 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/PadElimination]: PadElimination finished after 0.010 seconds 2025-11-09T20:53:32Z INFO 252 [sg0000/Tensorizer/Delinearization]: Running Delinearization 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/Delinearization]: Finished (changed=False) 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/Delinearization]: Delinearization finished after 0.091 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.083 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Running LoopFusion_iteration_0 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/LoopFusion]: LoopFusion_iteration_0 finished after 0.149 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/LoopFusion]: Finished (changed=False) 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/LoopFusion]: LoopFusion finished after 0.237 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/GenericAccessSimplifier]: Finished (changed=False) 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.022 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_0 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.077 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/Simplifier]: Finished (changed=False) 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier finished after 0.078 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/LICM]: Running LICM 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/LICM]: Finished (changed=True) 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/LICM]: LICM finished after 0.043 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/ValueNumbering]: Running ValueNumbering 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/ValueNumbering]: Finished (changed=False) 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/ValueNumbering]: ValueNumbering finished after 0.067 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/TCTransform]: Running TCTransform 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/TCTransform]: Finished (changed=True) 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/TCTransform]: TCTransform finished after 0.025 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/CommuteConcat]: Running CommuteConcat 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/CommuteConcat]: Running CommuteConcat_iteration_0 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/CommuteConcat]: CommuteConcat_iteration_0 finished after 0.024 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/CommuteConcat]: Finished (changed=False) 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/CommuteConcat]: CommuteConcat finished after 0.024 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/RecognizeOpIdiom]: Running RecognizeOpIdiom 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/RecognizeOpIdiom]: Running RecognizeOpIdiom_iteration_0 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/RecognizeOpIdiom]: RecognizeOpIdiom_iteration_0 finished after 0.120 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/RecognizeOpIdiom]: Finished (changed=False) 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/RecognizeOpIdiom]: RecognizeOpIdiom finished after 0.120 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/MaskPropagation]: Running MaskPropagation 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/MaskPropagation]: Finished (changed=False) 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/MaskPropagation]: MaskPropagation finished after 0.088 seconds 2025-11-09T20:53:33Z INFO 252 [sg0000/Tensorizer/DeadStoreElimination]: Running DeadStoreElimination 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/DeadStoreElimination]: Finished (changed=False) 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/DeadStoreElimination]: DeadStoreElimination finished after 0.805 seconds 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/Recompute]: Running Recompute 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/Recompute]: Finished (changed=False) 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/Recompute]: Recompute finished after 0.006 seconds 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination_iteration_0 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/DeadCodeElimination]: DeadCodeElimination_iteration_0 finished after 0.025 seconds 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/DeadCodeElimination]: Finished (changed=False) 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/DeadCodeElimination]: DeadCodeElimination finished after 0.025 seconds 2025-11-09T20:53:34Z INFO 252 [Tensorizer]: After optimization: 958 statements 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/DoNothing]: Running DoNothing 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/DoNothing]: Finished (changed=True) 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/DoNothing]: DoNothing finished after 0.000 seconds 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/MutateDataType]: Running MutateDataType 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/MutateDataType]: Finished (changed=False) 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/MutateDataType]: MutateDataType finished after 0.031 seconds 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/GenericAccessSimplifier]: Running GenericAccessSimplifier 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/GenericAccessSimplifier]: Finished (changed=False) 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/GenericAccessSimplifier]: GenericAccessSimplifier finished after 0.022 seconds 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/Simplifier]: Running Simplifier_iteration_0 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier_iteration_0 finished after 0.078 seconds 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/Simplifier]: Finished (changed=False) 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/Simplifier]: Simplifier finished after 0.078 seconds 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/TileCCOps]: Running TileCCOps 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/TileCCOps]: pass did not tile CC tensor due to `multi_rank_size=16384 is not above min_allgather_tile_size_in_bytes=8388608` 2025-11-09T20:53:34Z INFO 252 [sg0000/Tensorizer/TileCCOps]: in bfloat16 (2048, 4) %'all_gather.1' = AllGatherOp-402 AllGather_add(bfloat16 (512, 4) %'transpose.1', replica_groups = [[0, 1, 2, 3]],all_gather_dim = DimensionSet((2048, 4), {0}),stream_id = -1) # dl = tensor_op_name: _all-gather.50 | hlo_id: 50 | , id = 402 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/TileCCOps]: pass did not tile CC tensor due to `All gather output tensor check failed` 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/TileCCOps]: in float32 (1024, 4) %'all_gather.2' = AllGatherOp-7393 AllGather_add(float32 (256, 4) %'transpose.228', replica_groups = [[0, 1, 2, 3]],all_gather_dim = DimensionSet((1024, 4), {0}),stream_id = -1) # dl = tensor_op_name: _all-gather.9766 | hlo_id: 9766 | , id = 7393 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/TileCCOps]: pass did not tile CC tensor due to `multi_rank_size=16384 is not above min_allgather_tile_size_in_bytes=8388608` 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/TileCCOps]: in uint32 (1024, 4) %'all_gather.3' = AllGatherOp-7409 AllGather_add(uint32 (256, 4) %'transpose.229', replica_groups = [[0, 1, 2, 3]],all_gather_dim = DimensionSet((1024, 4), {0}),stream_id = -1) # dl = tensor_op_name: _all-gather.9905 | hlo_id: 9905 | , id = 7409 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/TileCCOps]: Finished (changed=False) 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/TileCCOps]: TileCCOps finished after 0.307 seconds 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/DelinearIndices]: Running DelinearIndices 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/DelinearIndices]: Finished (changed=True) 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.263 seconds 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/Delinearization]: Running Delinearization 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/Delinearization]: Finished (changed=False) 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/Delinearization]: Delinearization finished after 0.087 seconds 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/DelinearIndices]: Running DelinearIndices 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/DelinearIndices]: Finished (changed=False) 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.212 seconds 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/DeadCodeElimination]: Running DeadCodeElimination_iteration_0 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/DeadCodeElimination]: DeadCodeElimination_iteration_0 finished after 0.024 seconds 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/DeadCodeElimination]: Finished (changed=False) 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/DeadCodeElimination]: DeadCodeElimination finished after 0.025 seconds 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/LateLowerReshapeOp]: Running LateLowerReshapeOp 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/LateLowerReshapeOp]: Finished (changed=False) 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/LateLowerReshapeOp]: LateLowerReshapeOp finished after 0.029 seconds 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/InferIntrinsicOnCC]: Running InferIntrinsicOnCC 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/InferIntrinsicOnCC]: Finished (changed=False) 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/InferIntrinsicOnCC]: InferIntrinsicOnCC finished after 0.266 seconds 2025-11-09T20:53:35Z INFO 252 [sg0000/Tensorizer/ResolveAccessConflict]: Running ResolveAccessConflict 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/ResolveAccessConflict]: Running DeadCodeElimination_iteration_0 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/ResolveAccessConflict]: DeadCodeElimination_iteration_0 finished after 0.026 seconds 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/ResolveAccessConflict]: Running DeadCodeElimination_iteration_1 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/ResolveAccessConflict]: DeadCodeElimination_iteration_1 finished after 0.025 seconds 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/ResolveAccessConflict]: Finished (changed=True) 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/ResolveAccessConflict]: ResolveAccessConflict finished after 0.166 seconds 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/LICM]: Running LICM 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/LICM]: Finished (changed=True) 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/LICM]: LICM finished after 0.048 seconds 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/LocalLayoutOpt]: Running LocalLayoutOpt 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/LocalLayoutOpt]: Finished (changed=False) 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/LocalLayoutOpt]: LocalLayoutOpt finished after 0.514 seconds 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/DelinearIndices]: Running DelinearIndices 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/DelinearIndices]: Finished (changed=False) 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.223 seconds 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/PGLayoutTilingPipeline]: Running PGLayoutTilingPipeline 2025-11-09T20:53:36Z INFO 252 [sg0000/Tensorizer/LowerCCOpBlockAxis]: Running LowerCCOpBlockAxis 2025-11-09T20:53:37Z INFO 252 [sg0000/Tensorizer/LowerCCOpBlockAxis]: Finished (changed=False) 2025-11-09T20:53:37Z INFO 252 [sg0000/Tensorizer/LowerCCOpBlockAxis]: LowerCCOpBlockAxis finished after 0.254 seconds 2025-11-09T20:53:37Z INFO 252 [sg0000/Tensorizer/LayoutPreprocessingAndAnalysis]: Running LayoutPreprocessingAndAnalysis 2025-11-09T20:53:37Z INFO 252 [sg0000/Tensorizer/LayoutPreprocessing]: Running LayoutPreprocessing 2025-11-09T20:53:37Z INFO 252 [sg0000/Tensorizer/Delinearization]: Running Delinearization 2025-11-09T20:53:37Z INFO 252 [sg0000/Tensorizer/Delinearization]: Finished (changed=False) 2025-11-09T20:53:37Z INFO 252 [sg0000/Tensorizer/Delinearization]: Delinearization finished after 0.092 seconds 2025-11-09T20:53:37Z INFO 252 [sg0000/Tensorizer/LayoutPreprocessing]: Finished (changed=True) 2025-11-09T20:53:37Z INFO 252 [sg0000/Tensorizer/LayoutPreprocessing]: LayoutPreprocessing finished after 0.703 seconds 2025-11-09T20:53:37Z INFO 252 [sg0000/Tensorizer/LayoutRequirementAnalysis]: Running LayoutRequirementAnalysis 2025-11-09T20:53:38Z INFO 252 [sg0000/Tensorizer/LayoutRequirementAnalysis]: LayoutRequirementAnalysis finished after 0.408 seconds 2025-11-09T20:53:38Z INFO 252 [sg0000/Tensorizer/LayoutPreprocessingAndAnalysis]: LayoutPreprocessingAndAnalysis finished after 1.114 seconds 2025-11-09T20:53:38Z INFO 252 [sg0000/Tensorizer/InferNonlocalTensors]: Running InferNonlocalTensors 2025-11-09T20:53:38Z INFO 252 [sg0000/Tensorizer/InferNonlocalTensors]: prefer_non_broadcast_par: True 2025-11-09T20:53:39Z INFO 252 [sg0000/Tensorizer/InferNonlocalTensors]: prefer_non_broadcast_par: True 2025-11-09T20:53:41Z INFO 252 [sg0000/Tensorizer/InferNonlocalTensors]: Finished (changed=False) 2025-11-09T20:53:41Z INFO 252 [sg0000/Tensorizer/InferNonlocalTensors]: InferNonlocalTensors finished after 3.071 seconds 2025-11-09T20:53:41Z INFO 252 [sg0000/Tensorizer/PAGLayoutOpt]: Running PAGLayoutOpt 2025-11-09T20:53:41Z INFO 252 [sg0000/Tensorizer/ParAxesAnnotation]: Running ParAxesAnnotation 2025-11-09T20:53:41Z INFO 252 [sg0000/Tensorizer/LayoutSearchAlgorithm]: prefer_non_broadcast_par: True 2025-11-09T20:53:51Z INFO 252 [sg0000/Tensorizer/ParAxesAnnotation]: Finished (changed=True) 2025-11-09T20:53:51Z INFO 252 [sg0000/Tensorizer/ParAxesAnnotation]: ParAxesAnnotation finished after 10.237 seconds 2025-11-09T20:53:51Z INFO 252 [sg0000/Tensorizer/InsertLocalTransposes]: Running InsertLocalTransposes 2025-11-09T20:53:52Z INFO 252 [sg0000/Tensorizer/InsertLocalTransposes]: Finished (changed=True) 2025-11-09T20:53:52Z INFO 252 [sg0000/Tensorizer/InsertLocalTransposes]: InsertLocalTransposes finished after 0.854 seconds 2025-11-09T20:53:52Z INFO 252 [sg0000/Tensorizer/PAGLayoutOpt]: PAGLayoutOpt finished after 11.095 seconds 2025-11-09T20:53:52Z INFO 252 [sg0000/Tensorizer/DelinearizeSPMD]: Running DelinearizeSPMD 2025-11-09T20:53:52Z INFO 252 [sg0000/Tensorizer/Delinearization]: Running Delinearization 2025-11-09T20:53:52Z INFO 252 [sg0000/Tensorizer/Delinearization]: Finished (changed=False) 2025-11-09T20:53:52Z INFO 252 [sg0000/Tensorizer/Delinearization]: Delinearization finished after 0.112 seconds 2025-11-09T20:53:52Z INFO 252 [sg0000/Tensorizer/DelinearizeSPMD]: Finished (changed=False) 2025-11-09T20:53:52Z INFO 252 [sg0000/Tensorizer/DelinearizeSPMD]: DelinearizeSPMD finished after 0.144 seconds 2025-11-09T20:53:52Z INFO 252 [sg0000/Tensorizer/ShardingPropagationAnalysis]: Running ShardingPropagationAnalysis 2025-11-09T20:53:53Z INFO 252 [sg0000/Tensorizer/ShardingPropagationAnalysis]: ShardingPropagationAnalysis finished after 0.589 seconds 2025-11-09T20:53:53Z INFO 252 [sg0000/Tensorizer/InferShardAxis]: Running InferShardAxis 2025-11-09T20:53:55Z INFO 252 [sg0000/Tensorizer/ShardResult]: =================== Dumping Debug Info ===================== 2025-11-09T20:53:55Z INFO 252 [sg0000/Tensorizer/ShardResult]: ------------------ Sharding summary ------------------ total number of dags: 1213 total number of sharded dags: 369 total bytes transferred from input, output, non local tensors: 877832872 total bytes transferred from input, output, non local tensors with 2x bandwidths: 869177892 % bytes transferred with 2x bandwidths: 99.01 NC0 FLOPs: 1745889421 NC1 FLOPs: 1729034304 % FLOPs sharded: 99.50 Shard dim: 2, Number of dags: 168 Matmuls sharded with this dim: [2,2(s),64] @ [2(s),64] = [2] Number of occurrences: 28 [2,2(s),64] @ [2(s),64,128] = [2,128] Number of occurrences: 28 Shard dim: 2048, Number of dags: 112 Matmuls sharded with this dim: [4,2,2,128] @ [2,2,128,2048(s)] = [4,2048(s)] Number of occurrences: 28 [4,2048(s)] @ [2048(s),2,128] = [4,2,128] Number of occurrences: 28 [4,2048(s)] @ [2048(s),2,2,2,64] = [4,2,2,2,64] Number of occurrences: 28 [4,2048(s)] @ [2048(s),2,2,64] = [4,2,2,64] Number of occurrences: 28 Shard dim: 1536, Number of dags: 84 Matmuls sharded with this dim: [4,1536(s)] @ [1536(s),2048] = [4,2048] Number of occurrences: 28 [4,2048] @ [2048,1536(s)] = [4,1536(s)] Number of occurrences: 56 Shard dim: 4, Number of dags: 2 Matmuls sharded with this dim: Shard dim: 256, Number of dags: 1 Matmuls sharded with this dim: Shard dim: 37984, Number of dags: 1 Matmuls sharded with this dim: [4,2048] @ [2048,37984(s)] = [4,37984(s)] Number of occurrences: 1 Shard dim: 512, Number of dags: 1 Matmuls sharded with this dim: 2025-11-09T20:53:56Z INFO 252 [sg0000/Tensorizer/DelinearIndices]: Running DelinearIndices 2025-11-09T20:53:56Z INFO 252 [sg0000/Tensorizer/DelinearIndices]: Finished (changed=True) 2025-11-09T20:53:56Z INFO 252 [sg0000/Tensorizer/DelinearIndices]: DelinearIndices finished after 0.460 seconds 2025-11-09T20:53:56Z INFO 252 [sg0000/Tensorizer/RemoveShardedPartitionAxes]: Running RemoveShardedPartitionAxes 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/RemoveShardedPartitionAxes]: Finished (changed=True) 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/RemoveShardedPartitionAxes]: RemoveShardedPartitionAxes finished after 0.615 seconds 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/InferShardAxis]: Finished (changed=True) 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/InferShardAxis]: InferShardAxis finished after 4.046 seconds 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/MaskPropagation]: Running MaskPropagation 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/MaskPropagation]: Finished (changed=False) 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/MaskPropagation]: MaskPropagation finished after 0.110 seconds 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/CanonicalizeDAGForPGTiling]: Running CanonicalizeDAGForPGTiling 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/CanonicalizeDAGForPGTiling]: Finished (changed=True) 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/CanonicalizeDAGForPGTiling]: CanonicalizeDAGForPGTiling finished after 0.151 seconds 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/LowerCCOpBlockAxis]: Running LowerCCOpBlockAxis 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/LowerCCOpBlockAxis]: Finished (changed=False) 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/LowerCCOpBlockAxis]: LowerCCOpBlockAxis finished after 0.179 seconds 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/PGTiling]: Running PGTiling 2025-11-09T20:53:57Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: Running AGOrderingAnalysisPass 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 7662 of IO tensor {'CrossPassTensor': ''}bfloat16 %input4|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (130, 'AG2572'), (274, 'AG2565'), (158, 'AG2570')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 7956 of IO tensor {'CrossPassTensor': ''}bfloat16 %input6|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (131, 'AG2581'), (274, 'AG2565'), (159, 'AG2579')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 8207 of IO tensor {'CrossPassTensor': ''}bfloat16 %input8|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (132, 'AG2590'), (274, 'AG2565'), (160, 'AG2588')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 8458 of IO tensor {'CrossPassTensor': ''}bfloat16 %input10|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (133, 'AG2599'), (274, 'AG2565'), (161, 'AG2597')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 8709 of IO tensor {'CrossPassTensor': ''}bfloat16 %input12|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (134, 'AG2608'), (274, 'AG2565'), (162, 'AG2606')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 8960 of IO tensor {'CrossPassTensor': ''}bfloat16 %input14|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (135, 'AG2617'), (274, 'AG2565'), (163, 'AG2615')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 9211 of IO tensor {'CrossPassTensor': ''}bfloat16 %input16|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (136, 'AG2626'), (274, 'AG2565'), (164, 'AG2624')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 9462 of IO tensor {'CrossPassTensor': ''}bfloat16 %input18|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (137, 'AG2635'), (274, 'AG2565'), (165, 'AG2633')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 9713 of IO tensor {'CrossPassTensor': ''}bfloat16 %input20|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (138, 'AG2644'), (274, 'AG2565'), (166, 'AG2642')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 9964 of IO tensor {'CrossPassTensor': ''}bfloat16 %input22|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (139, 'AG2653'), (274, 'AG2565'), (167, 'AG2651')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 10215 of IO tensor {'CrossPassTensor': ''}bfloat16 %input24|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (140, 'AG2662'), (274, 'AG2565'), (168, 'AG2660')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 10466 of IO tensor {'CrossPassTensor': ''}bfloat16 %input26|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (141, 'AG2671'), (274, 'AG2565'), (169, 'AG2669')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 10717 of IO tensor {'CrossPassTensor': ''}bfloat16 %input28|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (142, 'AG2680'), (274, 'AG2565'), (170, 'AG2678')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 10968 of IO tensor {'CrossPassTensor': ''}bfloat16 %input30|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (143, 'AG2689'), (274, 'AG2565'), (171, 'AG2687')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 11219 of IO tensor {'CrossPassTensor': ''}bfloat16 %input32|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (144, 'AG2698'), (274, 'AG2565'), (172, 'AG2696')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 11470 of IO tensor {'CrossPassTensor': ''}bfloat16 %input34|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (145, 'AG2707'), (274, 'AG2565'), (173, 'AG2705')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 11721 of IO tensor {'CrossPassTensor': ''}bfloat16 %input36|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (146, 'AG2716'), (274, 'AG2565'), (174, 'AG2714')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 11972 of IO tensor {'CrossPassTensor': ''}bfloat16 %input38|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (147, 'AG2725'), (274, 'AG2565'), (175, 'AG2723')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 12223 of IO tensor {'CrossPassTensor': ''}bfloat16 %input40|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (148, 'AG2734'), (274, 'AG2565'), (176, 'AG2732')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 12474 of IO tensor {'CrossPassTensor': ''}bfloat16 %input42|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (149, 'AG2743'), (274, 'AG2565'), (177, 'AG2741')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 12725 of IO tensor {'CrossPassTensor': ''}bfloat16 %input44|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (150, 'AG2752'), (274, 'AG2565'), (178, 'AG2750')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 12976 of IO tensor {'CrossPassTensor': ''}bfloat16 %input46|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (151, 'AG2761'), (274, 'AG2565'), (179, 'AG2759')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 13227 of IO tensor {'CrossPassTensor': ''}bfloat16 %input48|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (152, 'AG2770'), (274, 'AG2565'), (180, 'AG2768')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 13478 of IO tensor {'CrossPassTensor': ''}bfloat16 %input50|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (153, 'AG2779'), (274, 'AG2565'), (181, 'AG2777')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 13729 of IO tensor {'CrossPassTensor': ''}bfloat16 %input52|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (154, 'AG2788'), (274, 'AG2565'), (182, 'AG2786')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 13980 of IO tensor {'CrossPassTensor': ''}bfloat16 %input54|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (155, 'AG2797'), (274, 'AG2565'), (183, 'AG2795')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 14231 of IO tensor {'CrossPassTensor': ''}bfloat16 %input56|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (156, 'AG2806'), (274, 'AG2565'), (184, 'AG2804')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 14482 of IO tensor {'CrossPassTensor': ''}bfloat16 %input58|NHWC|(4, 2, 16, 128, 2, 64) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (157, 'AG2815'), (274, 'AG2565'), (185, 'AG2813')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 7876 of IO tensor non_local bfloat16 %all_reduce.1(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 7909 of IO tensor non_local bfloat16 %all_reduce.3(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 8127 of IO tensor non_local bfloat16 %all_reduce.5(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 8160 of IO tensor non_local bfloat16 %all_reduce.7(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 8378 of IO tensor non_local bfloat16 %all_reduce.9(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 8411 of IO tensor non_local bfloat16 %all_reduce.11(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 8629 of IO tensor non_local bfloat16 %all_reduce.13(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 8662 of IO tensor non_local bfloat16 %all_reduce.15(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 8880 of IO tensor non_local bfloat16 %all_reduce.17(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 8913 of IO tensor non_local bfloat16 %all_reduce.19(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 9131 of IO tensor non_local bfloat16 %all_reduce.21(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 9164 of IO tensor non_local bfloat16 %all_reduce.23(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 9382 of IO tensor non_local bfloat16 %all_reduce.25(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 9415 of IO tensor non_local bfloat16 %all_reduce.27(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 9633 of IO tensor non_local bfloat16 %all_reduce.29(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 9666 of IO tensor non_local bfloat16 %all_reduce.31(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 9884 of IO tensor non_local bfloat16 %all_reduce.33(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 9917 of IO tensor non_local bfloat16 %all_reduce.35(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 10135 of IO tensor non_local bfloat16 %all_reduce.37(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 10168 of IO tensor non_local bfloat16 %all_reduce.39(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 10386 of IO tensor non_local bfloat16 %all_reduce.41(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 10419 of IO tensor non_local bfloat16 %all_reduce.43(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 10637 of IO tensor non_local bfloat16 %all_reduce.45(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 10670 of IO tensor non_local bfloat16 %all_reduce.47(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 10888 of IO tensor non_local bfloat16 %all_reduce.49(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 10921 of IO tensor non_local bfloat16 %all_reduce.51(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 11139 of IO tensor non_local bfloat16 %all_reduce.53(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 11172 of IO tensor non_local bfloat16 %all_reduce.55(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 11390 of IO tensor non_local bfloat16 %all_reduce.57(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 11423 of IO tensor non_local bfloat16 %all_reduce.59(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 11641 of IO tensor non_local bfloat16 %all_reduce.61(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 11674 of IO tensor non_local bfloat16 %all_reduce.63(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 11892 of IO tensor non_local bfloat16 %all_reduce.65(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 11925 of IO tensor non_local bfloat16 %all_reduce.67(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 12143 of IO tensor non_local bfloat16 %all_reduce.69(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 12176 of IO tensor non_local bfloat16 %all_reduce.71(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 12394 of IO tensor non_local bfloat16 %all_reduce.73(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 12427 of IO tensor non_local bfloat16 %all_reduce.75(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 12645 of IO tensor non_local bfloat16 %all_reduce.77(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 12678 of IO tensor non_local bfloat16 %all_reduce.79(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 12896 of IO tensor non_local bfloat16 %all_reduce.81(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 12929 of IO tensor non_local bfloat16 %all_reduce.83(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 13147 of IO tensor non_local bfloat16 %all_reduce.85(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 13180 of IO tensor non_local bfloat16 %all_reduce.87(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 13398 of IO tensor non_local bfloat16 %all_reduce.89(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 13431 of IO tensor non_local bfloat16 %all_reduce.91(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 13649 of IO tensor non_local bfloat16 %all_reduce.93(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 13682 of IO tensor non_local bfloat16 %all_reduce.95(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 13900 of IO tensor non_local bfloat16 %all_reduce.97(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 13933 of IO tensor non_local bfloat16 %all_reduce.99(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 14151 of IO tensor non_local bfloat16 %all_reduce.101(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 14184 of IO tensor non_local bfloat16 %all_reduce.103(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 14402 of IO tensor non_local bfloat16 %all_reduce.105(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 14435 of IO tensor non_local bfloat16 %all_reduce.107(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 14653 of IO tensor non_local bfloat16 %all_reduce.109(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 14686 of IO tensor non_local bfloat16 %all_reduce.111(4, 2, 1024) is not sorted, index list (w/ AG ids): [(129, 'AG2566'), (1, 'AG2568')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 20776 of IO tensor non_local uint32 %get_tuple_element.4(4, 2, 128) is not sorted, index list (w/ AG ids): [(42, 'AG2830'), (5, 'AG2833')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: WARNING: non P dims of loadstore 14742 of IO tensor non_local int32 %gather.2|NC|(4, 256) is not sorted, index list (w/ AG ids): [(42, 'AG2830'), (5, 'AG2833')] 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/AGOrderingAnalysisPass]: AGOrderingAnalysisPass finished after 2.378 seconds 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/StaticTransposeLocalTensor]: Running StaticTransposeLocalTensor 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/StaticTransposeLocalTensor]: Finished (changed=True) 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/StaticTransposeLocalTensor]: StaticTransposeLocalTensor finished after 0.262 seconds 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/PComputeCutting]: Running PComputeCutting 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/PComputeCutting]: Finished (changed=True) 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/PComputeCutting]: PComputeCutting finished after 0.283 seconds 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/BFComputeCutting]: Running BFComputeCutting 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/BFComputeCutting]: Finished (changed=True) 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/BFComputeCutting]: BFComputeCutting finished after 0.073 seconds 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/LoopSplitting]: Running LoopSplitting 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/LoopSplitting]: Finished (changed=False) 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/LoopSplitting]: LoopSplitting finished after 0.026 seconds 2025-11-09T20:54:00Z INFO 252 [sg0000/Tensorizer/MacroGeneration]: Running MacroGeneration 2025-11-09T20:54:02Z INFO 252 [sg0000/Tensorizer/MacroGeneration]: Finished (changed=True) 2025-11-09T20:54:02Z INFO 252 [sg0000/Tensorizer/MacroGeneration]: MacroGeneration finished after 1.907 seconds 2025-11-09T20:54:02Z INFO 252 [sg0000/Tensorizer/PGTiling]: PGTiling finished after 4.958 seconds 2025-11-09T20:54:02Z INFO 252 [sg0000/Tensorizer/InsertIOTransposes]: Running InsertIOTransposes 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/InsertIOTransposes]: Finished (changed=True) 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/InsertIOTransposes]: InsertIOTransposes finished after 1.581 seconds 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/InsertOffloadedTransposes]: Running InsertOffloadedTransposes 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/InsertOffloadedTransposes]: OffloadedTranspose inserted: 0 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/InsertOffloadedTransposes]: Finished (changed=False) 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/InsertOffloadedTransposes]: InsertOffloadedTransposes finished after 0.078 seconds 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/DramToDramTranspose]: Running DramToDramTranspose 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/DramToDramTranspose]: Finished (changed=True) 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/DramToDramTranspose]: DramToDramTranspose finished after 0.280 seconds 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/PGLayoutTilingPipeline]: PGLayoutTilingPipeline finished after 27.679 seconds 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingProfiler]: Running TilingProfiler 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 20 MACROS WITH LARGEST INSTRUCTION COUNTS: 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 4768: transpose_128x128 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 4768: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 298: transpose_128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingProfiler]: Finished (changed=False) 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/TilingProfiler]: TilingProfiler finished after 0.332 seconds 2025-11-09T20:54:04Z INFO 252 [sg0000/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop 2025-11-09T20:54:05Z INFO 252 [sg0000/Tensorizer/FlattenMacroLoop]: Finished (changed=True) 2025-11-09T20:54:05Z INFO 252 [sg0000/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.243 seconds 2025-11-09T20:54:05Z INFO 252 [sg0000/Tensorizer/InferNeuronTensor]: Running InferNeuronTensor 2025-11-09T20:54:05Z INFO 252 [sg0000/Tensorizer/InferNeuronTensor]: Running InferNeuronTensor_iteration_0 2025-11-09T20:54:05Z WARNING 252 [sg0000/Tensorizer/InferNeuronTensor]: Large tensor demoted to DRAM: uint8 %scatter.1(2, 128, 4), [B, F, F], 512 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/InferNeuronTensor]: InferNeuronTensor_iteration_0 finished after 1.374 seconds 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/InferNeuronTensor]: Running InferNeuronTensor_iteration_1 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/InferNeuronTensor]: InferNeuronTensor_iteration_1 finished after 0.053 seconds 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/InferNeuronTensor]: Finished (changed=True) 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/InferNeuronTensor]: InferNeuronTensor finished after 1.427 seconds 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.252 seconds 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: Finished (changed=False) 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.252 seconds 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/LICM]: Running LICM 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/LICM]: Finished (changed=True) 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/LICM]: LICM finished after 0.085 seconds 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/RewriteReplicationMatmul]: Running RewriteReplicationMatmul 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/RewriteReplicationMatmul]: Finished (changed=False) 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/RewriteReplicationMatmul]: RewriteReplicationMatmul finished after 0.038 seconds 2025-11-09T20:54:06Z INFO 252 [sg0000/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop 2025-11-09T20:54:07Z INFO 252 [sg0000/Tensorizer/FlattenMacroLoop]: Finished (changed=True) 2025-11-09T20:54:07Z INFO 252 [sg0000/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.146 seconds 2025-11-09T20:54:07Z INFO 252 [sg0000/Tensorizer/SimplifyMacroPredicates]: Running SimplifyMacroPredicates 2025-11-09T20:54:07Z INFO 252 [sg0000/Tensorizer/SimplifyMacroPredicates]: Finished (changed=True) 2025-11-09T20:54:07Z INFO 252 [sg0000/Tensorizer/SimplifyMacroPredicates]: SimplifyMacroPredicates finished after 0.115 seconds 2025-11-09T20:54:07Z INFO 252 [sg0000/Tensorizer/DataLocalityOpt]: Running DataLocalityOpt 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/DataLocalityOpt]: Finished (changed=True) 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/DataLocalityOpt]: DataLocalityOpt finished after 3.034 seconds 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/DMATilingProfiler]: Running DMATilingProfiler 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 20 MACROS WITH LARGEST INSTRUCTION COUNTS: 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 4768: transpose_128x128 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 4768: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 298: transpose_128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/PostDLOTilingBottleneck]: 192: matmul_128x128x4 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/DMATilingProfiler]: Finished (changed=False) 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/DMATilingProfiler]: DMATilingProfiler finished after 0.090 seconds 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.321 seconds 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: Finished (changed=False) 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.321 seconds 2025-11-09T20:54:10Z INFO 252 [sg0000/Tensorizer/LegalizeSundaMacro]: Running LegalizeSundaMacro 2025-11-09T20:54:11Z INFO 252 [sg0000/Tensorizer/LegalizeSundaMacro]: Finished (changed=True) 2025-11-09T20:54:11Z INFO 252 [sg0000/Tensorizer/LegalizeSundaMacro]: LegalizeSundaMacro finished after 0.716 seconds 2025-11-09T20:54:11Z INFO 252 [sg0000/Tensorizer/InsertImplicitShardAxisBeforeISel]: Running InsertImplicitShardAxisBeforeISel 2025-11-09T20:54:11Z INFO 252 [sg0000/Tensorizer/InsertImplicitShardAxisBeforeISel]: Finished (changed=True) 2025-11-09T20:54:11Z INFO 252 [sg0000/Tensorizer/InsertImplicitShardAxisBeforeISel]: InsertImplicitShardAxisBeforeISel finished after 0.378 seconds 2025-11-09T20:54:11Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier 2025-11-09T20:54:11Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.443 seconds 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: Finished (changed=False) 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.443 seconds 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/PerfectLoopNest]: Running PerfectLoopNest 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/PerfectLoopNest]: Finished (changed=False) 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/PerfectLoopNest]: PerfectLoopNest finished after 0.060 seconds 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/FlattenMacroLoop]: Finished (changed=True) 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.234 seconds 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/RewriteWeights]: Running RewriteWeights 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/RewriteWeights]: Finished (changed=True) 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/RewriteWeights]: RewriteWeights finished after 0.064 seconds 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/ReshapeWeights]: Running ReshapeWeights 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/ReshapeWeights]: Finished (changed=True) 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/ReshapeWeights]: ReshapeWeights finished after 0.021 seconds 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/FlattenMacroLoop]: Running FlattenMacroLoop 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/FlattenMacroLoop]: Finished (changed=False) 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/FlattenMacroLoop]: FlattenMacroLoop finished after 0.080 seconds 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/SimplifyMacroPredicates]: Running SimplifyMacroPredicates 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/SimplifyMacroPredicates]: Finished (changed=True) 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/SimplifyMacroPredicates]: SimplifyMacroPredicates finished after 0.255 seconds 2025-11-09T20:54:12Z INFO 252 [sg0000/Tensorizer/InferInitValue]: Running InferInitValue 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/InferInitValue]: Finished (changed=True) 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/InferInitValue]: InferInitValue finished after 1.304 seconds 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: Running NeuronSimplifier_iteration_0 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier_iteration_0 finished after 0.447 seconds 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: Finished (changed=False) 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/NeuronSimplifier]: NeuronSimplifier finished after 0.448 seconds 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/SimplifyTensor]: Running SimplifyTensor 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/SimplifyTensor]: Running DeadCodeElimination_iteration_0 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/SimplifyTensor]: DeadCodeElimination_iteration_0 finished after 0.066 seconds 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/SimplifyTensor]: Finished (changed=True) 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/SimplifyTensor]: SimplifyTensor finished after 0.237 seconds 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/LICM]: Running LICM 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/LICM]: Finished (changed=True) 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/LICM]: LICM finished after 0.108 seconds 2025-11-09T20:54:14Z INFO 252 [sg0000/Tensorizer/SundaISel]: Running SundaISel 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/SundaISel]: Finished (changed=True) 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/SundaISel]: SundaISel finished after 1.340 seconds 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/NeuronAliasDependencyReset]: Running NeuronAliasDependencyReset 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/AliasDependencyElimination]: Running AliasDependencyElimination 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/AliasDependencyElimination]: Finished (changed=True) 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/AliasDependencyElimination]: AliasDependencyElimination finished after 0.002 seconds 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/NeuronAliasDependencyInduction]: Running NeuronAliasDependencyInduction 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/NeuronAliasDependencyInduction]: Finished (changed=True) 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/NeuronAliasDependencyInduction]: NeuronAliasDependencyInduction finished after 0.014 seconds 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/NeuronAliasDependencyReset]: NeuronAliasDependencyReset finished after 0.019 seconds 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/LowerComplexBroadcast]: Running LowerComplexBroadcast 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/LowerComplexBroadcast]: Finished (changed=False) 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/LowerComplexBroadcast]: LowerComplexBroadcast finished after 0.061 seconds 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/NeuronLoopInterchange]: Running NeuronLoopInterchange 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/NeuronLoopInterchange]: Finished (changed=True) 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/NeuronLoopInterchange]: NeuronLoopInterchange finished after 0.061 seconds 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=True) 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.197 seconds 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion 2025-11-09T20:54:16Z INFO 252 [sg0000/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion_iteration_0 2025-11-09T20:54:17Z INFO 252 [sg0000/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion_iteration_0 finished after 0.580 seconds 2025-11-09T20:54:17Z INFO 252 [sg0000/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion_iteration_1 2025-11-09T20:54:17Z INFO 252 [sg0000/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion_iteration_1 finished after 0.226 seconds 2025-11-09T20:54:17Z INFO 252 [sg0000/Tensorizer/NeuronLoopFusion]: Running NeuronLoopFusion_iteration_2 2025-11-09T20:54:17Z INFO 252 [sg0000/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion_iteration_2 finished after 0.190 seconds 2025-11-09T20:54:17Z INFO 252 [sg0000/Tensorizer/NeuronLoopFusion]: Finished (changed=True) 2025-11-09T20:54:17Z INFO 252 [sg0000/Tensorizer/NeuronLoopFusion]: NeuronLoopFusion finished after 0.997 seconds 2025-11-09T20:54:17Z INFO 252 [sg0000/Tensorizer/NeuronLoopInterchange]: Running NeuronLoopInterchange 2025-11-09T20:54:17Z INFO 252 [sg0000/Tensorizer/NeuronLoopInterchange]: Finished (changed=False) 2025-11-09T20:54:17Z INFO 252 [sg0000/Tensorizer/NeuronLoopInterchange]: NeuronLoopInterchange finished after 0.050 seconds 2025-11-09T20:54:17Z INFO 252 [sg0000/Tensorizer/NeuronLICM]: Running NeuronLICM 2025-11-09T20:54:18Z INFO 252 [sg0000/Tensorizer/NeuronLICM]: Finished (changed=True) 2025-11-09T20:54:18Z INFO 252 [sg0000/Tensorizer/NeuronLICM]: NeuronLICM finished after 1.031 seconds 2025-11-09T20:54:18Z INFO 252 [sg0000/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims 2025-11-09T20:54:19Z INFO 252 [sg0000/Tensorizer/FactorizeBlkDims]: Finished (changed=True) 2025-11-09T20:54:19Z INFO 252 [sg0000/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.486 seconds 2025-11-09T20:54:19Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: Running NeuronInstComb 2025-11-09T20:54:19Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0 2025-11-09T20:54:20Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 1.650 seconds 2025-11-09T20:54:20Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_1 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_1 finished after 0.158 seconds 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_2 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_2 finished after 0.132 seconds 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: Finished (changed=True) 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 1.952 seconds 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronValueNumbering]: Finished (changed=False) 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.099 seconds 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: Running NeuronInstComb 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.147 seconds 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_1 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_1 finished after 0.135 seconds 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: Finished (changed=True) 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.288 seconds 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/InferSharedMemLoc]: Finished (changed=True) 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.072 seconds 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/VectorizeDMA]: Running VectorizeDMA 2025-11-09T20:54:21Z INFO 252 [sg0000/Tensorizer/VectorizeDMA]: Running VectorizeDMA_iteration_0 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/VectorizeDMA]: VectorizeDMA_iteration_0 finished after 0.481 seconds 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/VectorizeDMA]: Running VectorizeDMA_iteration_1 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/VectorizeDMA]: VectorizeDMA_iteration_1 finished after 0.037 seconds 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/VectorizeDMA]: Finished (changed=True) 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/VectorizeDMA]: VectorizeDMA finished after 0.519 seconds 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False) 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.110 seconds 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/LegalizePartitionReduce]: Running LegalizePartitionReduce 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/LegalizePartitionReduce]: Finished (changed=False) 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/LegalizePartitionReduce]: LegalizePartitionReduce finished after 0.037 seconds 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/DeConcat]: Running DeConcat 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/DeConcat]: Running DeConcat_iteration_0 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/DeConcat]: DeConcat_iteration_0 finished after 0.042 seconds 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/DeConcat]: Finished (changed=False) 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/DeConcat]: DeConcat finished after 0.042 seconds 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/FactorizeThreadAxesInFreeDims]: Running FactorizeThreadAxesInFreeDims 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/FactorizeThreadAxesInFreeDims]: Finished (changed=False) 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/FactorizeThreadAxesInFreeDims]: FactorizeThreadAxesInFreeDims finished after 0.052 seconds 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/PartialSimdFusion]: Running PartialSimdFusion 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/PartialSimdFusion]: Running PartialSimdFusion_iteration_0 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/PartialSimdFusion]: PartialSimdFusion_iteration_0 finished after 0.529 seconds 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/PartialSimdFusion]: Finished (changed=True) 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/PartialSimdFusion]: PartialSimdFusion finished after 0.530 seconds 2025-11-09T20:54:22Z INFO 252 [sg0000/Tensorizer/TritiumFusion]: Running TritiumFusion 2025-11-09T20:54:23Z INFO 252 [sg0000/Tensorizer/TritiumFusion]: Finished (changed=True) 2025-11-09T20:54:23Z INFO 252 [sg0000/Tensorizer/TritiumFusion]: TritiumFusion finished after 0.132 seconds 2025-11-09T20:54:23Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: Running CCOpFusion 2025-11-09T20:54:23Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: Running CCOpFusion_iteration_0 2025-11-09T20:54:23Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: CCOpFusion_iteration_0 finished after 0.386 seconds 2025-11-09T20:54:23Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: Finished (changed=False) 2025-11-09T20:54:23Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: CCOpFusion finished after 0.387 seconds 2025-11-09T20:54:23Z INFO 252 [sg0000/Tensorizer/VectorizeMatMult]: Running VectorizeMatMult 2025-11-09T20:54:23Z INFO 252 [sg0000/Tensorizer/VectorizeMatMult]: Finished (changed=False) 2025-11-09T20:54:23Z INFO 252 [sg0000/Tensorizer/VectorizeMatMult]: VectorizeMatMult finished after 0.046 seconds 2025-11-09T20:54:23Z INFO 252 [sg0000/Tensorizer/PartialLoopFusion]: Running PartialLoopFusion 2025-11-09T20:54:23Z INFO 252 [sg0000/Tensorizer/PartialLoopFusion]: Running PartialLoopFusion_iteration_0 2025-11-09T20:54:24Z INFO 252 [sg0000/Tensorizer/PartialLoopFusion]: PartialLoopFusion_iteration_0 finished after 1.097 seconds 2025-11-09T20:54:24Z INFO 252 [sg0000/Tensorizer/PartialLoopFusion]: Finished (changed=True) 2025-11-09T20:54:24Z INFO 252 [sg0000/Tensorizer/PartialLoopFusion]: PartialLoopFusion finished after 1.097 seconds 2025-11-09T20:54:24Z INFO 252 [sg0000/Tensorizer/NeuronLICM]: Running NeuronLICM 2025-11-09T20:54:24Z INFO 252 [sg0000/Tensorizer/NeuronLICM]: Finished (changed=True) 2025-11-09T20:54:24Z INFO 252 [sg0000/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.184 seconds 2025-11-09T20:54:24Z INFO 252 [sg0000/Tensorizer/LowerTranspose]: Running LowerTranspose 2025-11-09T20:54:25Z INFO 252 [sg0000/Tensorizer/LowerTranspose]: Finished (changed=True) 2025-11-09T20:54:25Z INFO 252 [sg0000/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.413 seconds 2025-11-09T20:54:25Z INFO 252 [sg0000/Tensorizer/LowerBroadcast]: Running LowerBroadcast 2025-11-09T20:54:25Z INFO 252 [sg0000/Tensorizer/LowerBroadcast]: Finished (changed=False) 2025-11-09T20:54:25Z INFO 252 [sg0000/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.046 seconds 2025-11-09T20:54:25Z INFO 252 [sg0000/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb 2025-11-09T20:54:25Z INFO 252 [sg0000/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0 2025-11-09T20:54:26Z INFO 252 [sg0000/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.821 seconds 2025-11-09T20:54:26Z INFO 252 [sg0000/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_1 2025-11-09T20:54:26Z INFO 252 [sg0000/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_1 finished after 0.131 seconds 2025-11-09T20:54:26Z INFO 252 [sg0000/Tensorizer/LateNeuronInstComb]: Finished (changed=True) 2025-11-09T20:54:26Z INFO 252 [sg0000/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.958 seconds 2025-11-09T20:54:26Z INFO 252 [sg0000/Tensorizer/SplitAccGrp]: Running SplitAccGrp 2025-11-09T20:54:26Z INFO 252 [sg0000/Tensorizer/SplitAccGrp]: Finished (changed=False) 2025-11-09T20:54:26Z INFO 252 [sg0000/Tensorizer/SplitAccGrp]: SplitAccGrp finished after 0.037 seconds 2025-11-09T20:54:26Z INFO 252 [sg0000/Tensorizer/SpillPSum]: Running SpillPSum 2025-11-09T20:54:26Z INFO 252 [sg0000/Tensorizer/SpillPSum]: Finished (changed=True) 2025-11-09T20:54:26Z INFO 252 [sg0000/Tensorizer/SpillPSum]: SpillPSum finished after 0.458 seconds 2025-11-09T20:54:26Z INFO 252 [sg0000/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics 2025-11-09T20:54:27Z INFO 252 [sg0000/Tensorizer/LowerIntrinsics]: Finished (changed=True) 2025-11-09T20:54:27Z INFO 252 [sg0000/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.899 seconds 2025-11-09T20:54:27Z INFO 252 [sg0000/Tensorizer/InlineNativeKernels]: Running InlineNativeKernels 2025-11-09T20:54:27Z INFO 252 [sg0000/Tensorizer/InlineNativeKernels]: Finished (changed=False) 2025-11-09T20:54:27Z INFO 252 [sg0000/Tensorizer/InlineNativeKernels]: InlineNativeKernels finished after 0.046 seconds 2025-11-09T20:54:27Z INFO 252 [sg0000/Tensorizer/LegalizeType]: Running LegalizeType 2025-11-09T20:54:27Z INFO 252 [sg0000/Tensorizer/LegalizeType]: Finished (changed=True) 2025-11-09T20:54:27Z INFO 252 [sg0000/Tensorizer/LegalizeType]: LegalizeType finished after 0.128 seconds 2025-11-09T20:54:27Z INFO 252 [sg0000/Tensorizer/NeuronLICM]: Running NeuronLICM 2025-11-09T20:54:28Z INFO 252 [sg0000/Tensorizer/NeuronLICM]: Finished (changed=True) 2025-11-09T20:54:28Z INFO 252 [sg0000/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.250 seconds 2025-11-09T20:54:28Z INFO 252 [sg0000/Tensorizer/InferPSumTensor]: Running InferPSumTensor 2025-11-09T20:54:28Z INFO 252 [sg0000/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0 2025-11-09T20:54:29Z INFO 252 [sg0000/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 1.384 seconds 2025-11-09T20:54:29Z INFO 252 [sg0000/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_1 2025-11-09T20:54:29Z INFO 252 [sg0000/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_1 finished after 0.481 seconds 2025-11-09T20:54:29Z INFO 252 [sg0000/Tensorizer/InferPSumTensor]: Finished (changed=True) 2025-11-09T20:54:29Z INFO 252 [sg0000/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 1.867 seconds 2025-11-09T20:54:29Z INFO 252 [sg0000/Tensorizer/WeightCoalescing]: Running WeightCoalescing 2025-11-09T20:54:29Z INFO 252 [sg0000/Tensorizer/WeightCoalescing]: Finished (changed=False) 2025-11-09T20:54:29Z INFO 252 [sg0000/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.049 seconds 2025-11-09T20:54:29Z INFO 252 [sg0000/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess 2025-11-09T20:54:30Z INFO 252 [sg0000/Tensorizer/LegalizeSundaAccess]: Finished (changed=True) 2025-11-09T20:54:30Z INFO 252 [sg0000/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.926 seconds 2025-11-09T20:54:30Z INFO 252 [sg0000/Tensorizer/RelaxPredicates]: Running RelaxPredicates 2025-11-09T20:54:30Z INFO 252 [sg0000/Tensorizer/RelaxPredicates]: Finished (changed=False) 2025-11-09T20:54:30Z INFO 252 [sg0000/Tensorizer/RelaxPredicates]: RelaxPredicates finished after 0.095 seconds 2025-11-09T20:54:30Z INFO 252 [sg0000/Tensorizer/TensorInitialization]: Running TensorInitialization 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/TensorInitialization]: Finished (changed=True) 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/TensorInitialization]: TensorInitialization finished after 0.167 seconds 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False) 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.128 seconds 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/ExpandISAMacro]: Finished (changed=False) 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.074 seconds 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.028 seconds 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/SimplifyNeuronTensor]: Finished (changed=False) 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.277 seconds 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/DMALocalityOpt]: Finished (changed=True) 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.034 seconds 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/DataStreaming]: Running DataStreaming 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/DataStreaming]: Finished (changed=True) 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/DataStreaming]: DataStreaming finished after 0.122 seconds 2025-11-09T20:54:31Z INFO 252 [sg0000/Tensorizer/SFKVectorizer]: Running SFKVectorizer 2025-11-09T20:54:35Z INFO 252 [sg0000/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 1.679 seconds 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_1 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_1 finished after 0.179 seconds 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/SFKVectorizer]: Finished (changed=True) 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 5.750 seconds 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/LateLegalizeInst]: Finished (changed=True) 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.139 seconds 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/CoalesceCCOp]: Finished (changed=True) 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.156 seconds 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/SimpleAllReduceTiling]: Finished (changed=False) 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.054 seconds 2025-11-09T20:54:37Z INFO 252 [sg0000/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/InsertCoreBarrier]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.118 seconds 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: Running DMAProfiler 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs: 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 772.293us (152.000MiB, est bw: 206.377GB/s, 12.579% of tot. time) for bfloat16<128 x 2048> TongaSB partitions[2] bfloat16 (2, 149, 128, 2048) %'26287.44512'[i4894_0,4i4894_1_0_0+i4894_1_0_1,i0.128,i1.128+128i2.16] = load bfloat16<128 x 2048> {'CrossPassTensor': '', 'transposable': True}bfloat16 (2, 18992, 16, 128) %'input369'[i4894_0,i0.128+512i4894_1_0_0+128i4894_1_0_1,i2.16,i1.128] # id=44511, src_id=None, , instances=304 # dl = tensor_op_name: input369_pftranspose_26287 | hlo_id: 14374 | if -i0.128-512i4894_1_0_0-128i4894_1_0_1+18991 >= 0 and -4i4894_1_0_0-i4894_1_0_1+148 >= 0 [[i0.128];[i1.128, i2.16]] -> [[i0.128];[i1.128, i2.16]] 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 117.635us (608.000KiB, est bw: 5.293GB/s, 1.916% of tot. time) for float32<4 x 128> non_local float32 (4, 2, 18992) %'convert.656'[i1.4,i4894_0,i0.128+512i4894_1_0_0+128i4894_1_0_1] = store float32<4 x 128> TongaSB partitions[2] float32 (2, 149, 4, 128) %'26800.44522'[i4894_0,4i4894_1_0_0+i4894_1_0_1,i1.4,i0.128] # id=44520, src_id=None, , instances=304 # dl = tensor_op_name: convert.656_pftranspose_26800 | hlo_id: 14374 | if -i0.128-512i4894_1_0_0-128i4894_1_0_1+18991 >= 0 and -4i4894_1_0_0-i4894_1_0_1+148 >= 0 [[i1.4];[i0.128]] -> [[i1.4];[i0.128]] 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 74.194us (16.016MiB, est bw: 226.346GB/s, 1.208% of tot. time) for bfloat16<128 x 4100> TongaSB partitions[2] bfloat16 (2, 8, 128, 4100) %'all_gather.1_nostride_48639'(init=0.0)[i242_0_31292,c0_28109,i0.128,i1.4100] = load bfloat16<128 x 4100> non_local bfloat16 (8192,) %'all_gather.1'[4i0.128+512c0_28109+i1.4100] # id=36930, src_id=None, , attrs={'can_read_uninit': True}, instances=16 # dl = tensor_op_name: _add.395 | hlo_id: 395 | [[i0.128];[i1.4100]] -> [[i0.128];[i1.4100]] 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 30.064us (6.000MiB, est bw: 209.271GB/s, 0.490% of tot. time) for bfloat16<128 x 3072> TongaSB partitions[2] bfloat16 (2, 4, 128, 3072) %'input68_local_28153'[i242_0_31292,2i243_0_0_0+i243_0_0_1,i0.128,i1.3072] = load bfloat16<128 x 3072> {'CrossPassTensor': '', 'transposable': True, 'static_io_transpose': {'reshape': (4, 4, 128, 2, 6, 128), 'transpose': [0, 3, 5, 4, 1, 2]}}bfloat16 (4, 2, 128, 3072) %'input68'[2i243_0_0_0+i243_0_0_1,i242_0_31292,i0.128,i1.3072] # id=36945, src_id=None, , instances=8 # dl = tensor_op_name: _dot.425 | hlo_id: 11374 | [[i0.128];[i1.3072]] -> [[i0.128];[i1.3072]] 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 30.064us (6.000MiB, est bw: 209.271GB/s, 0.490% of tot. time) for bfloat16<128 x 3072> TongaSB partitions[2] bfloat16 (2, 4, 128, 3072) %'input79_local_28264'[i414_0_31355,2i415_0_0_0+i415_0_0_1,i0.128,i1.3072] = load bfloat16<128 x 3072> {'CrossPassTensor': '', 'transposable': True, 'static_io_transpose': {'reshape': (4, 4, 128, 2, 6, 128), 'transpose': [0, 3, 5, 4, 1, 2]}}bfloat16 (4, 2, 128, 3072) %'input79'[2i415_0_0_0+i415_0_0_1,i414_0_31355,i0.128,i1.3072] # id=37141, src_id=None, , instances=8 # dl = tensor_op_name: _dot.769 | hlo_id: 11485 | [[i0.128];[i1.3072]] -> [[i0.128];[i1.3072]] 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 30.064us (6.000MiB, est bw: 209.271GB/s, 0.490% of tot. time) for bfloat16<128 x 3072> TongaSB partitions[2] bfloat16 (2, 4, 128, 3072) %'input90_local_28375'[i586_0_31418,2i587_0_0_0+i587_0_0_1,i0.128,i1.3072] = load bfloat16<128 x 3072> {'CrossPassTensor': '', 'transposable': True, 'static_io_transpose': {'reshape': (4, 4, 128, 2, 6, 128), 'transpose': [0, 3, 5, 4, 1, 2]}}bfloat16 (4, 2, 128, 3072) %'input90'[2i587_0_0_0+i587_0_0_1,i586_0_31418,i0.128,i1.3072] # id=37337, src_id=None, , instances=8 # dl = tensor_op_name: _dot.1113 | hlo_id: 11596 | [[i0.128];[i1.3072]] -> [[i0.128];[i1.3072]] 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 30.064us (6.000MiB, est bw: 209.271GB/s, 0.490% of tot. time) for bfloat16<128 x 3072> TongaSB partitions[2] bfloat16 (2, 4, 128, 3072) %'input101_local_28486'[i758_0_31481,2i759_0_0_0+i759_0_0_1,i0.128,i1.3072] = load bfloat16<128 x 3072> {'CrossPassTensor': '', 'transposable': True, 'static_io_transpose': {'reshape': (4, 4, 128, 2, 6, 128), 'transpose': [0, 3, 5, 4, 1, 2]}}bfloat16 (4, 2, 128, 3072) %'input101'[2i759_0_0_0+i759_0_0_1,i758_0_31481,i0.128,i1.3072] # id=37533, src_id=None, , instances=8 # dl = tensor_op_name: _dot.1457 | hlo_id: 11707 | [[i0.128];[i1.3072]] -> [[i0.128];[i1.3072]] 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 30.064us (6.000MiB, est bw: 209.271GB/s, 0.490% of tot. time) for bfloat16<128 x 3072> TongaSB partitions[2] bfloat16 (2, 4, 128, 3072) %'input112_local_28597'[i930_0_31544,2i931_0_0_0+i931_0_0_1,i0.128,i1.3072] = load bfloat16<128 x 3072> {'CrossPassTensor': '', 'transposable': True, 'static_io_transpose': {'reshape': (4, 4, 128, 2, 6, 128), 'transpose': [0, 3, 5, 4, 1, 2]}}bfloat16 (4, 2, 128, 3072) %'input112'[2i931_0_0_0+i931_0_0_1,i930_0_31544,i0.128,i1.3072] # id=37729, src_id=None, , instances=8 # dl = tensor_op_name: _dot.1801 | hlo_id: 11818 | [[i0.128];[i1.3072]] -> [[i0.128];[i1.3072]] 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 30.064us (6.000MiB, est bw: 209.271GB/s, 0.490% of tot. time) for bfloat16<128 x 3072> TongaSB partitions[2] bfloat16 (2, 4, 128, 3072) %'input123_local_28708'[i1102_0_31607,2i1103_0_0_0+i1103_0_0_1,i0.128,i1.3072] = load bfloat16<128 x 3072> {'CrossPassTensor': '', 'transposable': True, 'static_io_transpose': {'reshape': (4, 4, 128, 2, 6, 128), 'transpose': [0, 3, 5, 4, 1, 2]}}bfloat16 (4, 2, 128, 3072) %'input123'[2i1103_0_0_0+i1103_0_0_1,i1102_0_31607,i0.128,i1.3072] # id=37925, src_id=None, , instances=8 # dl = tensor_op_name: _dot.2145 | hlo_id: 11929 | [[i0.128];[i1.3072]] -> [[i0.128];[i1.3072]] 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: Est. DMA time: 30.064us (6.000MiB, est bw: 209.271GB/s, 0.490% of tot. time) for bfloat16<128 x 3072> TongaSB partitions[2] bfloat16 (2, 4, 128, 3072) %'input134_local_28819'[i1274_0_31670,2i1275_0_0_0+i1275_0_0_1,i0.128,i1.3072] = load bfloat16<128 x 3072> {'CrossPassTensor': '', 'transposable': True, 'static_io_transpose': {'reshape': (4, 4, 128, 2, 6, 128), 'transpose': [0, 3, 5, 4, 1, 2]}}bfloat16 (4, 2, 128, 3072) %'input134'[2i1275_0_0_0+i1275_0_0_1,i1274_0_31670,i0.128,i1.3072] # id=38121, src_id=None, , instances=8 # dl = tensor_op_name: _dot.2489 | hlo_id: 12040 | [[i0.128];[i1.3072]] -> [[i0.128];[i1.3072]] 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.070 seconds 2025-11-09T20:54:38Z INFO 252 [sg0000/Tensorizer/OptimizeNKIKernels]: Running OptimizeNKIKernels 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DoNothing]: Running DoNothing 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DoNothing]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DoNothing]: DoNothing finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferSharedMemLoc]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.005 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/FactorizeBlkDims]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.011 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.009 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_1 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_1 finished after 0.008 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.018 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronValueNumbering]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.004 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.008 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.008 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerTranspose]: Running LowerTranspose 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerTranspose]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerBroadcast]: Running LowerBroadcast 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerBroadcast]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.008 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateNeuronInstComb]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.008 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SpillPSum]: Running SpillPSum 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SpillPSum]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SpillPSum]: SpillPSum finished after 0.038 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerIntrinsics]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.004 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LegalizeType]: Running LegalizeType 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LegalizeType]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LegalizeType]: LegalizeType finished after 0.010 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronLICM]: Running NeuronLICM 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronLICM]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.009 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferPSumTensor]: Running InferPSumTensor 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 0.011 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferPSumTensor]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 0.011 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/WeightCoalescing]: Running WeightCoalescing 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/WeightCoalescing]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LegalizeSundaAccess]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.015 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.004 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/ExpandISAMacro]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.004 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimplifyNeuronTensor]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.052 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMALocalityOpt]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DataStreaming]: Running DataStreaming 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DataStreaming]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DataStreaming]: DataStreaming finished after 0.007 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SFKVectorizer]: Running SFKVectorizer 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SFKVectorizer]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 0.047 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateLegalizeInst]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.007 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/CoalesceCCOp]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.004 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimpleAllReduceTiling]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.004 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InsertCoreBarrier]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Running DMAProfiler 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs: 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 4.186us (593.500KiB, est bw: 145.188GB/s, 19.617% of tot. time) for float32<128 x 1187> TongaSB partitions[0] float32 (128, 1443) %4(init=0.0)[i0.128,i1.1187] = load float32<128 x 1187> float32 (128, 1187) %6[i0.128,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 | [[i0.128];[i1.1187]] -> [[i0.128];[i1.1187]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 4.186us (593.500KiB, est bw: 145.188GB/s, 19.617% of tot. time) for float32<128 x 1187> TongaSB partitions[0] float32 (128, 1187) %10[i0.128,i1.1187] = load float32<128 x 1187> float32 (4, 37984) %'inp'[i0.128,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 | [[i0.128];[i1.1187]] -> [[i0.128];[i1.1187]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 2.079us (64.000KiB, est bw: 31.526GB/s, 9.742% of tot. time) for float32<128 x 128> TongaSB partitions[0] float32 (128, 128) %485[i0.128,i1.128] = load float32<128 x 128> float32 (128, 128) %3[i0.128,i1.128] # 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 | [[i0.128];[i1.128]] -> [[i0.128];[i1.128]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 2.068us (4.000KiB, est bw: 1.981GB/s, 9.690% of tot. time) for float32<4 x 256> TongaSB partitions[0] float32 (4, 256) %316[i0.4,i1.256] = load float32<4 x 256> float32 (128, 8) %304[i0.4,i1.256] # 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 | [[i0.4];[i1.256]] -> [[i0.4];[i1.256]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 2.068us (4.000KiB, est bw: 1.981GB/s, 9.690% of tot. time) for uint32<4 x 256> TongaSB partitions[0] uint32 (4, 256) %319[i0.4,i1.256] = load float32<4 x 256> float32 (128, 8) %307[i0.4,i1.256] # 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 | [[i0.4];[i1.256]] -> [[i0.4];[i1.256]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.757us (4.000KiB, est bw: 2.331GB/s, 8.236% of tot. time) for uint32<4 x 256> uint32 (4, 256) %'topk_indices'[i0.4,i1.256] = store uint32<4 x 256> TongaSB partitions[0] uint32 (4, 256) %'global_id_buf'(init=0.0)[i0.4,i1.256] # 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 | [[i0.4];[i1.256]] -> [[i0.4];[i1.256]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.757us (4.000KiB, est bw: 2.331GB/s, 8.236% of tot. time) for float32<4 x 256> float32 (4, 256) %'topk_values'[i0.4,i1.256] = store float32<4 x 256> TongaSB partitions[0] float32 (4, 256) %'val_buf'(init=0.0)[i0.4,i1.256] # 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 | [[i0.4];[i1.256]] -> [[i0.4];[i1.256]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.619us (4.000KiB, est bw: 2.531GB/s, 7.586% of tot. time) for float32<128 x 8> float32 (128, 8) %304[i0.128,i1.8] = store float32<128 x 8> TongaSB partitions[0] float32 (128, 8) %296[i0.128,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 | [[i0.128];[i1.8]] -> [[i0.128];[i1.8]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.619us (4.000KiB, est bw: 2.531GB/s, 7.586% of tot. time) for float32<128 x 8> float32 (128, 8) %307[i0.128,i1.8] = store float32<128 x 8> TongaSB partitions[0] float32 (128, 8) %517[i0.128,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 | [[i0.128];[i1.8]] -> [[i0.128];[i1.8]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferSharedMemLoc]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DoNothing]: Running DoNothing 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DoNothing]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DoNothing]: DoNothing finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferSharedMemLoc]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.004 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/FactorizeBlkDims]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.011 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.009 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_1 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_1 finished after 0.008 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.017 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronValueNumbering]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.004 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.008 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.008 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerTranspose]: Running LowerTranspose 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerTranspose]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerBroadcast]: Running LowerBroadcast 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerBroadcast]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.008 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateNeuronInstComb]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.008 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SpillPSum]: Running SpillPSum 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SpillPSum]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SpillPSum]: SpillPSum finished after 0.020 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerIntrinsics]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.004 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LegalizeType]: Running LegalizeType 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LegalizeType]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LegalizeType]: LegalizeType finished after 0.009 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronLICM]: Running NeuronLICM 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronLICM]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.009 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferPSumTensor]: Running InferPSumTensor 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 0.010 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferPSumTensor]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 0.010 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/WeightCoalescing]: Running WeightCoalescing 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/WeightCoalescing]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LegalizeSundaAccess]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.014 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.004 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/ExpandISAMacro]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.004 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimplifyNeuronTensor]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.058 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMALocalityOpt]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DataStreaming]: Running DataStreaming 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DataStreaming]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DataStreaming]: DataStreaming finished after 0.006 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SFKVectorizer]: Running SFKVectorizer 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SFKVectorizer]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 0.031 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateLegalizeInst]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.007 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/CoalesceCCOp]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.004 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimpleAllReduceTiling]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.004 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InsertCoreBarrier]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Running DMAProfiler 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs: 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 2.079us (64.000KiB, est bw: 31.526GB/s, 12.349% of tot. time) for float32<128 x 128> TongaSB partitions[0] float32 (128, 128) %485[i0.128,i1.128] = load float32<128 x 128> float32 (128, 128) %3[i0.128,i1.128] # 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 | [[i0.128];[i1.128]] -> [[i0.128];[i1.128]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 2.068us (4.000KiB, est bw: 1.981GB/s, 12.282% of tot. time) for float32<4 x 256> TongaSB partitions[0] float32 (4, 256) %316[i0.4,i1.256] = load float32<4 x 256> float32 (128, 8) %304[i0.4,i1.256] # 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 | [[i0.4];[i1.256]] -> [[i0.4];[i1.256]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 2.068us (4.000KiB, est bw: 1.981GB/s, 12.282% of tot. time) for uint32<4 x 256> TongaSB partitions[0] uint32 (4, 256) %319[i0.4,i1.256] = load float32<4 x 256> float32 (128, 8) %307[i0.4,i1.256] # 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 | [[i0.4];[i1.256]] -> [[i0.4];[i1.256]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.934us (16.000KiB, est bw: 8.471GB/s, 11.489% of tot. time) for float32<128 x 32> TongaSB partitions[0] float32 (128, 288) %4(init=0.0)[i0.128,i1.32] = load float32<128 x 32> float32 (128, 32) %6[i0.128,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 | [[i0.128];[i1.32]] -> [[i0.128];[i1.32]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.934us (16.000KiB, est bw: 8.471GB/s, 11.489% of tot. time) for float32<128 x 32> TongaSB partitions[0] float32 (128, 32) %10[i0.128,i1.32] = load float32<128 x 32> float32 (4, 1024) %'inp'[i0.128,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 | [[i0.128];[i1.32]] -> [[i0.128];[i1.32]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.757us (4.000KiB, est bw: 2.331GB/s, 10.439% of tot. time) for uint32<4 x 256> uint32 (4, 256) %'topk_indices'[i0.4,i1.256] = store uint32<4 x 256> TongaSB partitions[0] uint32 (4, 256) %'global_id_buf'(init=0.0)[i0.4,i1.256] # 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 | [[i0.4];[i1.256]] -> [[i0.4];[i1.256]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.757us (4.000KiB, est bw: 2.331GB/s, 10.439% of tot. time) for float32<4 x 256> float32 (4, 256) %'topk_values'[i0.4,i1.256] = store float32<4 x 256> TongaSB partitions[0] float32 (4, 256) %'val_buf'(init=0.0)[i0.4,i1.256] # 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 | [[i0.4];[i1.256]] -> [[i0.4];[i1.256]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.619us (4.000KiB, est bw: 2.531GB/s, 9.615% of tot. time) for float32<128 x 8> float32 (128, 8) %304[i0.128,i1.8] = store float32<128 x 8> TongaSB partitions[0] float32 (128, 8) %296[i0.128,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 | [[i0.128];[i1.8]] -> [[i0.128];[i1.8]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Est. DMA time: 1.619us (4.000KiB, est bw: 2.531GB/s, 9.615% of tot. time) for float32<128 x 8> float32 (128, 8) %307[i0.128,i1.8] = store float32<128 x 8> TongaSB partitions[0] float32 (128, 8) %517[i0.128,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 | [[i0.128];[i1.8]] -> [[i0.128];[i1.8]] 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferSharedMemLoc]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [topk/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DoNothing]: Running DoNothing 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DoNothing]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DoNothing]: DoNothing finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferSharedMemLoc]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/FactorizeBlkDims]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronValueNumbering]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerTranspose]: Running LowerTranspose 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerTranspose]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerBroadcast]: Running LowerBroadcast 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerBroadcast]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LateNeuronInstComb]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SpillPSum]: Running SpillPSum 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SpillPSum]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SpillPSum]: SpillPSum finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerIntrinsics]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LegalizeType]: Running LegalizeType 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LegalizeType]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LegalizeType]: LegalizeType finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronLICM]: Running NeuronLICM 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronLICM]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferPSumTensor]: Running InferPSumTensor 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferPSumTensor]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/WeightCoalescing]: Running WeightCoalescing 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/WeightCoalescing]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LegalizeSundaAccess]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.002 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.002 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/ExpandISAMacro]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SimplifyNeuronTensor]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DMALocalityOpt]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DataStreaming]: Running DataStreaming 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DataStreaming]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DataStreaming]: DataStreaming finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SFKVectorizer]: Running SFKVectorizer 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SFKVectorizer]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 0.003 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LateLegalizeInst]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/CoalesceCCOp]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SimpleAllReduceTiling]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InsertCoreBarrier]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DMAProfiler]: Running DMAProfiler 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs: 2025-11-09T20:54:38Z INFO 252 [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 (4, 256) %'x'[i0.128,i1.2048] # id=8, src_id=None, , instances=1 # dl = tensor_op_name: | if -i0.128+3 >= 0 and -i1.2048+255 >= 0 [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]] 2025-11-09T20:54:38Z INFO 252 [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 (4, 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+3 >= 0 and -i1.2048+255 >= 0 [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]] 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DMAProfiler]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferSharedMemLoc]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DoNothing]: Running DoNothing 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DoNothing]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/DoNothing]: DoNothing finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferSharedMemLoc]: Finished (changed=True) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/FactorizeBlkDims]: Running FactorizeBlkDims 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/FactorizeBlkDims]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/FactorizeBlkDims]: FactorizeBlkDims finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronValueNumbering]: Running NeuronValueNumbering 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronValueNumbering]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronValueNumbering]: NeuronValueNumbering finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: Running NeuronInstComb_iteration_0 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb_iteration_0 finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronInstComb]: NeuronInstComb finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerTranspose]: Running LowerTranspose 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerTranspose]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerTranspose]: LowerTranspose finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerBroadcast]: Running LowerBroadcast 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerBroadcast]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerBroadcast]: LowerBroadcast finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LateNeuronInstComb]: Running LateNeuronInstComb_iteration_0 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb_iteration_0 finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LateNeuronInstComb]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LateNeuronInstComb]: LateNeuronInstComb finished after 0.001 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SpillPSum]: Running SpillPSum 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SpillPSum]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/SpillPSum]: SpillPSum finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerIntrinsics]: Running LowerIntrinsics 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerIntrinsics]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LowerIntrinsics]: LowerIntrinsics finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LegalizeType]: Running LegalizeType 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LegalizeType]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/LegalizeType]: LegalizeType finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronLICM]: Running NeuronLICM 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronLICM]: Finished (changed=False) 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/NeuronLICM]: NeuronLICM finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferPSumTensor]: Running InferPSumTensor 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferPSumTensor]: Running InferPSumTensor_iteration_0 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferPSumTensor]: InferPSumTensor_iteration_0 finished after 0.000 seconds 2025-11-09T20:54:38Z INFO 252 [cumsum/Tensorizer/InferPSumTensor]: Finished (changed=False) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/InferPSumTensor]: InferPSumTensor finished after 0.001 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/WeightCoalescing]: Running WeightCoalescing 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/WeightCoalescing]: Finished (changed=False) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/WeightCoalescing]: WeightCoalescing finished after 0.000 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/LegalizeSundaAccess]: Running LegalizeSundaAccess 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/LegalizeSundaAccess]: Finished (changed=True) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/LegalizeSundaAccess]: LegalizeSundaAccess finished after 0.001 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/NeuronSimplifyPredicates]: Running NeuronSimplifyPredicates 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/NeuronSimplifyPredicates]: Finished (changed=False) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/NeuronSimplifyPredicates]: NeuronSimplifyPredicates finished after 0.002 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/ExpandISAMacro]: Running ExpandISAMacro 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/ExpandISAMacro]: Finished (changed=False) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/ExpandISAMacro]: ExpandISAMacro finished after 0.001 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/SimplifyNeuronTensor]: Running SimplifyNeuronTensor 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/SimplifyNeuronTensor]: Running DeadCodeElimination_iteration_0 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/SimplifyNeuronTensor]: DeadCodeElimination_iteration_0 finished after 0.000 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/SimplifyNeuronTensor]: Finished (changed=False) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/SimplifyNeuronTensor]: SimplifyNeuronTensor finished after 0.000 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/DMALocalityOpt]: Running DMALocalityOpt 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/DMALocalityOpt]: Finished (changed=False) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/DMALocalityOpt]: DMALocalityOpt finished after 0.000 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/DataStreaming]: Running DataStreaming 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/DataStreaming]: Finished (changed=False) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/DataStreaming]: DataStreaming finished after 0.000 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/SFKVectorizer]: Running SFKVectorizer 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/SFKVectorizer]: Running VectorizeLoop_iteration_0 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/SFKVectorizer]: VectorizeLoop_iteration_0 finished after 0.000 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/SFKVectorizer]: Finished (changed=True) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/SFKVectorizer]: SFKVectorizer finished after 0.002 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/LateLegalizeInst]: Running LateLegalizeInst 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/LateLegalizeInst]: Finished (changed=False) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/LateLegalizeInst]: LateLegalizeInst finished after 0.000 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/CoalesceCCOp]: Running CoalesceCCOp 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/CoalesceCCOp]: Finished (changed=False) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/CoalesceCCOp]: CoalesceCCOp finished after 0.000 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/SimpleAllReduceTiling]: Running SimpleAllReduceTiling 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/SimpleAllReduceTiling]: Finished (changed=False) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/SimpleAllReduceTiling]: SimpleAllReduceTiling finished after 0.000 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/InsertCoreBarrier]: Running InsertCoreBarrier 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/InsertCoreBarrier]: Finished (changed=False) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/InsertCoreBarrier]: InsertCoreBarrier finished after 0.000 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/DMAProfiler]: Running DMAProfiler 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/DMAProfiler]: Top 10 (estimated) latency DMAs: 2025-11-09T20:54:39Z INFO 252 [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 (4, 256) %'x'[i0.128,i1.2048] # id=8, src_id=None, , instances=1 # dl = tensor_op_name: | if -i0.128+3 >= 0 and -i1.2048+255 >= 0 [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]] 2025-11-09T20:54:39Z INFO 252 [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 (4, 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+3 >= 0 and -i1.2048+255 >= 0 [[i0.128];[i1.2048]] -> [[i0.128];[i1.2048]] 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/DMAProfiler]: Finished (changed=False) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/DMAProfiler]: DMAProfiler finished after 0.001 seconds 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/InferSharedMemLoc]: Finished (changed=True) 2025-11-09T20:54:39Z INFO 252 [cumsum/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.000 seconds 2025-11-09T20:54:39Z INFO 252 [sg0000/Tensorizer/OptimizeNKIKernels]: Finished (changed=True) 2025-11-09T20:54:39Z INFO 252 [sg0000/Tensorizer/OptimizeNKIKernels]: OptimizeNKIKernels finished after 0.979 seconds 2025-11-09T20:54:39Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: Running CCOpFusion 2025-11-09T20:54:39Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: Running CCOpFusion_iteration_0 2025-11-09T20:54:39Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: CCOpFusion_iteration_0 finished after 0.655 seconds 2025-11-09T20:54:39Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: Finished (changed=True) 2025-11-09T20:54:39Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: CCOpFusion finished after 0.656 seconds 2025-11-09T20:54:39Z INFO 252 [sg0000/Tensorizer/StaticProfiler]: Running StaticProfiler 2025-11-09T20:54:39Z WARNING 252 [sg0000/Tensorizer/StaticProfiler]: matmul-based transposes inserted by penguin takes up 85.07 percent of all matmul computation 2025-11-09T20:54:39Z INFO 252 [sg0000/Tensorizer/StaticProfiler]: Finished (changed=False) 2025-11-09T20:54:39Z INFO 252 [sg0000/Tensorizer/StaticProfiler]: StaticProfiler finished after 0.139 seconds 2025-11-09T20:54:39Z INFO 252 [sg0000/Tensorizer/SplitAPUnionSets]: Running SplitAPUnionSets 2025-11-09T20:54:40Z INFO 252 [sg0000/Tensorizer/SplitAPUnionSets]: Finished (changed=True) 2025-11-09T20:54:40Z INFO 252 [sg0000/Tensorizer/SplitAPUnionSets]: SplitAPUnionSets finished after 0.680 seconds 2025-11-09T20:54:40Z INFO 252 [sg0000/Tensorizer/LateLegalizePostSplit]: Running LateLegalizePostSplit 2025-11-09T20:54:40Z INFO 252 [sg0000/Tensorizer/LateLegalizePostSplit]: Finished (changed=False) 2025-11-09T20:54:40Z INFO 252 [sg0000/Tensorizer/LateLegalizePostSplit]: LateLegalizePostSplit finished after 0.087 seconds 2025-11-09T20:54:40Z INFO 252 [sg0000/Tensorizer/InferSharedMemLoc]: Running InferSharedMemLoc 2025-11-09T20:54:40Z INFO 252 [sg0000/Tensorizer/InferSharedMemLoc]: Finished (changed=True) 2025-11-09T20:54:40Z INFO 252 [sg0000/Tensorizer/InferSharedMemLoc]: InferSharedMemLoc finished after 0.101 seconds 2025-11-09T20:54:40Z INFO 252 [sg0000/Tensorizer/LowerShardAxis]: Running LowerShardAxis 2025-11-09T20:54:40Z INFO 252 [sg0000/Tensorizer/LowerShardAxis]: Finished (changed=True) 2025-11-09T20:54:40Z INFO 252 [sg0000/Tensorizer/LowerShardAxis]: LowerShardAxis finished after 0.195 seconds 2025-11-09T20:54:40Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: Running CCOpFusion 2025-11-09T20:54:40Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: Running CCOpFusion_iteration_0 2025-11-09T20:54:41Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: CCOpFusion_iteration_0 finished after 0.531 seconds 2025-11-09T20:54:41Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: Finished (changed=False) 2025-11-09T20:54:41Z INFO 252 [sg0000/Tensorizer/CCOpFusion]: CCOpFusion finished after 0.533 seconds 2025-11-09T20:54:41Z INFO 252 [sg0000/Tensorizer/DumpGraphAndMetadata]: Running DumpGraphAndMetadata 2025-11-09T20:54:41Z INFO 252 [sg0000/Tensorizer/DumpGraphAndMetadata]: Finished (changed=False) 2025-11-09T20:54:41Z INFO 252 [sg0000/Tensorizer/DumpGraphAndMetadata]: DumpGraphAndMetadata finished after 0.145 seconds 2025-11-09T20:54:41Z INFO 252 [sg0000/Tensorizer/ZeroSizeTensorElimination]: Running ZeroSizeTensorElimination 2025-11-09T20:54:41Z INFO 252 [sg0000/Tensorizer/ZeroSizeTensorElimination]: Finished (changed=False) 2025-11-09T20:54:41Z INFO 252 [sg0000/Tensorizer/ZeroSizeTensorElimination]: ZeroSizeTensorElimination finished after 0.000 seconds 2025-11-09T20:54:41Z INFO 252 [sg0000/Tensorizer/LowerToSendRecv]: Running LowerToSendRecv 2025-11-09T20:54:41Z INFO 252 [sg0000/Tensorizer/LowerToSendRecv]: Finished (changed=True) 2025-11-09T20:54:41Z INFO 252 [sg0000/Tensorizer/LowerToSendRecv]: LowerToSendRecv finished after 0.148 seconds 2025-11-09T20:54:41Z INFO 252 [sg0000/Tensorizer/BirCodeGenLoop]: Running BirCodeGenLoop 2025-11-09T20:54:44Z INFO 252 [sg0000/Tensorizer/BirCodeGenLoop]: Finished (changed=False) 2025-11-09T20:54:44Z INFO 252 [sg0000/Tensorizer/BirCodeGenLoop]: BirCodeGenLoop finished after 2.442 seconds 2025-11-09T20:54:46Z INFO 252 [Tensorizer]: BirCodeGen estimate #instances=36582 in sg0000 2025-11-09T20:54:46Z INFO 252 [Tensorizer]: IR signature: 927b282b106c60d7f7e60c8c3cc71ee4fb9c674902d98913cdadfa6b10019634 for nc00/sg0000/TensorizerBIR 2025-11-09T20:54:46Z INFO 252 [sg0000/Tensorizer/BirCodeGenLoop]: Running BirCodeGenLoop 2025-11-09T20:54:49Z INFO 252 [sg0000/Tensorizer/BirCodeGenLoop]: Finished (changed=False) 2025-11-09T20:54:49Z INFO 252 [sg0000/Tensorizer/BirCodeGenLoop]: BirCodeGenLoop finished after 2.482 seconds 2025-11-09T20:54:51Z INFO 252 [Tensorizer]: BirCodeGen estimate #instances=36582 in sg0000 2025-11-09T20:54:51Z INFO 252 [Tensorizer]: IR signature: 724a3f25dacf16a5cc4d2b49317648e0a9bde5a198ed9fff47d0fc4a814fdc4c for nc01/sg0000/TensorizerBIR 2025-11-09T20:54:51Z INFO 252 [Tensorizer]: Weights total number of bytes: 988936 2025-11-09T20:54:51Z INFO 252 [Tensorizer]: Successfully built model. 2025-11-09T20:54:51Z USER 252 [root/Tensorizer/Tensorizer]: Tensorizer finished after 91.655 seconds 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: End tensorization 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input0 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input1 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input2 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input3 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input4 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input5 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input6 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input7 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input8 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input9 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input10 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input11 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input12 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input13 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input14 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input15 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input16 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input17 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input18 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input19 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input20 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input21 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input22 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input23 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input24 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input25 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input26 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input27 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input28 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input29 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input30 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input31 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input32 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input33 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input34 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input35 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input36 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input37 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input38 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input39 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input40 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input41 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input42 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input43 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input44 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input45 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input46 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input47 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input48 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input49 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input50 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input51 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input52 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input53 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input54 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input55 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input56 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input57 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input58 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input59 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input60 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input61 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input62 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input63 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input64 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input65 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input66 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input67 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input68 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input69 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input70 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input71 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input72 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input73 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input74 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input75 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input76 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input77 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input78 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input79 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input80 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input81 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input82 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input83 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input84 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input85 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input86 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input87 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input88 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input89 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input90 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input91 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input92 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input93 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input94 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input95 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input96 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input97 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input98 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input99 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input100 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input101 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input102 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input103 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input104 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input105 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input106 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input107 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input108 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input109 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input110 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input111 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input112 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input113 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input114 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input115 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input116 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input117 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input118 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input119 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input120 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input121 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input122 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input123 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input124 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input125 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input126 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input127 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input128 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input129 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input130 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input131 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input132 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input133 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input134 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input135 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input136 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input137 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input138 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input139 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input140 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input141 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input142 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input143 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input144 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input145 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input146 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input147 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input148 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input149 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input150 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input151 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input152 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input153 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input154 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input155 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input156 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input157 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input158 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input159 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input160 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input161 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input162 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input163 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input164 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input165 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input166 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input167 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input168 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input169 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input170 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input171 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input172 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input173 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input174 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input175 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input176 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input177 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input178 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input179 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input180 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input181 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input182 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input183 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input184 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input185 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input186 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input187 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input188 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input189 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input190 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input191 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input192 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input193 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input194 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input195 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input196 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input197 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input198 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input199 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input200 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input201 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input202 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input203 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input204 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input205 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input206 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input207 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input208 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input209 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input210 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input211 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input212 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input213 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input214 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input215 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input216 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input217 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input218 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input219 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input220 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input221 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input222 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input223 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input224 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input225 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input226 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input227 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input228 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input229 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input230 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input231 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input232 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input233 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input234 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input235 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input236 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input237 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input238 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input239 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input240 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input241 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input242 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input243 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input244 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input245 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input246 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input247 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input248 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input249 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input250 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input251 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input252 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input253 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input254 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input255 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input256 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input257 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input258 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input259 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input260 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input261 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input262 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input263 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input264 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input265 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input266 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input267 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input268 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input269 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input270 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input271 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input272 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input273 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input274 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input275 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input276 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input277 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input278 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input279 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input280 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input281 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input282 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input283 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input284 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input285 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input286 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input287 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input288 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input289 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input290 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input291 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input292 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input293 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input294 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input295 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input296 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input297 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input298 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input299 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input300 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input301 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input302 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input303 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input304 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input305 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input306 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input307 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input308 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input309 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input310 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input311 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input312 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input313 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input314 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input315 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input316 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input317 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input318 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input319 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input320 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input321 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input322 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input323 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input324 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input325 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input326 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input327 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input328 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input329 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input330 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input331 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input332 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input333 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input334 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input335 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input336 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input337 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input338 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input339 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input340 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input341 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input342 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input343 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input344 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input345 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input346 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input347 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input348 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input349 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input350 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input351 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input352 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input353 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input354 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input355 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input356 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input357 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input358 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input359 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input360 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input361 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input362 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input363 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input364 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input365 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input366 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input367 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input368 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input369 2025-11-09T20:54:51Z INFO 252 [job.Frontend.0]: Network input: input370 2025-11-09T20:54:52Z INFO 252 [job.Frontend.0]: wrote bir.json 2025-11-09T20:54:52Z INFO 252 [job.Frontend.0]: wrote tensor_map.json 2025-11-09T20:54:52Z INFO 252 [job.Frontend.0]: wrote bir.json 2025-11-09T20:54:52Z INFO 252 [job.Frontend.0]: wrote tensor_map.json 2025-11-09T20:54:52Z INFO 252 [job.Frontend.0]: Job #0 finished 2025-11-09T20:54:52Z INFO 252 [pipeline.Pipeline.0]: Finished job job.Frontend.0 2025-11-09T20:54:52Z INFO 252 [pipeline.Pipeline.0]: Starting job job.StaticIOTranspose.0 2025-11-09T20:54:52Z INFO 252 [pipeline.Pipeline.0]: Finished job job.StaticIOTranspose.0 2025-11-09T20:54:52Z INFO 252 [pipeline.Pipeline.0]: Starting job job.WalrusDriver.0 2025-11-09T20:54:52Z INFO 252 [job.WalrusDriver.0]: BackendDriver has 2 states with 2 core LNC 2025-11-09T20:54:52Z INFO 252 [job.WalrusDriver.0]: BackendDriver VNC cwd: /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/neuronxcc-sij89sjf 2025-11-09T20:54:52Z INFO 252 [job.WalrusDriver.0]: BackendDriver: no partitions within VNC found. Switching to VNC + flat flow. 2025-11-09T20:54:52Z INFO 252 [job.WalrusDriver.0]: BackendDriver in_state.num_states 2 with 2 core LNC 2025-11-09T20:54:52Z INFO 252 [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/token_generation_model/_tp0_bk0/log-neuron-cc.txt --vnc-nc-per-sengine 2 --link-subgraphs nc00/sg00,nc01/sg00 --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-color-rotation --max-load-lower-bound 0.14 --mm-reorder-opt --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 --unified-backend-and-legacy-codegen --enable-verifier=true --enable-birsim=false --enable-birsim-sync-only=false --enable-data-race-checker=false --enable-new-backend=true --inject-error=NONE --dge-levels io,scalar_dynamic_offset,spill_reload,vector_dynamic_offsets --dynamic-dma-scratch-size-per-partition=16384 --neff-output-filename /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/model.MODULE_5e3d0ce8963512f9ea2d+937cd7a2.neff 2025-11-09T20:54:52Z INFO 252 [job.WalrusDriver.0]: Working directory is /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/neuronxcc-sij89sjf 2025-11-09T20:54:52Z INFO 252 [job.WalrusDriver.0]: propagate_exit=True 2025-11-09T20:54:52Z INFO 252 [job.WalrusDriver.0]: use_logger=False 2025-11-09T20:54:52Z INFO 252 [job.WalrusDriver.0]: expose_stderr=True 2025-11-09T20:54:52Z INFO 293 [Logging]: Logging to ../log-neuron-cc.txt at level 'INFO' 2025-11-09T20:54:52Z INFO 293 [BackendDriver]: max_allowed_parallelism=12 2025-11-09T20:54:52Z INFO 293 [BackendDriver]: Loading module from nc00/sg00/bir.json 2025-11-09T20:54:52Z INFO 293 [BackendDriver]: Loading module from nc01/sg00/bir.json 2025-11-09T20:54:53Z INFO 293 [BackendDriver]: Backend driver mtBackend: false numModules: 2 Cwd: "/models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/neuronxcc-sij89sjf" 2025-11-09T20:54:53Z INFO 293 [BackendDriver]: DynamicDMA is enabled 2025-11-09T20:54:53Z INFO 293 [BackendDriver]: DynamicDMA levels being enabled: io, spill_reload, scalar_dynamic_offset, vector_dynamic_offsets, 2025-11-09T20:54:53Z USER 293 [BackendPassManager]: Running mod_parallel_pass 2025-11-09T20:54:53Z INFO 293 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=2 allocs=12322 blocks=2 instructions=11710 Max writers: 65 Max Readers: 285 2025-11-09T20:54:53Z USER 293 (nc00/sg00) [ModuleForkPass]: Running do_nothing 2025-11-09T20:54:53Z USER 293 (nc01/sg00) [ModuleForkPass]: Running do_nothing 2025-11-09T20:54:53Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to do_nothing: modules=1 functions=1 allocs=6161 blocks=1 instructions=5855 Max writers: 65 Max Readers: 285 2025-11-09T20:54:53Z USER 293 (nc01/sg00) [ModuleForkPass]: do_nothing finished after 0.012 seconds 2025-11-09T20:54:53Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 342mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:53Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to do_nothing: modules=1 functions=1 allocs=6161 blocks=1 instructions=5855 Max writers: 65 Max Readers: 285 2025-11-09T20:54:53Z USER 293 (nc00/sg00) [ModuleForkPass]: do_nothing finished after 0.014 seconds 2025-11-09T20:54:53Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 342mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:53Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 6161 memory location(s), 1 block(s), and 5855 instruction(s). Max writers: 65 Max Readers: 285 2025-11-09T20:54:53Z USER 293 (nc00/sg00) [ModuleForkPass]: Running birverifier 2025-11-09T20:54:53Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=6161 blocks=1 instructions=5855 Max writers: 65 Max Readers: 285 2025-11-09T20:54:53Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 6161 memory location(s), 1 block(s), and 5855 instruction(s). Max writers: 65 Max Readers: 285 2025-11-09T20:54:53Z USER 293 (nc01/sg00) [ModuleForkPass]: Running birverifier 2025-11-09T20:54:53Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=6161 blocks=1 instructions=5855 Max writers: 65 Max Readers: 285 2025-11-09T20:54:53Z WARNING 293 [birverifier::InstVisitor]: (nc00/sg00) Non - output memory location with no reader: {convert.375.51914}@SB<0,0>(1x2)#Internal DebugInfo: 2025-11-09T20:54:53Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {convert.375.51914}@SB<0,0>(1x2)#Internal DebugInfo: 2025-11-09T20:54:54Z USER 293 (nc00/sg00) [ModuleForkPass]: birverifier finished after 0.722 seconds 2025-11-09T20:54:54Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 355mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:54Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 6161 memory location(s), 1 block(s), and 5855 instruction(s). Max writers: 65 Max Readers: 285 2025-11-09T20:54:54Z USER 293 (nc01/sg00) [ModuleForkPass]: birverifier finished after 0.745 seconds 2025-11-09T20:54:54Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 361mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:54Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 6161 memory location(s), 1 block(s), and 5855 instruction(s). Max writers: 65 Max Readers: 285 2025-11-09T20:54:54Z USER 293 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:54:54Z USER 293 [BackendPassManager]: mod_parallel_pass finished after 0.789 seconds 2025-11-09T20:54:54Z INFO 293 [BackendPassManager]: curr_vmrss: 361mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:54Z USER 293 [BackendPassManager]: Running subgraph_parallel_pass 2025-11-09T20:54:54Z INFO 293 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=2 functions=2 allocs=12322 blocks=2 instructions=11710 Max writers: 65 Max Readers: 285 2025-11-09T20:54:54Z USER 293 (sg00) [SubgraphForkPass]: Running lnc_verifier 2025-11-09T20:54:54Z INFO 293 (sg00) [SubgraphForkPass]: Inputs to lnc_verifier: modules=2 functions=2 allocs=12322 blocks=2 instructions=11710 Max writers: 65 Max Readers: 285 2025-11-09T20:54:54Z USER 293 (sg00) [SubgraphForkPass]: lnc_verifier finished after 0.007 seconds 2025-11-09T20:54:54Z INFO 293 (sg00) [SubgraphForkPass]: curr_vmrss: 361mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:54Z INFO 293 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 12322 memory location(s), 2 block(s), and 11710 instruction(s). Max writers: 65 Max Readers: 285 2025-11-09T20:54:54Z USER 293 [SubgraphForkPass]: Compilation status: Total subgraphs: 1, Passed: 1, Failed: 0 2025-11-09T20:54:54Z USER 293 [BackendPassManager]: subgraph_parallel_pass finished after 0.016 seconds 2025-11-09T20:54:54Z INFO 293 [BackendPassManager]: curr_vmrss: 361mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:54Z USER 293 [BackendPassManager]: Running mod_parallel_pass 2025-11-09T20:54:54Z INFO 293 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=2 allocs=12322 blocks=2 instructions=11710 Max writers: 65 Max Readers: 285 2025-11-09T20:54:54Z USER 293 (nc00/sg00) [ModuleForkPass]: Running expand_replication 2025-11-09T20:54:54Z USER 293 (nc01/sg00) [ModuleForkPass]: Running expand_replication 2025-11-09T20:54:54Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to expand_replication: modules=1 functions=1 allocs=6161 blocks=1 instructions=5855 Max writers: 65 Max Readers: 285 2025-11-09T20:54:54Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to expand_replication: modules=1 functions=1 allocs=6161 blocks=1 instructions=5855 Max writers: 65 Max Readers: 285 2025-11-09T20:54:54Z INFO 293 (nc01/sg00) [ExpandReplication]: Found 0 replicated matmults 2025-11-09T20:54:54Z USER 293 (nc01/sg00) [ModuleForkPass]: expand_replication finished after 0.003 seconds 2025-11-09T20:54:54Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 361mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:54Z INFO 293 (nc00/sg00) [ExpandReplication]: Found 0 replicated matmults 2025-11-09T20:54:54Z USER 293 (nc00/sg00) [ModuleForkPass]: expand_replication finished after 0.003 seconds 2025-11-09T20:54:54Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 361mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:54Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 6161 memory location(s), 1 block(s), and 5855 instruction(s). Max writers: 65 Max Readers: 285 2025-11-09T20:54:54Z USER 293 (nc00/sg00) [ModuleForkPass]: Running unroll 2025-11-09T20:54:54Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 6161 memory location(s), 1 block(s), and 5855 instruction(s). Max writers: 65 Max Readers: 285 2025-11-09T20:54:54Z USER 293 (nc01/sg00) [ModuleForkPass]: Running unroll 2025-11-09T20:54:54Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to unroll: modules=1 functions=1 allocs=6161 blocks=1 instructions=5855 Max writers: 65 Max Readers: 285 2025-11-09T20:54:54Z INFO 293 (nc00/sg00) [Unroll]: INFO (Unroll) Start unrolling at Sun Nov 9 20:54:54 2025 2025-11-09T20:54:54Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to unroll: modules=1 functions=1 allocs=6161 blocks=1 instructions=5855 Max writers: 65 Max Readers: 285 2025-11-09T20:54:54Z INFO 293 (nc01/sg00) [Unroll]: INFO (Unroll) Start unrolling at Sun Nov 9 20:54:54 2025 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: INFO (Unroll) DONE unrolling Sun Nov 9 20:54:54 2025 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: INFO (Unroll) DONE unrolling Sun Nov 9 20:54:54 2025 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: sg0000 Instruction count after Unroll: 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: Total count: 30103 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: Matmult: 21262 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: GenericCopy: 2599 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: TensorScalarPtr: 1857 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: TensorTensor: 1085 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: Load: 1067 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: Activation: 593 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: Memset: 246 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: CollectiveCompute: 227 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: Save: 190 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: CoreBarrier: 181 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: Gather: 128 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: MaxIndexAndMatchReplace: 128 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: Max: 128 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: Iota: 114 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: TensorReduce: 64 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: DMACopy: 62 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: Reciprocal: 59 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: StreamTranspose: 57 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: Select: 30 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: StreamShuffle: 26 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [Unroll]: Unrolled DGE count with Dynamic AP: 62 2025-11-09T20:54:55Z USER 293 (nc01/sg00) [ModuleForkPass]: unroll finished after 1.076 seconds 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 769mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: sg0000 Instruction count after Unroll: 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: Total count: 30479 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: Matmult: 21262 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: GenericCopy: 2599 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: TensorScalarPtr: 1969 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: TensorTensor: 1085 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: Load: 1067 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: Activation: 593 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: Save: 342 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: Memset: 246 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: CollectiveCompute: 227 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: CoreBarrier: 181 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: Iota: 170 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: MaxIndexAndMatchReplace: 128 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: Max: 128 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: Gather: 128 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: DMACopy: 118 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: TensorReduce: 64 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: Reciprocal: 59 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: StreamTranspose: 57 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: Select: 30 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: StreamShuffle: 26 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [Unroll]: Unrolled DGE count with Dynamic AP: 118 2025-11-09T20:54:55Z USER 293 (nc00/sg00) [ModuleForkPass]: unroll finished after 1.079 seconds 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 748mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 22187 memory location(s), 1 block(s), and 30479 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:55Z USER 293 (nc00/sg00) [ModuleForkPass]: Running dead_code_elim_o1 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 22187 memory location(s), 1 block(s), and 30103 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:55Z USER 293 (nc01/sg00) [ModuleForkPass]: Running dead_code_elim_o1 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to dead_code_elim_o1: modules=1 functions=1 allocs=22187 blocks=1 instructions=30479 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to dead_code_elim_o1: modules=1 functions=1 allocs=22187 blocks=1 instructions=30103 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [DeadCodeElim]: eliminateDeadStore removed 0 instructions 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [DeadCodeElim]: eliminateDeadStore removed 0 instructions 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [DeadCodeElim]: remove_must_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [DeadCodeElim]: remove_must_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [DeadCodeElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [DeadCodeElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [DeadCodeElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [DeadCodeElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys 2025-11-09T20:54:55Z USER 293 (nc01/sg00) [ModuleForkPass]: dead_code_elim_o1 finished after 0.334 seconds 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 542mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:55Z USER 293 (nc00/sg00) [ModuleForkPass]: dead_code_elim_o1 finished after 0.336 seconds 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 542mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:55Z USER 293 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:54:55Z USER 293 [BackendPassManager]: mod_parallel_pass finished after 1.474 seconds 2025-11-09T20:54:55Z INFO 293 [BackendPassManager]: curr_vmrss: 542mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:55Z USER 293 [BackendPassManager]: Running subgraph_parallel_pass 2025-11-09T20:54:55Z INFO 293 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=2 functions=2 allocs=17632 blocks=2 instructions=59076 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:55Z USER 293 (sg00) [SubgraphForkPass]: Running localize_shared_memory 2025-11-09T20:54:55Z INFO 293 (sg00) [SubgraphForkPass]: Inputs to localize_shared_memory: modules=2 functions=2 allocs=17632 blocks=2 instructions=59076 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:55Z USER 293 (sg00) [SubgraphForkPass]: localize_shared_memory finished after 0.004 seconds 2025-11-09T20:54:55Z INFO 293 (sg00) [SubgraphForkPass]: curr_vmrss: 542mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:55Z INFO 293 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 17632 memory location(s), 2 block(s), and 59076 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:55Z USER 293 [SubgraphForkPass]: Compilation status: Total subgraphs: 1, Passed: 1, Failed: 0 2025-11-09T20:54:55Z USER 293 [BackendPassManager]: subgraph_parallel_pass finished after 0.007 seconds 2025-11-09T20:54:55Z INFO 293 [BackendPassManager]: curr_vmrss: 542mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:55Z USER 293 [BackendPassManager]: Running mod_parallel_pass 2025-11-09T20:54:55Z INFO 293 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=2 allocs=17632 blocks=2 instructions=59076 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:55Z USER 293 (nc00/sg00) [ModuleForkPass]: Running birverifier 2025-11-09T20:54:55Z USER 293 (nc01/sg00) [ModuleForkPass]: Running birverifier 2025-11-09T20:54:55Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:55Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.425-t36485_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.425||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.769-t36493_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.769||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.1113-t36501_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.1113||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.1457-t36509_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.1457||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.1801-t36517_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.1801||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.2145-t36525_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.2145||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.2489-t36533_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.2489||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.2833-t36541_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.2833||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.3177-t36549_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.3177||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.3521-t36557_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.3521||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.3865-t36565_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.3865||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.4209-t36573_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.4209||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.4553-t36581_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.4553||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.4897-t36589_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.4897||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.5241-t36597_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.5241||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.5585-t36605_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.5585||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.5929-t36613_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.5929||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.6273-t36621_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.6273||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.6617-t36629_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.6617||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.6961-t36637_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.6961||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.7305-t36645_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.7305||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.7649-t36653_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.7649||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.7993-t36661_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.7993||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.8337-t36669_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.8337||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.8681-t36677_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.8681||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.9025-t36685_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.9025||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.9369-t36693_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.9369||UNDEF||[128, 64, 1]> 2025-11-09T20:54:55Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.9713-t36701_i1}@SB<0,0>(128x128)#Internal DebugInfo: <_dot.9713||UNDEF||[128, 64, 1]> 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: birverifier finished after 0.546 seconds 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: birverifier finished after 0.546 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:54:56Z USER 293 [BackendPassManager]: mod_parallel_pass finished after 0.551 seconds 2025-11-09T20:54:56Z INFO 293 [BackendPassManager]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z USER 293 [BackendPassManager]: Running subgraph_parallel_pass 2025-11-09T20:54:56Z INFO 293 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=2 functions=2 allocs=17632 blocks=2 instructions=59076 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (sg00) [SubgraphForkPass]: Running lnc_verifier 2025-11-09T20:54:56Z INFO 293 (sg00) [SubgraphForkPass]: Inputs to lnc_verifier: modules=2 functions=2 allocs=17632 blocks=2 instructions=59076 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (sg00) [SubgraphForkPass]: lnc_verifier finished after 0.022 seconds 2025-11-09T20:54:56Z INFO 293 (sg00) [SubgraphForkPass]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 17632 memory location(s), 2 block(s), and 59076 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 [SubgraphForkPass]: Compilation status: Total subgraphs: 1, Passed: 1, Failed: 0 2025-11-09T20:54:56Z USER 293 [BackendPassManager]: subgraph_parallel_pass finished after 0.025 seconds 2025-11-09T20:54:56Z INFO 293 [BackendPassManager]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z USER 293 [BackendPassManager]: Running mod_parallel_pass 2025-11-09T20:54:56Z INFO 293 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=2 allocs=17632 blocks=2 instructions=59076 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: Running instruction_reorder 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: Running instruction_reorder 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to instruction_reorder: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to instruction_reorder: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: instruction_reorder finished after 0.018 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: Running psum_legalization 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: instruction_reorder finished after 0.019 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to psum_legalization: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: Running psum_legalization 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to psum_legalization: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: psum_legalization finished after 0.012 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: Running non_ssa_legalization 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: psum_legalization finished after 0.011 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [NonSSALeg]: remove_redundant_loads 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: Running non_ssa_legalization 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [NonSSALeg]: remove_redundant_loads 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [NonSSALeg]: remove_redundant_loads: 0 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [NonSSALeg]: remove_redundant_loads: 0 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [NonSSALeg]: [Non-SSA legalization]created 0 memorylocations 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: non_ssa_legalization finished after 0.050 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: Running legalize_cce_dma 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to legalize_cce_dma: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: legalize_cce_dma finished after 0.005 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: Running error_injector 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to error_injector: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z WARNING 293 (nc01/sg00) [ErrorInjector]: Unrecognized injected error value "0" 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: error_injector finished after 0.001 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [NonSSALeg]: [Non-SSA legalization]created 0 memorylocations 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: non_ssa_legalization finished after 0.059 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: Running vn_splitter 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to vn_splitter: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: Running legalize_cce_dma 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to legalize_cce_dma: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [VNSplitter]: INFO (VNSplitter) Collected all the internal vnodes: size = 0 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [VNSplitter]: INFO (VNSplitter) Done with analyze and splitting: total dead nodes = 0 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: legalize_cce_dma finished after 0.009 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 548mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: Running error_injector 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to error_injector: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z WARNING 293 (nc00/sg00) [ErrorInjector]: Unrecognized injected error value "0" 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: error_injector finished after 0.001 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 549mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: Running vn_splitter 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to vn_splitter: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [VNSplitter]: INFO (VNSplitter) Collected all the internal vnodes: size = 6 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [VNSplitter]: INFO (VNSplitter) Done with analyze and splitting: total dead nodes = 0 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ShrinkDN]: INFO (ShrinkDN): Shrunk 1 nodes. Total savings 504 bytes/partition 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ShrinkDN]: INFO (ShrinkDN): Shrunk 2 nodes. Total savings 14336 bytes/partition 2025-11-09T20:54:56Z INFO 293 [PerformanceProfiler]: number of tensorizer non-local-tensor caused reload left 0 2025-11-09T20:54:56Z INFO 293 [PerformanceProfiler]: number of tensorizer non-local-tensor caused spill left 0 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [VNSplitterPass]: INFO (VNSplitter) Time: 0 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [VNSplitterPass]: INFO (VerticalFusion) Time: 0.013 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [VNSplitterPass]: INFO (ShrinkDN) Time: 0.014 seconds 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: vn_splitter finished after 0.042 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 549mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: Running constant_propagate 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to constant_propagate: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ConstantPropagate]: [Constant_propagate for select] directly remove instruction number: 0 2025-11-09T20:54:56Z INFO 293 [PerformanceProfiler]: number of tensorizer non-local-tensor caused reload left 0 2025-11-09T20:54:56Z INFO 293 [PerformanceProfiler]: number of tensorizer non-local-tensor caused spill left 0 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [VNSplitterPass]: INFO (VNSplitter) Time: 0 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [VNSplitterPass]: INFO (VerticalFusion) Time: 0.01 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [VNSplitterPass]: INFO (ShrinkDN) Time: 0.015 seconds 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: vn_splitter finished after 0.043 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 549mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: Running constant_propagate 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to constant_propagate: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ConstantPropagate]: [Constant_propagate for select] directly remove instruction number: 0 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ConstantPropagate]: eliminateDeadStore removed 0 instructions 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ConstantPropagate]: eliminateDeadStore removed 0 instructions 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ConstantPropagate]: [Constant_propagate for Affineselect] directly remove instruction number: 0 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ConstantPropagate]: eliminateDeadStore removed 0 instructions 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ConstantPropagate]: [Constant_propagate for Affineselect] directly remove instruction number: 0 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ConstantPropagate]: eliminateDeadStore removed 0 instructions 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: constant_propagate finished after 0.212 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 549mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: Running lower_ac 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to lower_ac: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ConstantPropagate]: remove_must_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [LowerAC]: INFO (LowerAC) Lowered 0 loads, 0 saves, 0 copies. 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: lower_ac finished after 0.009 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 549mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: Running input_dma_coalescing 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to input_dma_coalescing: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ConstantPropagate]: remove_redundant_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ConstantPropagate]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: constant_propagate finished after 0.231 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 550mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: Running lower_ac 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to lower_ac: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: DMA input Coalescing combined 0 input loads 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: input_dma_coalescing finished after 0.033 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 550mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: Running remat_optimization 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to remat_optimization: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [LowerAC]: INFO (LowerAC) Lowered 0 loads, 0 saves, 0 copies. 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: lower_ac finished after 0.015 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 550mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: Running input_dma_coalescing 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to input_dma_coalescing: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [RematOpt]: Removed 0 remat instructions 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: remat_optimization finished after 0.029 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 551mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: Running coalesce_multichannel_cc_ops 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to coalesce_multichannel_cc_ops: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: coalesce_multichannel_cc_ops finished after 0.011 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 551mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: DMA input Coalescing combined 0 input loads 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: input_dma_coalescing finished after 0.038 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 551mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: Running infer_stream_ids 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: Running remat_optimization 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to infer_stream_ids: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to remat_optimization: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: infer_stream_ids finished after 0.006 seconds 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 551mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8381 memory location(s), 1 block(s), and 28608 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z USER 293 (nc01/sg00) [ModuleForkPass]: Running pre_sched 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to pre_sched: modules=1 functions=1 allocs=8381 blocks=1 instructions=28608 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: Start PRE scheduling 2 cores: 1 at: Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 [LayerSpiller]: LayerSpill: Start... 2025-11-09T20:54:56Z INFO 293 [LayerSpiller]: LayerSpill: Found 224 Splits CCs 2025-11-09T20:54:56Z INFO 293 [LayerSpiller]: Grouped CCs to 224 clusters. 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [RematOpt]: Removed 0 remat instructions 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: remat_optimization finished after 0.028 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 551mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: Running coalesce_multichannel_cc_ops 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to coalesce_multichannel_cc_ops: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z INFO 293 [LayerSpiller]: LayerSpill: To Spill 3 multi-layer tensors 2025-11-09T20:54:56Z INFO 293 [LayerSpiller]: LayerSpill: set uninit flag on 0 insts 2025-11-09T20:54:56Z INFO 293 [LayerSpiller]: LayerSpill: Done. 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: Start split live ranges Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: coalesce_multichannel_cc_ops finished after 0.008 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 551mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: Running infer_stream_ids 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to infer_stream_ids: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: Num_Splits: 1 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: infer_stream_ids finished after 0.009 seconds 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 551mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9251 memory location(s), 1 block(s), and 30468 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z USER 293 (nc00/sg00) [ModuleForkPass]: Running pre_sched 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: End split live ranges Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: Strt remove redundncies Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: remove_redundant_memsets 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to pre_sched: modules=1 functions=1 allocs=9251 blocks=1 instructions=30468 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: Start PRE scheduling 2 cores: 1 at: Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 [LayerSpiller]: LayerSpill: Start... 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: remove_redundant_memsets: 0 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: remove_redundant_loads 2025-11-09T20:54:56Z INFO 293 [LayerSpiller]: LayerSpill: Found 224 Splits CCs 2025-11-09T20:54:56Z INFO 293 [LayerSpiller]: Grouped CCs to 224 clusters. 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: remove_redundant_loads: 0 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: End remove redundncies Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: Start DCE Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 [LayerSpiller]: LayerSpill: To Spill 3 multi-layer tensors 2025-11-09T20:54:56Z INFO 293 [LayerSpiller]: LayerSpill: set uninit flag on 0 insts 2025-11-09T20:54:56Z INFO 293 [LayerSpiller]: LayerSpill: Done. 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: Start split live ranges Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: eliminateDeadStore removed 0 instructions 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: Num_Splits: 1 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: End split live ranges Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: Strt remove redundncies Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: remove_redundant_memsets 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: remove_redundant_memsets: 5 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: remove_redundant_loads 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: remove_redundant_loads: 0 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: End remove redundncies Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: Start DCE Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: remove_must_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: eliminateDeadStore removed 0 instructions 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: remove_redundant_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: End DCE Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: remove_must_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: remove_redundant_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys 2025-11-09T20:54:56Z INFO 293 (nc00/sg00) [PreSched]: End DCE Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [PreSched]: Start build flow dependencies Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [build_flow_deps]: Start build fdeps. Invocation: 1Sun Nov 9 20:54:56 2025 2025-11-09T20:54:56Z INFO 293 (nc01/sg00) [build_flow_deps]: Allocs: 8389 instructions: 28616 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [PreSched]: Start build flow dependencies Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [build_flow_deps]: Start build fdeps. Invocation: 2Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [build_flow_deps]: Allocs: 9259 instructions: 30471 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [build_flow_deps]: Build fdeps inserted 71890 edges 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [build_flow_deps]: Done build fdeps 71890 Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [PreSched]: End build flow dependencies Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [PreSched]: Start remove useless insts Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [PreSched]: remove_useless_insts 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [PreSched]: remove Useless Instructions: 0 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [PreSched]: End remove useless insts Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [PreSched]: Start scratchpad optimization Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [PreSched]: End scratchpad optimization Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [build_flow_deps]: Build fdeps inserted 86241 edges 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [build_flow_deps]: Done build fdeps 86241 Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [PreSched]: End build flow dependencies Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [PreSched]: Start remove useless insts Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [PreSched]: remove_useless_insts 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [PreSched]: remove Useless Instructions: 0 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [PreSched]: End remove useless insts Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [PreSched]: Start scratchpad optimization Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [PreSched]: End scratchpad optimization Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [PreSched]: DONE PRE scheduling Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z USER 293 (nc01/sg00) [ModuleForkPass]: pre_sched finished after 0.990 seconds 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 572mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:57Z USER 293 (nc01/sg00) [ModuleForkPass]: Running tensor_copy_elim 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=8389 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [TensorCopyElim]: Tensor CP elimination: 0 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [PreSched]: DONE PRE scheduling Sun Nov 9 20:54:57 2025 2025-11-09T20:54:57Z USER 293 (nc00/sg00) [ModuleForkPass]: pre_sched finished after 1.102 seconds 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 572mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9259 memory location(s), 1 block(s), and 30471 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:57Z USER 293 (nc00/sg00) [ModuleForkPass]: Running tensor_copy_elim 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=9259 blocks=1 instructions=30471 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [TensorCopyElim]: eliminateDeadStore removed 0 instructions 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [TensorCopyElim]: Tensor CP elimination: 63 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [TensorCopyElim]: remove_must_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [TensorCopyElim]: eliminateDeadStore removed 0 instructions 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [TensorCopyElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [TensorCopyElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys 2025-11-09T20:54:57Z USER 293 (nc01/sg00) [ModuleForkPass]: tensor_copy_elim finished after 0.260 seconds 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 572mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:57Z USER 293 (nc01/sg00) [ModuleForkPass]: Running dynamic_dma_setup 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to dynamic_dma_setup: modules=1 functions=1 allocs=8389 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:57Z USER 293 (nc01/sg00) [ModuleForkPass]: dynamic_dma_setup finished after 0.001 seconds 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 572mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8390 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:57Z USER 293 (nc01/sg00) [ModuleForkPass]: Running runtime_memory_reservation 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to runtime_memory_reservation: modules=1 functions=1 allocs=8390 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:57Z USER 293 (nc01/sg00) [ModuleForkPass]: runtime_memory_reservation finished after 0.000 seconds 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 572mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8391 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:57Z USER 293 (nc01/sg00) [ModuleForkPass]: Running lower_klir_kernel 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=8391 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:57Z USER 293 (nc01/sg00) [ModuleForkPass]: lower_klir_kernel finished after 0.006 seconds 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 572mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8391 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:57Z USER 293 (nc01/sg00) [ModuleForkPass]: Running lower_nki_kernel 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=8391 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:57Z USER 293 (nc01/sg00) [ModuleForkPass]: lower_nki_kernel finished after 0.005 seconds 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 572mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8391 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:57Z USER 293 (nc01/sg00) [ModuleForkPass]: Running coloring_allocator_psum 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to coloring_allocator_psum: modules=1 functions=1 allocs=8391 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: Allocating functions 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: linearize and check 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [TensorCopyElim]: remove_must_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [TensorCopyElim]: remove_redundant_alias_dmacopy removed 0 DMAcopys 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [TensorCopyElim]: remove_redundant_internal2internal_dmacopy removed 0 DMAcopys 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [PSUM_Allocator]: allocating PSUM 2025-11-09T20:54:57Z USER 293 (nc00/sg00) [ModuleForkPass]: tensor_copy_elim finished after 0.190 seconds 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 572mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9196 memory location(s), 1 block(s), and 30408 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:57Z USER 293 (nc00/sg00) [ModuleForkPass]: Running dynamic_dma_setup 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to dynamic_dma_setup: modules=1 functions=1 allocs=9196 blocks=1 instructions=30408 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:57Z USER 293 (nc00/sg00) [ModuleForkPass]: dynamic_dma_setup finished after 0.001 seconds 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 573mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9197 memory location(s), 1 block(s), and 30408 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:57Z USER 293 (nc00/sg00) [ModuleForkPass]: Running runtime_memory_reservation 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to runtime_memory_reservation: modules=1 functions=1 allocs=9197 blocks=1 instructions=30408 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:57Z USER 293 (nc00/sg00) [ModuleForkPass]: runtime_memory_reservation finished after 0.001 seconds 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 573mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [PSUM_Allocator]: main loop 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9198 memory location(s), 1 block(s), and 30408 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:57Z USER 293 (nc00/sg00) [ModuleForkPass]: Running lower_klir_kernel 2025-11-09T20:54:57Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=9198 blocks=1 instructions=30408 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [PSUM_Allocator]: renumber locations 2025-11-09T20:54:57Z INFO 293 (nc01/sg00) [PSUM_Allocator]: size = 2931 2025-11-09T20:54:58Z USER 293 (nc00/sg00) [ModuleForkPass]: lower_klir_kernel finished after 0.006 seconds 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 573mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9198 memory location(s), 1 block(s), and 30408 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:58Z USER 293 (nc00/sg00) [ModuleForkPass]: Running lower_nki_kernel 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=9198 blocks=1 instructions=30408 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:58Z USER 293 (nc00/sg00) [ModuleForkPass]: lower_nki_kernel finished after 0.005 seconds 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 573mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9198 memory location(s), 1 block(s), and 30408 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:58Z USER 293 (nc00/sg00) [ModuleForkPass]: Running coloring_allocator_psum 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to coloring_allocator_psum: modules=1 functions=1 allocs=9198 blocks=1 instructions=30408 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: Allocating functions 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: linearize and check 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: build_no_bitmap start 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: 100% PSUM demand before spilling 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: PSUM high-water mark = 8 tensors 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: found 4767 edges 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: mean: 3.25281 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: median: 1.98366 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: adjacency vectors require 38136 bytes 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: build_no_bitmap done 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: find costs 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: allocating PSUM 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: main loop 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: renumber locations 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: size = 3144 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: best-of-n loop, heuristic = 0, allow_psum_spill_within_accum_group = false 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: simplify interference graph 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: initialize low and high 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: lo = 2894 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: hi = 37 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: inf = 0 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: total = 2931 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: simplify 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: new candidates = 0 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: select ranges 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: no more spills 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: PSUM score = 0 (lower is better) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: spilling from PSUM cost about 0 cycles 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [PSUM_Allocator]: 100% PSUM utilization after allocation 2025-11-09T20:54:58Z USER 293 (nc01/sg00) [ModuleForkPass]: coloring_allocator_psum finished after 0.234 seconds 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 573mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8391 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:58Z USER 293 (nc01/sg00) [ModuleForkPass]: Running dma_optimization_psum 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to dma_optimization_psum: modules=1 functions=1 allocs=8391 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: build_no_bitmap start 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: 100% PSUM demand before spilling 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: PSUM high-water mark = 8 tensors 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: found 4857 edges 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: mean: 3.08969 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: median: 1.7129 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: adjacency vectors require 38856 bytes 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: build_no_bitmap done 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: find costs 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: best-of-n loop, heuristic = 0, allow_psum_spill_within_accum_group = false 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: simplify interference graph 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: initialize low and high 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: lo = 3107 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: hi = 37 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: inf = 0 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: total = 3144 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: simplify 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: new candidates = 0 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: select ranges 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload instructions 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload memory locations 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: no more spills 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: PSUM score = 0 (lower is better) 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: spilling from PSUM cost about 0 cycles 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [PSUM_Allocator]: 100% PSUM utilization after allocation 2025-11-09T20:54:58Z USER 293 (nc01/sg00) [ModuleForkPass]: dma_optimization_psum finished after 0.122 seconds 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 573mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8391 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:58Z USER 293 (nc01/sg00) [ModuleForkPass]: Running address_rotation_psum 2025-11-09T20:54:58Z USER 293 (nc00/sg00) [ModuleForkPass]: coloring_allocator_psum finished after 0.294 seconds 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 573mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to address_rotation_psum: modules=1 functions=1 allocs=8391 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9198 memory location(s), 1 block(s), and 30408 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:58Z USER 293 (nc00/sg00) [ModuleForkPass]: Running dma_optimization_psum 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to dma_optimization_psum: modules=1 functions=1 allocs=9198 blocks=1 instructions=30408 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 3 PSUM Banks 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload instructions 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [psum spill optimization]: removed 0 spill/reload memory locations 2025-11-09T20:54:58Z USER 293 (nc00/sg00) [ModuleForkPass]: dma_optimization_psum finished after 0.126 seconds 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 575mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9198 memory location(s), 1 block(s), and 30408 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:58Z USER 293 (nc00/sg00) [ModuleForkPass]: Running address_rotation_psum 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to address_rotation_psum: modules=1 functions=1 allocs=9198 blocks=1 instructions=30408 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 115 PSUM Banks 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 71 PSUM Banks 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 528 PSUM Banks 2025-11-09T20:54:58Z USER 293 (nc01/sg00) [ModuleForkPass]: address_rotation_psum finished after 0.293 seconds 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 575mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8391 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:58Z USER 293 (nc01/sg00) [ModuleForkPass]: Running coloring_allocator_sb 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to coloring_allocator_sb: modules=1 functions=1 allocs=8391 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes loaded 452782918 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA average loaded DMA size 3831 bytes 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes saved 608528 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA average saved DMA size 363 bytes 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 35728 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 24 bytes 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: Allocating functions 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: linearize and check 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 200 PSUM Banks 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: allocating SB 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: main loop 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: renumber locations 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: size = 4832 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: find partners 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: found 2340 accumulation groups 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: largest = _dot.9701-t32986_i10 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: tensors = 2 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: requires 8320 bytes/partition 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: expanding partners 2025-11-09T20:54:58Z INFO 293 []: find first defs for local 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 548 PSUM Banks 2025-11-09T20:54:58Z USER 293 (nc00/sg00) [ModuleForkPass]: address_rotation_psum finished after 0.309 seconds 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 577mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9198 memory location(s), 1 block(s), and 30408 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:58Z USER 293 (nc00/sg00) [ModuleForkPass]: Running coloring_allocator_sb 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to coloring_allocator_sb: modules=1 functions=1 allocs=9198 blocks=1 instructions=30408 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes loaded 454305750 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA average loaded DMA size 3805 bytes 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA DRAM bytes saved 1322294 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Pre GCA average saved DMA size 135 bytes 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 94000 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 48 bytes 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: Allocating functions 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: linearize and check 2025-11-09T20:54:58Z INFO 293 []: find first defs for global 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [SB_Allocator]: allocating SB 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [SB_Allocator]: main loop 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [SB_Allocator]: renumber locations 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [SB_Allocator]: size = 5417 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: find loads 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: 2 pin count 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: 1038 remat count 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: 2 pinned tensors will require about 16392 bytes/partition 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: build interference graph 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: pass 1 int-tree 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [SB_Allocator]: find partners 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [SB_Allocator]: found 2552 accumulation groups 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [SB_Allocator]: largest = _dot.5699-t32239_i1 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [SB_Allocator]: tensors = 2 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [SB_Allocator]: requires 8320 bytes/partition 2025-11-09T20:54:58Z INFO 293 (nc00/sg00) [SB_Allocator]: expanding partners 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Num intervals 4832 Num locations 4832 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: IntervalTree Build Done 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: info.neighbors init Done 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: info.neighbors partners Done 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: IntervalTree readback Done 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: edge: 57241 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: mean: 23.6925 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: median: 15.1803 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: find costs 2025-11-09T20:54:58Z INFO 293 []: find first defs for local 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: best-of-n loop, heuristic = 0 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: simplify interference graph 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: initialize safe & unsafe 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: safe = 4822 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: unsafe = 8 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: inf = 0 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: total = 4830 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: simplify 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: simplify_step3_sorted2 #Unsafe 0 #Pinned 0 #Safe 0 minCost 1.79769e+308 maxCost 2.22507e-308 locations 4832 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: new candidates = 0 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: select ranges 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Total: 4830 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Spilled: 0.000 (0) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Allocated: 1.000 (4830) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Rover zone: 0.821 (3967) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Pre-rover zone: 0.162 (781) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Post-rover zone: 0.011 (54) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Slice zone: 0.006 (28) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Blocks nothing: 0.254 (1228) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Blocks medium: 0.035 (171) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Visited until medium blocking (mean): 0.379 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Visited until medium blocking (median): 0.338 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Visited until medium blocking (p95): 0.945 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Blocks tall: 0.710 (3431) 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Visited until tall blocking (mean): 0.559 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Visited until tall blocking (median): 0.365 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Visited until tall blocking (p95): 1.000 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: Success 2025-11-09T20:54:58Z INFO 293 []: find first defs for global 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: SB spills = 0 tensors 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: size = 0 bytes/partition 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: remats = 0 tensors 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: unpinned = 0 tensors 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: size = 0 bytes/partition 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: SB score = 0 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: spilling from SB cost about 0 cycles 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: 16392 bytes/partition (100%) successfully pinned 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: pinning saved approximately 8300 cycles 2025-11-09T20:54:58Z INFO 293 (nc01/sg00) [SB_Allocator]: 0% SB utilization after allocation 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes loaded 452782918 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average loaded DMA size 3831 bytes 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes saved 608528 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average saved DMA size 363 bytes 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 35728 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 24 bytes 2025-11-09T20:54:59Z USER 293 (nc01/sg00) [ModuleForkPass]: coloring_allocator_sb finished after 0.418 seconds 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 582mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8391 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:59Z USER 293 (nc01/sg00) [ModuleForkPass]: Running address_rotation_sb 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=8391 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: find loads 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: 2 pin count 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: 1053 remat count 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: 2 pinned tensors will require about 16392 bytes/partition 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: build interference graph 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: pass 1 int-tree 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Num intervals 5417 Num locations 5417 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: IntervalTree Build Done 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: info.neighbors init Done 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: info.neighbors partners Done 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: IntervalTree readback Done 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: edge: 63396 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: mean: 23.4063 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: median: 14.7275 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: find costs 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: best-of-n loop, heuristic = 0 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: simplify interference graph 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: initialize safe & unsafe 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: safe = 5405 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: unsafe = 10 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: inf = 0 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: total = 5415 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: simplify 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: simplify_step3_sorted2 #Unsafe 0 #Pinned 0 #Safe 0 minCost 1.79769e+308 maxCost 2.22507e-308 locations 5417 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: new candidates = 0 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: select ranges 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address 2025-11-09T20:54:59Z USER 293 (nc01/sg00) [ModuleForkPass]: address_rotation_sb finished after 0.117 seconds 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 583mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8391 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:59Z USER 293 (nc01/sg00) [ModuleForkPass]: Running dma_optimization_sb 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to dma_optimization_sb: modules=1 functions=1 allocs=8391 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: DMA optimization In bytes loaded or saved 453391446, 97.3711% input load, 0% output write, 2.62889% spill/reload [sg0000] 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Total: 5415 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Spilled: 0.000 (0) 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Allocated: 1.000 (5415) 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Rover zone: 0.812 (4397) 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Pre-rover zone: 0.170 (923) 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Post-rover zone: 0.012 (65) 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Slice zone: 0.006 (30) 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Blocks nothing: 0.228 (1237) 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Blocks medium: 0.024 (130) 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Visited until medium blocking (mean): 0.552 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Visited until medium blocking (median): 0.499 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Visited until medium blocking (p95): 0.942 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Blocks tall: 0.748 (4048) 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Visited until tall blocking (mean): 0.529 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Visited until tall blocking (median): 0.272 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Visited until tall blocking (p95): 1.000 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: Success 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: SB spills = 0 tensors 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: size = 0 bytes/partition 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: remats = 0 tensors 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: unpinned = 0 tensors 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: size = 0 bytes/partition 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: SB score = 0 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: spilling from SB cost about 0 cycles 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: 16392 bytes/partition (100%) successfully pinned 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: pinning saved approximately 8300 cycles 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [SB_Allocator]: 0% SB utilization after allocation 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: removed 0 identical load 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: adjusted 0 DMACopy remat 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes loaded 454305750 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average loaded DMA size 3805 bytes 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes saved 1322294 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average saved DMA size 135 bytes 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA DRAM bytes DMACopyed 94000 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: INFO: Post GCA average DMACopyed DMA size 48 bytes 2025-11-09T20:54:59Z USER 293 (nc00/sg00) [ModuleForkPass]: coloring_allocator_sb finished after 0.507 seconds 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 584mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9198 memory location(s), 1 block(s), and 30408 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:59Z USER 293 (nc00/sg00) [ModuleForkPass]: Running address_rotation_sb 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=9198 blocks=1 instructions=30408 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: sub-graph will get execute 1 times 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [Load Merging]: removed 0 remat/cloned instructions 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [Load shrink]: shrinked 0 GCA remat/cloned instructions 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [Load Merging + Load shrink] reduced input/const loading DMA traffic 0, 0% out of total dma traffic(4.41472e+08) 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address 2025-11-09T20:54:59Z USER 293 (nc00/sg00) [ModuleForkPass]: address_rotation_sb finished after 0.177 seconds 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 586mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9198 memory location(s), 1 block(s), and 30408 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:54:59Z USER 293 (nc00/sg00) [ModuleForkPass]: Running dma_optimization_sb 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to dma_optimization_sb: modules=1 functions=1 allocs=9198 blocks=1 instructions=30408 Max writers: 150 Max Readers: 4719 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: DMA optimization In bytes loaded or saved 455628044, 97.074% input load, 3.51164e-06% output write, 2.92602% spill/reload [sg0000] 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload instructions 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload memory locations 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [Re-allocation Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [remove extra save] removed 0 memlocs and 0 instructions 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: removed 0 identical load 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: adjusted 0 DMACopy remat 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload instructions 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload memory locations 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: eliminateDeadStore removed 0 instructions 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: sub-graph will get execute 1 times 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [Load Merging]: removed 0 remat/cloned instructions 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [Load shrink]: shrinked 0 GCA remat/cloned instructions 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [Load Merging + Load shrink] reduced input/const loading DMA traffic 65536, 0.0143837% out of total dma traffic(4.42296e+08) 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 2 spill/reload instructions 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 2 spill/reload memory locations 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: DMA SpillSave Coalescing Round 0 combined 0 SpillSaves and Reloads 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: average loaded DMA size 3831 bytes 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [spill optimization round 1]: removed 0 spill/reload instructions 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [spill optimization round 1]: removed 0 spill/reload memory locations 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: average saved DMA size 363 bytes 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 2048, 0.0153618% out of total spill/reload dma traffic 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes loaded 452782918 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing average loaded DMA size 3831 bytes 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes saved 608528 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing average saved DMA size 363 bytes 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload instructions 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [Allocation optimization]: removed 0 spill/reload memory locations 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [Re-allocation Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [Experiment partial DMA access] reduced DMA traffic 0, 0% out of total spill/reload dma traffic 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: [DMA optimization] reduced DMA traffic 0, 0% out of total dma traffic 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: DMA optimization Out bytes loaded or saved 453391446, 97.3711% input load, 0% output write, 2.62889% spill/reload [sg0000] 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes loaded 452782918 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average loaded DMA size 3831 bytes 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes saved 608528 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average saved DMA size 363 bytes 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes DMAcopyed 35728 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average DMAcopyed DMA size 24 bytes 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average DMA size 3736 bytes 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: INFO: Finished set_spill_canreadUninit(module); 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: DMA optimization re-enable optimization 2025-11-09T20:54:59Z USER 293 (nc01/sg00) [ModuleForkPass]: dma_optimization_sb finished after 0.745 seconds 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 588mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:54:59Z USER 293 (nc01/sg00) [ModuleForkPass]: Running address_rotation_sb 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=8389 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload instructions 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [spill optimization round 0]: removed 0 spill/reload memory locations 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [Spill Optimization] reduced DMA traffic 0, 0% out of total spill/reload dma traffic 2025-11-09T20:54:59Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [remove extra save] removed 0 memlocs and 0 instructions 2025-11-09T20:54:59Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 96 Sb address 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload instructions 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [remove_memset_spill]: removed 0 spill/reload memory locations 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: eliminateDeadStore removed 0 instructions 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 766 Sb address 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: DMA SpillSave Coalescing Round 0 combined 0 SpillSaves and Reloads 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: average loaded DMA size 3810 bytes 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: average saved DMA size 136 bytes 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes loaded 454239190 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing average loaded DMA size 3810 bytes 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing DRAM bytes saved 1321270 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA coalescing average saved DMA size 136 bytes 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [DMA optimization]Reload_just_for_save Optimization removed 0 memlocs 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [Experiment partial DMA access] reduced DMA traffic 0, 0% out of total spill/reload dma traffic 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: [DMA optimization] reduced DMA traffic 67584, 0.0148332% out of total dma traffic 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: DMA optimization Out bytes loaded or saved 455560460, 97.074% input load, 3.51216e-06% output write, 2.92601% spill/reload [sg0000] 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes loaded 454239190 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average loaded DMA size 3810 bytes 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes saved 1321270 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average saved DMA size 136 bytes 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization DRAM bytes DMAcopyed 94000 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average DMAcopyed DMA size 48 bytes 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: INFO: Post DMA optimization average DMA size 3481 bytes 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: INFO: Finished set_spill_canreadUninit(module); 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: DMA optimization re-enable optimization 2025-11-09T20:55:00Z USER 293 (nc00/sg00) [ModuleForkPass]: dma_optimization_sb finished after 0.771 seconds 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 588mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30405 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:00Z USER 293 (nc00/sg00) [ModuleForkPass]: Running address_rotation_sb 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=9193 blocks=1 instructions=30405 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 134 Sb address 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 141 Sb address 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 726 Sb address 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 106 Sb address 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 1526 Sb address 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: address_rotation_sb finished after 0.644 seconds 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 589mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: Running coloring_allocator_dram 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to coloring_allocator_dram: modules=1 functions=1 allocs=8389 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: Allocating functions 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: linearize and check 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Local 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: reserved space = 164096 bytes 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: spill space = 67088 bytes 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: aligned spill space = 77824 bytes 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: dram space = 107374182400 bytes 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: renumber locations 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: size = 4 2025-11-09T20:55:00Z INFO 293 []: find first defs for local 2025-11-09T20:55:00Z INFO 293 []: find first defs for global 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: Num intervals 4 Num locations 4 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: IntervalTree Build Done 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: info.neighbors init Done 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: IntervalTree readback Done 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: simplify interference graph 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: initialize low and high 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: lo = 4 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: hi = 0 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: total = 4 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: simplify 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: new candidates = 0 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: select ranges 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: CC buffer size limit 524288000 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: allreduce_dram_hwm 0 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: Real CC buffer size 0 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: DRAM hwm after allocation: 77824 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DRAM_Allocator]: DRAM allocation successful 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: coloring_allocator_dram finished after 0.120 seconds 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 589mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: Running address_rotation_dram 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to address_rotation_dram: modules=1 functions=1 allocs=8389 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: Runtime page size at 512MB 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: DRAM hwm before rotation 74240 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: allreduce buffer size 524288000 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: allreduce hwm 16384 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: Real CC buffer size 16384 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: DRAM hwm after rotation 74240 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: DRAM Rotation rotated 0 Dram address 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: address_rotation_dram finished after 0.067 seconds 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 590mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: Running tensorcopy_accel 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to tensorcopy_accel: modules=1 functions=1 allocs=8389 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [TensorCopyAccel::Impl]: Running peephole optimization pass 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 177 Sb address 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [TensorCopyAccel::Impl]: Accelerated 437 out of 2542 tensorcopy in Function: sg0000 average acceleration factor: 1 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: tensorcopy_accel finished after 0.012 seconds 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 590mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28616 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: Running peephole_opts 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to peephole_opts: modules=1 functions=1 allocs=8389 blocks=1 instructions=28616 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [PeepholeOpts]: PeepholeOpts enabled? Recip: true Tsp: true Tc: false SplitSelect: true SimplifyMemset true 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: peephole_opts finished after 0.040 seconds 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 590mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28644 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: Running lower_kernel 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to lower_kernel: modules=1 functions=1 allocs=8389 blocks=1 instructions=28644 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [LowerKernel]: Started running LowerKernel 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [LowerKernel]: BIR SB coloring allocator is disabled 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [LowerKernel]: Start of kernel lowering pass, number of insts: 28644, number of allocs: 8389 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [LowerKernel]: Scan BKs time (s): 0.015072 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [LowerKernel]: Lower BKs time (s): 1e-06 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: lower_kernel finished after 0.006 seconds 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 590mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28644 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: Running lower_klir_kernel 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=8389 blocks=1 instructions=28644 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: lower_klir_kernel finished after 0.006 seconds 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 590mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28644 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: Running lower_nki_kernel 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=8389 blocks=1 instructions=28644 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: lower_nki_kernel finished after 0.006 seconds 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 590mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28644 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: Running non_ssa_legalization 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=8389 blocks=1 instructions=28644 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [NonSSALeg]: remove_redundant_loads 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [NonSSALeg]: remove_redundant_loads: 0 2025-11-09T20:55:00Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 93 Sb address 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [NonSSALeg]: [Non-SSA legalization]created 0 memorylocations 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: non_ssa_legalization finished after 0.044 seconds 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 590mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28644 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: Running dynamic_dma_cleanup 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to dynamic_dma_cleanup: modules=1 functions=1 allocs=8389 blocks=1 instructions=28644 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: dynamic_dma_cleanup finished after 0.010 seconds 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 590mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28644 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z USER 293 (nc01/sg00) [ModuleForkPass]: Running birverifier 2025-11-09T20:55:00Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=8389 blocks=1 instructions=28644 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.425-t36485_i1}@SB<0,28192>(128x128)#Internal DebugInfo: <_dot.425||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.769-t36493_i1}@SB<0,31048>(128x128)#Internal DebugInfo: <_dot.769||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.1113-t36501_i1}@SB<0,26400>(128x128)#Internal DebugInfo: <_dot.1113||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.1457-t36509_i1}@SB<0,23328>(128x128)#Internal DebugInfo: <_dot.1457||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.1801-t36517_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.1801||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.2145-t36525_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.2145||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.2489-t36533_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.2489||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.2833-t36541_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.2833||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.3177-t36549_i1}@SB<0,18432>(128x128)#Internal DebugInfo: <_dot.3177||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.3521-t36557_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.3521||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.3865-t36565_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.3865||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.4209-t36573_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.4209||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.4553-t36581_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.4553||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.4897-t36589_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.4897||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.5241-t36597_i1}@SB<0,18432>(128x128)#Internal DebugInfo: <_dot.5241||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.5585-t36605_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.5585||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.5929-t36613_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.5929||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.6273-t36621_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.6273||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.6617-t36629_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.6617||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.6961-t36637_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.6961||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.7305-t36645_i1}@SB<0,18432>(128x128)#Internal DebugInfo: <_dot.7305||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.7649-t36653_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.7649||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.7993-t36661_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.7993||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.8337-t36669_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.8337||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.8681-t36677_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.8681||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.9025-t36685_i1}@SB<0,18208>(128x128)#Internal DebugInfo: <_dot.9025||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.9369-t36693_i1}@SB<0,18432>(128x128)#Internal DebugInfo: <_dot.9369||UNDEF||[128, 64, 1]> 2025-11-09T20:55:00Z WARNING 293 [birverifier::InstVisitor]: (nc01/sg00) Non - output memory location with no reader: {_dot.9713-t36701_i1}@SB<0,26400>(128x128)#Internal DebugInfo: <_dot.9713||UNDEF||[128, 64, 1]> 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 1333 Sb address 2025-11-09T20:55:01Z USER 293 (nc01/sg00) [ModuleForkPass]: birverifier finished after 0.222 seconds 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 590mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28644 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:01Z USER 293 (nc01/sg00) [ModuleForkPass]: Running dynamic_dma_scan 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to dynamic_dma_scan: modules=1 functions=1 allocs=8389 blocks=1 instructions=28644 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:01Z USER 293 (nc01/sg00) [ModuleForkPass]: dynamic_dma_scan finished after 0.007 seconds 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 590mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28644 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:01Z USER 293 (nc01/sg00) [ModuleForkPass]: Running build_fdeps 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to build_fdeps: modules=1 functions=1 allocs=8389 blocks=1 instructions=28644 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [build_flow_deps]: Start build fdeps. Invocation: 3Sun Nov 9 20:55:01 2025 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [build_flow_deps]: Allocs: 8389 instructions: 28644 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address 2025-11-09T20:55:01Z USER 293 (nc00/sg00) [ModuleForkPass]: address_rotation_sb finished after 1.065 seconds 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 590mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30405 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:01Z USER 293 (nc00/sg00) [ModuleForkPass]: Running coloring_allocator_dram 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to coloring_allocator_dram: modules=1 functions=1 allocs=9193 blocks=1 instructions=30405 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: Allocating functions 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: linearize and check 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [build_flow_deps]: Build fdeps inserted 71918 edges 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [build_flow_deps]: Done build fdeps 71918 Sun Nov 9 20:55:01 2025 2025-11-09T20:55:01Z USER 293 (nc01/sg00) [ModuleForkPass]: build_fdeps finished after 0.300 seconds 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 590mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28644 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:01Z USER 293 (nc01/sg00) [ModuleForkPass]: Running remove_redundancies 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to remove_redundancies: modules=1 functions=1 allocs=8389 blocks=1 instructions=28644 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [RemoveRedundancies]: remove_clobbered_writes 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Local 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: reserved space = 168200 bytes 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: spill space = 83488 bytes 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: aligned spill space = 98304 bytes 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: dram space = 107374182400 bytes 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [RemoveRedundancies]: remove_clobbered_writes: 0 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [RemoveRedundancies]: remove_useless_insts 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: renumber locations 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: size = 9 2025-11-09T20:55:01Z INFO 293 []: find first defs for local 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [RemoveRedundancies]: remove Useless Instructions: 0 2025-11-09T20:55:01Z USER 293 (nc01/sg00) [ModuleForkPass]: remove_redundancies finished after 0.033 seconds 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 590mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28644 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:01Z USER 293 (nc01/sg00) [ModuleForkPass]: Running anti_dependency_analyzer 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=8389 blocks=1 instructions=28644 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB} 2025-11-09T20:55:01Z INFO 293 (nc01/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824 2025-11-09T20:55:01Z INFO 293 []: find first defs for global 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: Num intervals 9 Num locations 9 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: IntervalTree Build Done 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: info.neighbors init Done 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: IntervalTree readback Done 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: simplify interference graph 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: initialize low and high 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: lo = 9 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: hi = 0 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: total = 9 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: simplify 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: new candidates = 0 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: select ranges 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: CC buffer size limit 524288000 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: allreduce_dram_hwm 0 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: Real CC buffer size 0 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: DRAM hwm after allocation: 73728 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DRAM_Allocator]: DRAM allocation successful 2025-11-09T20:55:01Z USER 293 (nc00/sg00) [ModuleForkPass]: coloring_allocator_dram finished after 0.250 seconds 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 598mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30405 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:01Z USER 293 (nc00/sg00) [ModuleForkPass]: Running address_rotation_dram 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to address_rotation_dram: modules=1 functions=1 allocs=9193 blocks=1 instructions=30405 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: Runtime page size at 512MB 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: DRAM hwm before rotation 73728 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: allreduce buffer size 524288000 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: allreduce hwm 16384 2025-11-09T20:55:01Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: Real CC buffer size 16384 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: DRAM hwm after rotation 73728 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: DRAM Rotation rotated 0 Dram address 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: address_rotation_dram finished after 0.540 seconds 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 630mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30405 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: Running tensorcopy_accel 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to tensorcopy_accel: modules=1 functions=1 allocs=9193 blocks=1 instructions=30405 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [TensorCopyAccel::Impl]: Running peephole optimization pass 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [TensorCopyAccel::Impl]: Accelerated 521 out of 2770 tensorcopy in Function: sg0000 average acceleration factor: 1 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: tensorcopy_accel finished after 0.026 seconds 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 632mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30405 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: Running peephole_opts 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to peephole_opts: modules=1 functions=1 allocs=9193 blocks=1 instructions=30405 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [PeepholeOpts]: PeepholeOpts enabled? Recip: true Tsp: true Tc: false SplitSelect: true SimplifyMemset true 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: peephole_opts finished after 0.078 seconds 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 635mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30435 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: Running lower_kernel 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to lower_kernel: modules=1 functions=1 allocs=9193 blocks=1 instructions=30435 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [LowerKernel]: Started running LowerKernel 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [LowerKernel]: BIR SB coloring allocator is disabled 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [LowerKernel]: Start of kernel lowering pass, number of insts: 30435, number of allocs: 9193 2025-11-09T20:55:02Z USER 293 (nc01/sg00) [ModuleForkPass]: anti_dependency_analyzer finished after 0.850 seconds 2025-11-09T20:55:02Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 635mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28644 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:02Z USER 293 (nc01/sg00) [ModuleForkPass]: Running tensor_copy_elim 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [LowerKernel]: Scan BKs time (s): 0.02196 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [LowerKernel]: Lower BKs time (s): 1e-06 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: lower_kernel finished after 0.009 seconds 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 635mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=8389 blocks=1 instructions=28644 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30435 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: Running lower_klir_kernel 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to lower_klir_kernel: modules=1 functions=1 allocs=9193 blocks=1 instructions=30435 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: lower_klir_kernel finished after 0.005 seconds 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 635mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30435 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: Running lower_nki_kernel 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to lower_nki_kernel: modules=1 functions=1 allocs=9193 blocks=1 instructions=30435 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: lower_nki_kernel finished after 0.006 seconds 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 635mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30435 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: Running non_ssa_legalization 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to non_ssa_legalization: modules=1 functions=1 allocs=9193 blocks=1 instructions=30435 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [NonSSALeg]: remove_redundant_loads 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [NonSSALeg]: remove_redundant_loads: 0 2025-11-09T20:55:02Z INFO 293 (nc01/sg00) [TensorCopyElim]: Tensor CP elimination: 0 2025-11-09T20:55:02Z INFO 293 (nc01/sg00) [TensorCopyElim]: eliminateDeadStore removed 0 instructions 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [NonSSALeg]: [Non-SSA legalization]created 0 memorylocations 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: non_ssa_legalization finished after 0.068 seconds 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 636mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30435 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: Running dynamic_dma_cleanup 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to dynamic_dma_cleanup: modules=1 functions=1 allocs=9193 blocks=1 instructions=30435 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: dynamic_dma_cleanup finished after 0.012 seconds 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 636mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30435 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: Running birverifier 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=9193 blocks=1 instructions=30435 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc01/sg00) [ModuleForkPass]: tensor_copy_elim finished after 0.124 seconds 2025-11-09T20:55:02Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 636mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28644 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:02Z USER 293 (nc01/sg00) [ModuleForkPass]: Running dead_code_elim_o0 2025-11-09T20:55:02Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=8389 blocks=1 instructions=28644 Max writers: 150 Max Readers: 4215 2025-11-09T20:55:02Z USER 293 (nc01/sg00) [ModuleForkPass]: dead_code_elim_o0 finished after 0.059 seconds 2025-11-09T20:55:02Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 636mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8389 memory location(s), 1 block(s), and 28644 instruction(s). Max writers: 150 Max Readers: 4215 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: birverifier finished after 0.288 seconds 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 636mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30435 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: Running dynamic_dma_scan 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to dynamic_dma_scan: modules=1 functions=1 allocs=9193 blocks=1 instructions=30435 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: dynamic_dma_scan finished after 0.005 seconds 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 636mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30435 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: Running build_fdeps 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to build_fdeps: modules=1 functions=1 allocs=9193 blocks=1 instructions=30435 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [build_flow_deps]: Start build fdeps. Invocation: 4Sun Nov 9 20:55:02 2025 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [build_flow_deps]: Allocs: 9193 instructions: 30435 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [build_flow_deps]: Build fdeps inserted 86208 edges 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [build_flow_deps]: Done build fdeps 86208 Sun Nov 9 20:55:02 2025 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: build_fdeps finished after 0.208 seconds 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 641mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30435 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: Running remove_redundancies 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to remove_redundancies: modules=1 functions=1 allocs=9193 blocks=1 instructions=30435 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [RemoveRedundancies]: remove_clobbered_writes 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [RemoveRedundancies]: remove_clobbered_writes: 0 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [RemoveRedundancies]: remove_useless_insts 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [RemoveRedundancies]: remove Useless Instructions: 0 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: remove_redundancies finished after 0.020 seconds 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 641mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30435 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z USER 293 (nc00/sg00) [ModuleForkPass]: Running anti_dependency_analyzer 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=9193 blocks=1 instructions=30435 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB} 2025-11-09T20:55:02Z INFO 293 (nc00/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824 2025-11-09T20:55:03Z USER 293 (nc00/sg00) [ModuleForkPass]: anti_dependency_analyzer finished after 0.842 seconds 2025-11-09T20:55:03Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 662mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:03Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30435 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:03Z USER 293 (nc00/sg00) [ModuleForkPass]: Running tensor_copy_elim 2025-11-09T20:55:03Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to tensor_copy_elim: modules=1 functions=1 allocs=9193 blocks=1 instructions=30435 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:03Z INFO 293 (nc00/sg00) [TensorCopyElim]: Tensor CP elimination: 0 2025-11-09T20:55:03Z INFO 293 (nc00/sg00) [TensorCopyElim]: eliminateDeadStore removed 0 instructions 2025-11-09T20:55:03Z USER 293 (nc00/sg00) [ModuleForkPass]: tensor_copy_elim finished after 0.081 seconds 2025-11-09T20:55:03Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 662mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:03Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30435 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:03Z USER 293 (nc00/sg00) [ModuleForkPass]: Running dead_code_elim_o0 2025-11-09T20:55:03Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=9193 blocks=1 instructions=30435 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:03Z USER 293 (nc00/sg00) [ModuleForkPass]: dead_code_elim_o0 finished after 0.026 seconds 2025-11-09T20:55:03Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 662mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:03Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9193 memory location(s), 1 block(s), and 30435 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:03Z USER 293 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:55:03Z USER 293 [BackendPassManager]: mod_parallel_pass finished after 7.647 seconds 2025-11-09T20:55:03Z INFO 293 [BackendPassManager]: curr_vmrss: 662mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:03Z USER 293 [BackendPassManager]: Running subgraph_parallel_pass 2025-11-09T20:55:03Z INFO 293 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=2 functions=2 allocs=17582 blocks=2 instructions=59079 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:03Z USER 293 (sg00) [SubgraphForkPass]: Running localize_shared_memory 2025-11-09T20:55:03Z INFO 293 (sg00) [SubgraphForkPass]: Inputs to localize_shared_memory: modules=2 functions=2 allocs=17582 blocks=2 instructions=59079 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:03Z USER 293 (sg00) [SubgraphForkPass]: localize_shared_memory finished after 0.008 seconds 2025-11-09T20:55:03Z INFO 293 (sg00) [SubgraphForkPass]: curr_vmrss: 662mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:03Z INFO 293 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 17582 memory location(s), 2 block(s), and 59079 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:03Z USER 293 (sg00) [SubgraphForkPass]: Running lower_local_collectives 2025-11-09T20:55:03Z INFO 293 (sg00) [SubgraphForkPass]: Inputs to lower_local_collectives: modules=2 functions=2 allocs=17582 blocks=2 instructions=59079 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:03Z USER 293 (sg00) [SubgraphForkPass]: lower_local_collectives finished after 0.043 seconds 2025-11-09T20:55:03Z INFO 293 (sg00) [SubgraphForkPass]: curr_vmrss: 662mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:03Z INFO 293 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 17918 memory location(s), 2 block(s), and 59869 instruction(s). Max writers: 150 Max Readers: 4719 2025-11-09T20:55:03Z USER 293 (sg00) [SubgraphForkPass]: Running extend_shared_lifetimes 2025-11-09T20:55:03Z INFO 293 (sg00) [SubgraphForkPass]: Inputs to extend_shared_lifetimes: modules=2 functions=2 allocs=17918 blocks=2 instructions=59869 Max writers: 150 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 (sg00) [SubgraphForkPass]: extend_shared_lifetimes finished after 0.099 seconds 2025-11-09T20:55:04Z INFO 293 (sg00) [SubgraphForkPass]: curr_vmrss: 662mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z INFO 293 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 17918 memory location(s), 2 block(s), and 59873 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 [SubgraphForkPass]: Compilation status: Total subgraphs: 1, Passed: 1, Failed: 0 2025-11-09T20:55:04Z USER 293 [BackendPassManager]: subgraph_parallel_pass finished after 0.161 seconds 2025-11-09T20:55:04Z INFO 293 [BackendPassManager]: curr_vmrss: 662mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z USER 293 [BackendPassManager]: Running mod_parallel_pass 2025-11-09T20:55:04Z INFO 293 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=59873 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 (nc00/sg00) [ModuleForkPass]: Running coloring_allocator_dram_shared 2025-11-09T20:55:04Z USER 293 (nc01/sg00) [ModuleForkPass]: Running coloring_allocator_dram_shared 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to coloring_allocator_dram_shared: modules=1 functions=1 allocs=9361 blocks=1 instructions=30832 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: Allocating functions 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: linearize and check 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to coloring_allocator_dram_shared: modules=1 functions=1 allocs=8557 blocks=1 instructions=29041 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: Allocating functions 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: linearize and check 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Shared 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: reserved space = 251688 bytes 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: spill space = 2745858 bytes 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: aligned spill space = 2809856 bytes 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: dram space = 107374182400 bytes 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: renumber locations 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: size = 187 2025-11-09T20:55:04Z INFO 293 []: find first defs for local 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [DRAM_Allocator]: allocating spills in DRAM pre_link mode for address space Shared 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [DRAM_Allocator]: reserved space = 231184 bytes 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [DRAM_Allocator]: spill space = 2745858 bytes 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [DRAM_Allocator]: aligned spill space = 2809856 bytes 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [DRAM_Allocator]: dram space = 107374182400 bytes 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [DRAM_Allocator]: Skipping shared tensor allocations on core 1, marking as remoteLocalTarget instead 2025-11-09T20:55:04Z USER 293 (nc01/sg00) [ModuleForkPass]: coloring_allocator_dram_shared finished after 0.063 seconds 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 665mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29041 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:04Z INFO 293 []: find first defs for global 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: Num intervals 187 Num locations 187 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: IntervalTree Build Done 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: info.neighbors init Done 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: IntervalTree readback Done 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: simplify interference graph 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: initialize low and high 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: lo = 187 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: hi = 0 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: total = 187 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: simplify 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: new candidates = 0 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: Already used DRAM hwm: 73728 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: Fall back to default allocation strategy [Core0 Local, Shared] 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: Already used DRAM hwm: 73728 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: select ranges 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: CC buffer size limit 524288000 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: allreduce_dram_hwm 1970176 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: Real CC buffer size 1970176 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: DRAM hwm after allocation: 2592768 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [DRAM_Allocator]: DRAM allocation successful 2025-11-09T20:55:04Z USER 293 (nc00/sg00) [ModuleForkPass]: coloring_allocator_dram_shared finished after 0.131 seconds 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 665mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30832 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:55:04Z USER 293 [BackendPassManager]: mod_parallel_pass finished after 0.134 seconds 2025-11-09T20:55:04Z INFO 293 [BackendPassManager]: curr_vmrss: 665mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z USER 293 [BackendPassManager]: Running subgraph_parallel_pass 2025-11-09T20:55:04Z INFO 293 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=59873 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 (sg00) [SubgraphForkPass]: Running sync_shared_allocations 2025-11-09T20:55:04Z INFO 293 (sg00) [SubgraphForkPass]: Inputs to sync_shared_allocations: modules=2 functions=2 allocs=17918 blocks=2 instructions=59873 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 (sg00) [SubgraphForkPass]: sync_shared_allocations finished after 0.006 seconds 2025-11-09T20:55:04Z INFO 293 (sg00) [SubgraphForkPass]: curr_vmrss: 665mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z INFO 293 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 17918 memory location(s), 2 block(s), and 59873 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 [SubgraphForkPass]: Compilation status: Total subgraphs: 1, Passed: 1, Failed: 0 2025-11-09T20:55:04Z USER 293 [BackendPassManager]: subgraph_parallel_pass finished after 0.009 seconds 2025-11-09T20:55:04Z INFO 293 [BackendPassManager]: curr_vmrss: 665mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z USER 293 [BackendPassManager]: Running mod_parallel_pass 2025-11-09T20:55:04Z INFO 293 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=59873 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 (nc00/sg00) [ModuleForkPass]: Running anti_dependency_analyzer_post_shared_dram 2025-11-09T20:55:04Z USER 293 (nc01/sg00) [ModuleForkPass]: Running anti_dependency_analyzer_post_shared_dram 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer_post_shared_dram: modules=1 functions=1 allocs=8557 blocks=1 instructions=29041 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM} 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer_post_shared_dram: modules=1 functions=1 allocs=9361 blocks=1 instructions=30832 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM} 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824 2025-11-09T20:55:04Z USER 293 (nc00/sg00) [ModuleForkPass]: anti_dependency_analyzer_post_shared_dram finished after 0.060 seconds 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 665mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30832 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 (nc01/sg00) [ModuleForkPass]: anti_dependency_analyzer_post_shared_dram finished after 0.070 seconds 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 665mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29041 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:04Z USER 293 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:55:04Z USER 293 [BackendPassManager]: mod_parallel_pass finished after 0.072 seconds 2025-11-09T20:55:04Z INFO 293 [BackendPassManager]: curr_vmrss: 665mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z USER 293 [BackendPassManager]: Running nc_parallel_pass 2025-11-09T20:55:04Z INFO 293 [BackendPassManager]: Inputs to nc_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=59873 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 (nc01) [CoreForkPass]: Running memory_analysis_after_coloring_allocator_dram_shared 2025-11-09T20:55:04Z USER 293 (nc00) [CoreForkPass]: Running memory_analysis_after_coloring_allocator_dram_shared 2025-11-09T20:55:04Z INFO 293 (nc00) [CoreForkPass]: Inputs to memory_analysis_after_coloring_allocator_dram_shared: modules=1 functions=1 allocs=9361 blocks=1 instructions=30832 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z INFO 293 (nc01) [CoreForkPass]: Inputs to memory_analysis_after_coloring_allocator_dram_shared: modules=1 functions=1 allocs=8557 blocks=1 instructions=29041 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:04Z USER 293 (nc01) [CoreForkPass]: memory_analysis_after_coloring_allocator_dram_shared finished after 0.144 seconds 2025-11-09T20:55:04Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 666mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29041 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:04Z USER 293 (nc00) [CoreForkPass]: memory_analysis_after_coloring_allocator_dram_shared finished after 0.154 seconds 2025-11-09T20:55:04Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 666mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30832 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 [CoreForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:55:04Z USER 293 [BackendPassManager]: nc_parallel_pass finished after 0.158 seconds 2025-11-09T20:55:04Z INFO 293 [BackendPassManager]: curr_vmrss: 666mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z USER 293 [BackendPassManager]: Running mod_parallel_pass 2025-11-09T20:55:04Z INFO 293 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=59873 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 (nc00/sg00) [ModuleForkPass]: Running prefetch_scheduling_before_sched 2025-11-09T20:55:04Z USER 293 (nc01/sg00) [ModuleForkPass]: Running prefetch_scheduling_before_sched 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to prefetch_scheduling_before_sched: modules=1 functions=1 allocs=9361 blocks=1 instructions=30832 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 (nc00/sg00) [ModuleForkPass]: prefetch_scheduling_before_sched finished after 0.001 seconds 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 666mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to prefetch_scheduling_before_sched: modules=1 functions=1 allocs=8557 blocks=1 instructions=29041 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:04Z USER 293 (nc01/sg00) [ModuleForkPass]: prefetch_scheduling_before_sched finished after 0.001 seconds 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 666mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30832 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z USER 293 (nc00/sg00) [ModuleForkPass]: Running post_sched 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29041 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:04Z USER 293 (nc01/sg00) [ModuleForkPass]: Running post_sched 2025-11-09T20:55:04Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to post_sched: modules=1 functions=1 allocs=9361 blocks=1 instructions=30832 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:04Z INFO 293 [PostSched]: Detected modules.size() == 1; running LNC=1 post_sched 2025-11-09T20:55:04Z INFO 293 [PostSched]: Detected --lnc_aware_scheduler=false; running LNC=1 post_sched 2025-11-09T20:55:04Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to post_sched: modules=1 functions=1 allocs=8557 blocks=1 instructions=29041 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:04Z INFO 293 [PostSched]: Detected modules.size() == 1; running LNC=1 post_sched 2025-11-09T20:55:04Z INFO 293 [PostSched]: Detected --lnc_aware_scheduler=false; running LNC=1 post_sched 2025-11-09T20:55:04Z INFO 293 [post_scheduler]: Start PosT ScheD 3 gen3 Sun Nov 9 20:55:04 2025 2025-11-09T20:55:04Z INFO 293 [post_scheduler]: Start PosT ScheD 3 gen3 Sun Nov 9 20:55:04 2025 2025-11-09T20:55:04Z INFO 293 [post_scheduler]: Time-aware hwm post-sched 2025-11-09T20:55:04Z INFO 293 [post_scheduler]: Time-aware hwm post-sched 2025-11-09T20:55:05Z INFO 293 [post_scheduler]: Time-aware simulation time: 3184997 2025-11-09T20:55:05Z INFO 293 [post_scheduler]: Time-aware simulation time: 3565736 2025-11-09T20:55:05Z INFO 293 [post_scheduler]: Done PosT ScheD Sun Nov 9 20:55:05 2025 2025-11-09T20:55:05Z USER 293 (nc01/sg00) [ModuleForkPass]: post_sched finished after 1.543 seconds 2025-11-09T20:55:05Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 740mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:05Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29041 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:05Z USER 293 (nc01/sg00) [ModuleForkPass]: Running expand_scheduling_units 2025-11-09T20:55:05Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to expand_scheduling_units: modules=1 functions=1 allocs=8557 blocks=1 instructions=29041 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:05Z USER 293 (nc01/sg00) [ModuleForkPass]: expand_scheduling_units finished after 0.008 seconds 2025-11-09T20:55:05Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 655mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:05Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29041 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:05Z USER 293 (nc01/sg00) [ModuleForkPass]: Running dead_code_elim_o0 2025-11-09T20:55:05Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=8557 blocks=1 instructions=29041 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:05Z INFO 293 [post_scheduler]: Done PosT ScheD Sun Nov 9 20:55:05 2025 2025-11-09T20:55:05Z USER 293 (nc00/sg00) [ModuleForkPass]: post_sched finished after 1.580 seconds 2025-11-09T20:55:05Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 655mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:05Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30832 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:05Z USER 293 (nc00/sg00) [ModuleForkPass]: Running expand_scheduling_units 2025-11-09T20:55:05Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to expand_scheduling_units: modules=1 functions=1 allocs=9361 blocks=1 instructions=30832 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:05Z USER 293 (nc00/sg00) [ModuleForkPass]: expand_scheduling_units finished after 0.009 seconds 2025-11-09T20:55:05Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 655mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:05Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30832 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:05Z USER 293 (nc00/sg00) [ModuleForkPass]: Running dead_code_elim_o0 2025-11-09T20:55:05Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to dead_code_elim_o0: modules=1 functions=1 allocs=9361 blocks=1 instructions=30832 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:06Z USER 293 (nc01/sg00) [ModuleForkPass]: dead_code_elim_o0 finished after 0.089 seconds 2025-11-09T20:55:06Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 655mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:06Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29013 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:06Z USER 293 (nc00/sg00) [ModuleForkPass]: dead_code_elim_o0 finished after 0.081 seconds 2025-11-09T20:55:06Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 655mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:06Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30832 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:06Z USER 293 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:55:06Z USER 293 [BackendPassManager]: mod_parallel_pass finished after 1.682 seconds 2025-11-09T20:55:06Z INFO 293 [BackendPassManager]: curr_vmrss: 655mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:06Z USER 293 [BackendPassManager]: Running subgraph_parallel_pass 2025-11-09T20:55:06Z INFO 293 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=59845 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:06Z USER 293 (sg00) [SubgraphForkPass]: Running localize_shared_memory 2025-11-09T20:55:06Z INFO 293 (sg00) [SubgraphForkPass]: Inputs to localize_shared_memory: modules=2 functions=2 allocs=17918 blocks=2 instructions=59845 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:06Z USER 293 (sg00) [SubgraphForkPass]: localize_shared_memory finished after 0.007 seconds 2025-11-09T20:55:06Z INFO 293 (sg00) [SubgraphForkPass]: curr_vmrss: 655mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:06Z INFO 293 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 17918 memory location(s), 2 block(s), and 59845 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:06Z USER 293 [SubgraphForkPass]: Compilation status: Total subgraphs: 1, Passed: 1, Failed: 0 2025-11-09T20:55:06Z USER 293 [BackendPassManager]: subgraph_parallel_pass finished after 0.009 seconds 2025-11-09T20:55:06Z INFO 293 [BackendPassManager]: curr_vmrss: 655mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:06Z USER 293 [BackendPassManager]: Running mod_parallel_pass 2025-11-09T20:55:06Z INFO 293 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=59845 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:06Z USER 293 (nc00/sg00) [ModuleForkPass]: Running address_rotation_sb 2025-11-09T20:55:06Z USER 293 (nc01/sg00) [ModuleForkPass]: Running address_rotation_sb 2025-11-09T20:55:06Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=9361 blocks=1 instructions=30832 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:06Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to address_rotation_sb: modules=1 functions=1 allocs=8557 blocks=1 instructions=29013 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:06Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 1291 PSUM Banks 2025-11-09T20:55:06Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 1507 PSUM Banks 2025-11-09T20:55:06Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 225 PSUM Banks 2025-11-09T20:55:06Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 237 PSUM Banks 2025-11-09T20:55:06Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 1478 PSUM Banks 2025-11-09T20:55:06Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: PSUM Rotation rotated 1694 PSUM Banks 2025-11-09T20:55:06Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 58 Sb address 2025-11-09T20:55:06Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 82 Sb address 2025-11-09T20:55:07Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 114 Sb address 2025-11-09T20:55:07Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 75 Sb address 2025-11-09T20:55:07Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 117 Sb address 2025-11-09T20:55:07Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 229 Sb address 2025-11-09T20:55:07Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 54 Sb address 2025-11-09T20:55:07Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 54 Sb address 2025-11-09T20:55:07Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 730 Sb address 2025-11-09T20:55:07Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: moved 12 MM forward 2025-11-09T20:55:07Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 16 Sb address 2025-11-09T20:55:07Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 753 Sb address 2025-11-09T20:55:07Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: moved 9 MM forward 2025-11-09T20:55:07Z INFO 293 (nc01/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address 2025-11-09T20:55:07Z USER 293 (nc01/sg00) [ModuleForkPass]: address_rotation_sb finished after 1.421 seconds 2025-11-09T20:55:07Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 658mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:07Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29013 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:07Z USER 293 (nc01/sg00) [ModuleForkPass]: Running anti_dependency_analyzer 2025-11-09T20:55:07Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=8557 blocks=1 instructions=29013 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:07Z INFO 293 (nc01/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB} 2025-11-09T20:55:07Z INFO 293 (nc01/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824 2025-11-09T20:55:07Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 1 Sb address 2025-11-09T20:55:08Z INFO 293 (nc00/sg00) [DMAOptimizationBase]: SB Rotation rotated 0 Sb address 2025-11-09T20:55:08Z USER 293 (nc00/sg00) [ModuleForkPass]: address_rotation_sb finished after 1.965 seconds 2025-11-09T20:55:08Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 692mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:08Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30832 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:08Z USER 293 (nc00/sg00) [ModuleForkPass]: Running anti_dependency_analyzer 2025-11-09T20:55:08Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=9361 blocks=1 instructions=30832 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:08Z INFO 293 (nc00/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS,PSUM,SB} 2025-11-09T20:55:08Z INFO 293 (nc00/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824 2025-11-09T20:55:08Z USER 293 (nc01/sg00) [ModuleForkPass]: anti_dependency_analyzer finished after 1.028 seconds 2025-11-09T20:55:08Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 705mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:08Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29013 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:08Z USER 293 (nc01/sg00) [ModuleForkPass]: Running anti_dependency_analyzer 2025-11-09T20:55:08Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=8557 blocks=1 instructions=29013 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:08Z INFO 293 (nc01/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS} 2025-11-09T20:55:08Z INFO 293 (nc01/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824 2025-11-09T20:55:09Z USER 293 (nc01/sg00) [ModuleForkPass]: anti_dependency_analyzer finished after 0.499 seconds 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 711mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29013 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:09Z USER 293 (nc01/sg00) [ModuleForkPass]: Running dep_opt 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to dep_opt: modules=1 functions=1 allocs=8557 blocks=1 instructions=29013 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [build_flow_deps]: Start build fdeps. Invocation: 5Sun Nov 9 20:55:09 2025 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [build_flow_deps]: Allocs: 8557 instructions: 29013 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [build_flow_deps]: Build fdeps inserted 73361 edges 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [build_flow_deps]: Done build fdeps 73361 Sun Nov 9 20:55:09 2025 2025-11-09T20:55:09Z USER 293 (nc00/sg00) [ModuleForkPass]: anti_dependency_analyzer finished after 1.837 seconds 2025-11-09T20:55:09Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 715mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:09Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30832 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:09Z USER 293 (nc00/sg00) [ModuleForkPass]: Running anti_dependency_analyzer 2025-11-09T20:55:09Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to anti_dependency_analyzer: modules=1 functions=1 allocs=9361 blocks=1 instructions=30832 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:09Z INFO 293 (nc00/sg00) [AntiDependencyAnalyzer]: Analysis types: {DRAM,ALIAS} 2025-11-09T20:55:09Z INFO 293 (nc00/sg00) [AntiDependencyAnalyzer]: DRAM size: 25769803776 num-bins: 24 bin-size: 1073741824 2025-11-09T20:55:09Z USER 293 (nc01/sg00) [ModuleForkPass]: dep_opt finished after 0.903 seconds 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 715mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29013 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:09Z USER 293 (nc01/sg00) [ModuleForkPass]: Running report_stats 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to report_stats: modules=1 functions=1 allocs=8557 blocks=1 instructions=29013 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ReportStats]: Data Movement Statistics: sg0000 ┌──────────────┬────────────────────────────┬───────┬───────────┐ │ Instruction │ Kind │ Count │ Bytes │ ├──────────────┼────────────────────────────┼───────┼───────────┤ │ DMACopy │ ExternalInput -> Internal │ 1 │ 155582464 │ │ DMACopy │ Internal │ 144 │ 65536 │ │ DMACopy │ Internal -> ExternalOutput │ 56 │ 234881024 │ │ Load │ Const -> Internal │ 4 │ 99584 │ │ Load │ ExternalInput -> Internal │ 910 │ 441372720 │ │ Load │ Internal │ 121 │ 1076758 │ │ Load (Spill) │ Internal │ 10 │ 10233856 │ │ Save │ Internal │ 187 │ 608528 │ └──────────────┴────────────────────────────┴───────┴───────────┘ 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ReportStats]: ┌─────────────────────┬───────┐ │ Bytes per partition │ Count │ ├─────────────────────┼───────┤ │ 2 │ 1 │ │ 4 │ 68 │ │ 8 │ 5 │ │ 16 │ 32 │ │ 32 │ 85 │ │ 128 │ 224 │ │ 192 │ 1 │ │ 256 │ 1 │ │ 512 │ 154 │ │ 1024 │ 3 │ │ 2048 │ 56 │ │ 4096 │ 261 │ │ 6144 │ 112 │ │ 7176 │ 2 │ │ 8192 │ 224 │ │ 8200 │ 8 │ │ 524288 │ 56 │ └─────────────────────┴───────┘ 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ReportStats]: MM Stats: #MatMults 20622 #MatMult-Transposes 4222 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ReportStats]: IO Tensor size combined: 1485820000 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ReportStats]: IO Tensor Statistics: ┌────────────────────┬───────────────┬──────────┬──────────────┐ │ Largest IO Tensors │ Kind │ Src Type │ Size (Bytes) │ ├────────────────────┼───────────────┼──────────┼──────────────┤ │ input369 │ ExternalInput │ bfloat16 │ 155582464 │ │ input60 │ ExternalInput │ bfloat16 │ 155582464 │ │ input79 │ ExternalInput │ bfloat16 │ 6291456 │ │ input90 │ ExternalInput │ bfloat16 │ 6291456 │ │ input71 │ ExternalInput │ bfloat16 │ 6291456 │ │ input80 │ ExternalInput │ bfloat16 │ 6291456 │ │ input82 │ ExternalInput │ bfloat16 │ 6291456 │ │ input93 │ ExternalInput │ bfloat16 │ 6291456 │ │ input91 │ ExternalInput │ bfloat16 │ 6291456 │ │ input69 │ ExternalInput │ bfloat16 │ 6291456 │ └────────────────────┴───────────────┴──────────┴──────────────┘ 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ReportStats]: Large (Internal) Tensor Statistics: ┌─────────────────────────────────┬──────────┬──────────┬──────────────┐ │ Largest Tensors │ Kind │ Src Type │ Size (Bytes) │ ├─────────────────────────────────┼──────────┼──────────┼──────────────┤ │ DynamicDMAScratchLoc │ Internal │ uint8 │ 2097152 │ │ all_gather.1_nostride_48519_i1 │ Internal │ bfloat16 │ 1837056 │ │ all_gather.1_nostride_48639_i11 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i14 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i10 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i12 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i13 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i15 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i9 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i8 │ Internal │ bfloat16 │ 1049600 │ └─────────────────────────────────┴──────────┴──────────┴──────────────┘ 2025-11-09T20:55:09Z USER 293 (nc01/sg00) [ModuleForkPass]: report_stats finished after 0.028 seconds 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 715mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:09Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29013 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: anti_dependency_analyzer finished after 0.146 seconds 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30832 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: Running dep_opt 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to dep_opt: modules=1 functions=1 allocs=9361 blocks=1 instructions=30832 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [build_flow_deps]: Start build fdeps. Invocation: 6Sun Nov 9 20:55:10 2025 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [build_flow_deps]: Allocs: 9361 instructions: 30832 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [build_flow_deps]: Build fdeps inserted 87571 edges 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [build_flow_deps]: Done build fdeps 87571 Sun Nov 9 20:55:10 2025 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: dep_opt finished after 0.241 seconds 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30832 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: Running report_stats 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to report_stats: modules=1 functions=1 allocs=9361 blocks=1 instructions=30832 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ReportStats]: Data Movement Statistics: sg0000 ┌──────────────┬────────────────────────────┬───────┬───────────┐ │ Instruction │ Kind │ Count │ Bytes │ ├──────────────┼────────────────────────────┼───────┼───────────┤ │ DMACopy │ ExternalInput -> Internal │ 1 │ 155582464 │ │ DMACopy │ Internal │ 173 │ 69632 │ │ DMACopy │ Internal -> ExternalOutput │ 112 │ 469762048 │ │ Load │ Const -> Internal │ 10 │ 857864 │ │ Load │ ExternalInput -> Internal │ 910 │ 441372720 │ │ Load │ Internal │ 136 │ 1774630 │ │ Load (Spill) │ ExternalInput -> Internal │ 3 │ 120 │ │ Load (Spill) │ Internal │ 10 │ 10233856 │ │ Save │ Internal │ 344 │ 1321254 │ │ Save │ Internal -> ExternalOutput │ 1 │ 16 │ └──────────────┴────────────────────────────┴───────┴───────────┘ 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ReportStats]: ┌─────────────────────┬───────┐ │ Bytes per partition │ Count │ ├─────────────────────┼───────┤ │ 2 │ 2 │ │ 4 │ 74 │ │ 8 │ 6 │ │ 16 │ 87 │ │ 32 │ 146 │ │ 40 │ 3 │ │ 128 │ 228 │ │ 192 │ 1 │ │ 256 │ 1 │ │ 512 │ 156 │ │ 1024 │ 20 │ │ 2048 │ 56 │ │ 4096 │ 290 │ │ 4748 │ 2 │ │ 6144 │ 112 │ │ 7176 │ 2 │ │ 8192 │ 224 │ │ 8200 │ 8 │ │ 16384 │ 2 │ │ 524288 │ 112 │ └─────────────────────┴───────┘ 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ReportStats]: MM Stats: #MatMults 21258 #MatMult-Transposes 4734 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ReportStats]: IO Tensor size combined: 1485820000 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ReportStats]: IO Tensor Statistics: ┌────────────────────┬───────────────┬──────────┬──────────────┐ │ Largest IO Tensors │ Kind │ Src Type │ Size (Bytes) │ ├────────────────────┼───────────────┼──────────┼──────────────┤ │ input369 │ ExternalInput │ bfloat16 │ 155582464 │ │ input60 │ ExternalInput │ bfloat16 │ 155582464 │ │ input79 │ ExternalInput │ bfloat16 │ 6291456 │ │ input90 │ ExternalInput │ bfloat16 │ 6291456 │ │ input71 │ ExternalInput │ bfloat16 │ 6291456 │ │ input80 │ ExternalInput │ bfloat16 │ 6291456 │ │ input82 │ ExternalInput │ bfloat16 │ 6291456 │ │ input93 │ ExternalInput │ bfloat16 │ 6291456 │ │ input91 │ ExternalInput │ bfloat16 │ 6291456 │ │ input69 │ ExternalInput │ bfloat16 │ 6291456 │ └────────────────────┴───────────────┴──────────┴──────────────┘ 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ReportStats]: Large (Internal) Tensor Statistics: ┌────────────────────────────────┬──────────┬──────────┬──────────────┐ │ Largest Tensors │ Kind │ Src Type │ Size (Bytes) │ ├────────────────────────────────┼──────────┼──────────┼──────────────┤ │ DynamicDMAScratchLoc │ Internal │ uint8 │ 2097152 │ │ all_gather.1_nostride_48519_i0 │ Internal │ bfloat16 │ 1837056 │ │ all_gather.1_nostride_48639_i3 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i6 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i2 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i4 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i5 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i7 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i1 │ Internal │ bfloat16 │ 1049600 │ │ all_gather.1_nostride_48639_i0 │ Internal │ bfloat16 │ 1049600 │ └────────────────────────────────┴──────────┴──────────┴──────────────┘ 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: report_stats finished after 0.011 seconds 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30832 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: mod_parallel_pass finished after 4.226 seconds 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: Running assign_trigger_engine 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: Inputs to assign_trigger_engine: modules=2 functions=2 allocs=17918 blocks=2 instructions=59845 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [AssignTriggerEngine]: Assigned trigger engine for 413 DMA instructions. Moved 69 DMA instructions to CC's engines. 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [AssignTriggerEngine]: Assigned trigger engine for 254 DMA instructions. Moved 67 DMA instructions to CC's engines. 2025-11-09T20:55:10Z INFO 293 [AssignTriggerEngine]: Limiting IO queue to SP only 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: assign_trigger_engine finished after 0.039 seconds 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: Output has 2 module(s), 2 function(s), 17918 memory location(s), 2 block(s), and 59845 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: Running mod_parallel_pass 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=59845 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: Running sync_before_global_cc 2025-11-09T20:55:10Z USER 293 (nc01/sg00) [ModuleForkPass]: Running sync_before_global_cc 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to sync_before_global_cc: modules=1 functions=1 allocs=9361 blocks=1 instructions=30832 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to sync_before_global_cc: modules=1 functions=1 allocs=8557 blocks=1 instructions=29013 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: sync_before_global_cc finished after 0.011 seconds 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z USER 293 (nc01/sg00) [ModuleForkPass]: sync_before_global_cc finished after 0.012 seconds 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30891 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29072 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z USER 293 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: mod_parallel_pass finished after 0.014 seconds 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: Running assign_hwdge_engine 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: Inputs to assign_hwdge_engine: modules=2 functions=2 allocs=17918 blocks=2 instructions=59963 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: assign_hwdge_engine finished after 0.010 seconds 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: Output has 2 module(s), 2 function(s), 17918 memory location(s), 2 block(s), and 59963 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: Running mod_parallel_pass 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=59963 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: Running alloc_queues 2025-11-09T20:55:10Z USER 293 (nc01/sg00) [ModuleForkPass]: Running alloc_queues 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to alloc_queues: modules=1 functions=1 allocs=9361 blocks=1 instructions=30891 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to alloc_queues: modules=1 functions=1 allocs=8557 blocks=1 instructions=29072 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [AllocQueues]: Alloc Queue info: ┌───────────────────┬────────────────┬────────────┬────────────┬──────────────────┐ │ Name │ DMAQueue::Type │ Engine │ Num Queues │ Num instructions │ ├───────────────────┼────────────────┼────────────┼────────────┼──────────────────┤ │ qSPIO0 │ input │ SP │ 16 │ 4 │ │ qSPSpillReload0 │ data │ SP │ 16 │ 63 │ │ qPoolSpillReload0 │ data │ Pool │ 16 │ 198 │ │ qActSpillReload0 │ data │ Activation │ 16 │ 120 │ │ qDVESpillReload0 │ data │ DVE │ 16 │ 59 │ │ qSPDynamicHW │ dynamic │ SP │ 16 │ 18 │ │ qPoolDynamic │ dynamic │ Pool │ 16 │ 967 │ │ qActDynamicHW │ dynamic │ Activation │ 16 │ 4 │ └───────────────────┴────────────────┴────────────┴────────────┴──────────────────┘ 2025-11-09T20:55:10Z USER 293 (nc01/sg00) [ModuleForkPass]: alloc_queues finished after 0.007 seconds 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [AllocQueues]: Alloc Queue info: ┌───────────────────┬────────────────┬────────────┬────────────┬──────────────────┐ │ Name │ DMAQueue::Type │ Engine │ Num Queues │ Num instructions │ ├───────────────────┼────────────────┼────────────┼────────────┼──────────────────┤ │ qSPIO0 │ input │ SP │ 16 │ 8 │ │ qSPSpillReload0 │ data │ SP │ 16 │ 75 │ │ qPoolSpillReload0 │ data │ Pool │ 16 │ 229 │ │ qActSpillReload0 │ data │ Activation │ 16 │ 204 │ │ qDVESpillReload0 │ data │ DVE │ 16 │ 124 │ │ qSPDynamicHW │ dynamic │ SP │ 16 │ 29 │ │ qPoolDynamic │ dynamic │ Pool │ 16 │ 1024 │ │ qActDynamicHW │ dynamic │ Activation │ 16 │ 7 │ └───────────────────┴────────────────┴────────────┴────────────┴──────────────────┘ 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: alloc_queues finished after 0.007 seconds 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29072 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z USER 293 (nc01/sg00) [ModuleForkPass]: Running chain_dma_transposes 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30891 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: Running chain_dma_transposes 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to chain_dma_transposes: modules=1 functions=1 allocs=8557 blocks=1 instructions=29072 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to chain_dma_transposes: modules=1 functions=1 allocs=9361 blocks=1 instructions=30891 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 (nc01/sg00) [ModuleForkPass]: chain_dma_transposes finished after 0.010 seconds 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: chain_dma_transposes finished after 0.010 seconds 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30891 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29072 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z USER 293 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: mod_parallel_pass finished after 0.020 seconds 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: Running nc_parallel_pass 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: Inputs to nc_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=59963 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 (nc00) [CoreForkPass]: Running insert_dma_switch_queue_instance 2025-11-09T20:55:10Z USER 293 (nc01) [CoreForkPass]: Running insert_dma_switch_queue_instance 2025-11-09T20:55:10Z INFO 293 (nc00) [CoreForkPass]: Inputs to insert_dma_switch_queue_instance: modules=1 functions=1 allocs=9361 blocks=1 instructions=30891 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 (nc00) [CoreForkPass]: insert_dma_switch_queue_instance finished after 0.001 seconds 2025-11-09T20:55:10Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc01) [CoreForkPass]: Inputs to insert_dma_switch_queue_instance: modules=1 functions=1 allocs=8557 blocks=1 instructions=29072 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z USER 293 (nc01) [CoreForkPass]: insert_dma_switch_queue_instance finished after 0.001 seconds 2025-11-09T20:55:10Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30891 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29072 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z USER 293 [CoreForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: nc_parallel_pass finished after 0.002 seconds 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: Running mod_parallel_pass 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=59963 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: Running prefetch_scheduling_after_sched 2025-11-09T20:55:10Z USER 293 (nc01/sg00) [ModuleForkPass]: Running prefetch_scheduling_after_sched 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to prefetch_scheduling_after_sched: modules=1 functions=1 allocs=8557 blocks=1 instructions=29072 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to prefetch_scheduling_after_sched: modules=1 functions=1 allocs=9361 blocks=1 instructions=30891 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 (nc01/sg00) [ModuleForkPass]: prefetch_scheduling_after_sched finished after 0.001 seconds 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: prefetch_scheduling_after_sched finished after 0.001 seconds 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29072 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30891 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: Running lower_control 2025-11-09T20:55:10Z USER 293 (nc01/sg00) [ModuleForkPass]: Running lower_control 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to lower_control: modules=1 functions=1 allocs=8557 blocks=1 instructions=29072 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to lower_control: modules=1 functions=1 allocs=9361 blocks=1 instructions=30891 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [LowerControl]: EraseInterBbDeps removed 0 inter-BB deps 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [LowerControl]: EraseInterBbDeps removed 0 inter-BB deps 2025-11-09T20:55:10Z USER 293 (nc00/sg00) [ModuleForkPass]: lower_control finished after 0.075 seconds 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30891 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 (nc01/sg00) [ModuleForkPass]: lower_control finished after 0.079 seconds 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29072 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z USER 293 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: mod_parallel_pass finished after 0.083 seconds 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: curr_vmrss: 716mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z USER 293 [BackendPassManager]: Running nc_parallel_pass 2025-11-09T20:55:10Z INFO 293 [BackendPassManager]: Inputs to nc_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=59963 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z USER 293 (nc01) [CoreForkPass]: Running dep_reduction 2025-11-09T20:55:10Z USER 293 (nc00) [CoreForkPass]: Running dep_reduction 2025-11-09T20:55:10Z INFO 293 (nc01) [CoreForkPass]: Inputs to dep_reduction: modules=1 functions=1 allocs=8557 blocks=1 instructions=29072 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [DepReduction]: Start Dependency Reduction 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [DepReduction]: Cacheing dependencies for debug info 2025-11-09T20:55:10Z INFO 293 (nc00) [CoreForkPass]: Inputs to dep_reduction: modules=1 functions=1 allocs=9361 blocks=1 instructions=30891 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [DepReduction]: Start Dependency Reduction 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [DepReduction]: Cacheing dependencies for debug info 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [DepReduction]: Processing async instrs... 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [DepReduction]: Processing secondary edges per engine... 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [DepReduction]: Processing async instrs... 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [DepReduction]: Processing secondary edges per engine... 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [DepReduction]: Processing secondary edges per engine, Done. Num edges removed 26049 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [DepReduction]: Processing secondary edges per engine, Done. Num edges removed 28805 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [DepReduction]: Processing redundant descendants, Done. Num edges removed 28171 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [DepReduction]: Processing async instrs, Done. Num edges removed 28171 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [DepReduction]: Processing redundant descendants, Done. Num edges removed 31751 2025-11-09T20:55:10Z INFO 293 (nc00/sg00) [DepReduction]: Processing async instrs, Done. Num edges removed 31751 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [DepReduction]: Num Async removed: 0 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [DepReduction]: Finished dependency reduction: 182403 removed, new total 9055 2025-11-09T20:55:10Z INFO 293 (nc01/sg00) [DepReduction]: Finished Dependency Reduction 2025-11-09T20:55:10Z USER 293 (nc01) [CoreForkPass]: dep_reduction finished after 0.474 seconds 2025-11-09T20:55:10Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 754mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29072 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z USER 293 (nc01) [CoreForkPass]: Running lower_dynamic_dma 2025-11-09T20:55:10Z INFO 293 (nc01) [CoreForkPass]: Inputs to lower_dynamic_dma: modules=1 functions=1 allocs=8557 blocks=1 instructions=29072 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z USER 293 (nc01) [CoreForkPass]: lower_dynamic_dma finished after 0.032 seconds 2025-11-09T20:55:10Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:10Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29072 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:10Z USER 293 (nc01) [CoreForkPass]: Running legalize_dynamic_dma 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Inputs to legalize_dynamic_dma: modules=1 functions=1 allocs=8557 blocks=1 instructions=29072 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [DepReduction]: Num Async removed: 0 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [DepReduction]: Finished dependency reduction: 201021 removed, new total 10380 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [DepReduction]: Finished Dependency Reduction 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: dep_reduction finished after 0.535 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30891 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: Running lower_dynamic_dma 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Inputs to lower_dynamic_dma: modules=1 functions=1 allocs=9361 blocks=1 instructions=30891 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [LegalizeDynamicDMA]: Legalize Dynamic DMA scanned 0 DGE instructions 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [LegalizeDynamicDMA]: After Legalize Dynamic DMA, 0 DGE instructions were scanned 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [LegalizeDynamicDMA]: ┌───────────┬───────────────────────────────┬────────────────────────────┐ │ Sub-Pass │ Illegal Instructions Detected │ New Instructions Generated │ ├───────────┼───────────────────────────────┼────────────────────────────┤ │ Peeling │ 0 │ 0 │ │ Unrolling │ 0 │ 0 │ │ Splitting │ 0 │ 0 │ └───────────┴───────────────────────────────┴────────────────────────────┘ 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: legalize_dynamic_dma finished after 0.031 seconds 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29072 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: Running optimize_queue_switch 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Inputs to optimize_queue_switch: modules=1 functions=1 allocs=8557 blocks=1 instructions=29072 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [OptimizeQueueSwitch]: Optimize queue switch has replaced 0 total SQI Instructions with RQI 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: optimize_queue_switch finished after 0.005 seconds 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29072 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: Running lower_dma 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Inputs to lower_dma: modules=1 functions=1 allocs=8557 blocks=1 instructions=29072 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: lower_dynamic_dma finished after 0.018 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30891 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: Running legalize_dynamic_dma 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Inputs to legalize_dynamic_dma: modules=1 functions=1 allocs=9361 blocks=1 instructions=30891 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [LegalizeDynamicDMA]: Legalize Dynamic DMA scanned 0 DGE instructions 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [LegalizeDynamicDMA]: After Legalize Dynamic DMA, 0 DGE instructions were scanned 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [LegalizeDynamicDMA]: ┌───────────┬───────────────────────────────┬────────────────────────────┐ │ Sub-Pass │ Illegal Instructions Detected │ New Instructions Generated │ ├───────────┼───────────────────────────────┼────────────────────────────┤ │ Peeling │ 0 │ 0 │ │ Unrolling │ 0 │ 0 │ │ Splitting │ 0 │ 0 │ └───────────┴───────────────────────────────┴────────────────────────────┘ 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: legalize_dynamic_dma finished after 0.029 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30891 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: Running optimize_queue_switch 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Inputs to optimize_queue_switch: modules=1 functions=1 allocs=9361 blocks=1 instructions=30891 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [OptimizeQueueSwitch]: Optimize queue switch has replaced 0 total SQI Instructions with RQI 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: optimize_queue_switch finished after 0.005 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30891 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: Running lower_dma 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Inputs to lower_dma: modules=1 functions=1 allocs=9361 blocks=1 instructions=30891 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [LowerDMA]: lower_dma metrics start IO Copy (DGE/DMA) 128 partition : 792/792 (100% DGE) power-of-2 partition : 792/796 (99.4975% DGE) > 3 dimensional : 0/0 non-integer desc size : 0/0 total : 793/797 (99.4981% DGE) Cast (DGE/DMA) 128 partition : 57/57 (100% DGE) power-of-2 partition : 113/113 (100% DGE) > 3 dimensional : 0/0 non-integer desc size : 0/0 total : 113/113 (100% DGE) Spill/Reload Copy (DGE/DMA) 128 partition : 22/22 (100% DGE) power-of-2 partition : 22/322 (6.8323% DGE) > 3 dimensional : 0/0 non-integer desc size : 0/0 total : 22/322 (6.8323% 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 : 140 Transpose : 0 Replicate : 0 Dynamic (DGE/DMA) scalar : 0/0 vector : 61/61 (100% DGE) Opcode ReadVarAddr : 0 IndirectLoad : 0 IndirectSave : 0 IndirectSaveAccumulate : 0 DstReduceDGE : 0 lower_dma metrics end 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: lower_dma finished after 0.071 seconds 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29073 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: Running expand_all_engine 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Inputs to expand_all_engine: modules=1 functions=1 allocs=8557 blocks=1 instructions=29073 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: expand_all_engine finished after 0.037 seconds 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29073 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: Running alloc_semaphores 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Inputs to alloc_semaphores: modules=1 functions=1 allocs=8557 blocks=1 instructions=29073 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [LowerDMA]: lower_dma metrics start IO Copy (DGE/DMA) 128 partition : 792/792 (100% DGE) power-of-2 partition : 792/800 (99% DGE) > 3 dimensional : 0/0 non-integer desc size : 0/0 total : 793/801 (99.0013% DGE) Cast (DGE/DMA) 128 partition : 57/57 (100% DGE) power-of-2 partition : 113/113 (100% DGE) > 3 dimensional : 0/0 non-integer desc size : 0/0 total : 113/113 (100% DGE) Spill/Reload Copy (DGE/DMA) 128 partition : 36/36 (100% DGE) power-of-2 partition : 36/498 (7.22892% DGE) > 3 dimensional : 0/0 non-integer desc size : 0/0 total : 36/498 (7.22892% 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 : 168 Transpose : 0 Replicate : 0 Dynamic (DGE/DMA) scalar : 0/0 vector : 118/118 (100% DGE) Opcode ReadVarAddr : 0 IndirectLoad : 0 IndirectSave : 0 IndirectSaveAccumulate : 0 DstReduceDGE : 0 lower_dma metrics end 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: lower_dma finished after 0.113 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30893 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: Running expand_all_engine 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Inputs to expand_all_engine: modules=1 functions=1 allocs=9361 blocks=1 instructions=30893 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: expand_all_engine finished after 0.033 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30893 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: Running alloc_semaphores 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Inputs to alloc_semaphores: modules=1 functions=1 allocs=9361 blocks=1 instructions=30893 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: alloc_semaphores finished after 0.099 seconds 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29073 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: Running expand_inst_late 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Inputs to expand_inst_late: modules=1 functions=1 allocs=8557 blocks=1 instructions=29073 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: alloc_semaphores finished after 0.078 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30893 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: Running expand_inst_late 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Inputs to expand_inst_late: modules=1 functions=1 allocs=9361 blocks=1 instructions=30893 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: expand_inst_late finished after 0.137 seconds 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29134 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: Running seq_inst_opt 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Inputs to seq_inst_opt: modules=1 functions=1 allocs=8557 blocks=1 instructions=29134 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [SeqInstOpt]: Removing 58 unnecessary InstRegisterMove instruction(s) from Block1 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: seq_inst_opt finished after 0.009 seconds 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 29076 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: Running lower_sync 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Inputs to lower_sync: modules=1 functions=1 allocs=8557 blocks=1 instructions=29076 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: lower_sync finished after 0.033 seconds 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 30488 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: Running lower_act 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Inputs to lower_act: modules=1 functions=1 allocs=8557 blocks=1 instructions=30488 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: lower_act finished after 0.024 seconds 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 30629 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: Running lower_dve 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Inputs to lower_dve: modules=1 functions=1 allocs=8557 blocks=1 instructions=30629 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [LowerDVE]: Loading DVE opcodes table dve_info.json from /opt/conda/lib/python3.11/site-packages/neuronxcc/dve/dve_bin_gen3/dve_info.json 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: expand_inst_late finished after 0.154 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 31011 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: Running seq_inst_opt 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Inputs to seq_inst_opt: modules=1 functions=1 allocs=9361 blocks=1 instructions=31011 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [SeqInstOpt]: Removing 115 unnecessary InstRegisterMove instruction(s) from Block1 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: seq_inst_opt finished after 0.015 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 706mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 30896 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: Running lower_sync 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Inputs to lower_sync: modules=1 functions=1 allocs=9361 blocks=1 instructions=30896 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: lower_sync finished after 0.040 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 707mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 32702 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: Running lower_act 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Inputs to lower_act: modules=1 functions=1 allocs=9361 blocks=1 instructions=32702 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: lower_act finished after 0.021 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 709mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 32844 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: Running lower_dve 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Inputs to lower_dve: modules=1 functions=1 allocs=9361 blocks=1 instructions=32844 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [LowerDVE]: Loading DVE opcodes table dve_info.json from /opt/conda/lib/python3.11/site-packages/neuronxcc/dve/dve_bin_gen3/dve_info.json 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: lower_dve finished after 0.198 seconds 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 714mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 30629 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: Running lower_ap 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Inputs to lower_ap: modules=1 functions=1 allocs=8557 blocks=1 instructions=30629 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: lower_ap finished after 0.030 seconds 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 714mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 30629 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: Running coloring_allocator_reg 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Inputs to coloring_allocator_reg: modules=1 functions=1 allocs=8557 blocks=1 instructions=30629 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: Allocating functions 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [ColoringAllocator::Rep]: linearize and check 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: allocating REG 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: main loop iteration 1 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: renumber registers 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: size = 3 2025-11-09T20:55:11Z INFO 293 []: find first defs for local reg 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: lower_dve finished after 0.190 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 714mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 32844 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: Running lower_ap 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Inputs to lower_ap: modules=1 functions=1 allocs=9361 blocks=1 instructions=32844 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z INFO 293 []: find first defs for global reg 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: lower_ap finished after 0.034 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 714mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 32844 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: Running coloring_allocator_reg 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Inputs to coloring_allocator_reg: modules=1 functions=1 allocs=9361 blocks=1 instructions=32844 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: Allocating functions 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [ColoringAllocator::Rep]: linearize and check 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: live range analysis 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: allocating REG 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: main loop iteration 1 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: find costs 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: renumber registers 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: size = 3 2025-11-09T20:55:11Z INFO 293 []: find first defs for local reg 2025-11-09T20:55:11Z INFO 293 []: find first defs for global reg 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: simplify interference graph 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: initialize low and high 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: lo = 3 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: hi = 0 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: inf = 0 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: total = 3 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: simplify 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: new candidates = 0 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: select ranges 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: no more spills 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: REG score = 0 (lower is better) 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: Spilling from REG cost about 0 cycles 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [REG_Allocator]: 0% REG utilization after allocation 2025-11-09T20:55:11Z USER 293 (nc01) [CoreForkPass]: coloring_allocator_reg finished after 0.171 seconds 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: curr_vmrss: 720mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc01) [CoreForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 30629 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: live range analysis 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: find costs 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: simplify interference graph 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: initialize low and high 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: lo = 3 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: hi = 0 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: inf = 0 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: total = 3 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: simplify 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: new candidates = 0 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: select ranges 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: no more spills 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: REG score = 0 (lower is better) 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: Spilling from REG cost about 0 cycles 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [REG_Allocator]: 0% REG utilization after allocation 2025-11-09T20:55:11Z USER 293 (nc00) [CoreForkPass]: coloring_allocator_reg finished after 0.164 seconds 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: curr_vmrss: 721mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 (nc00) [CoreForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 32844 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 [CoreForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:55:11Z USER 293 [BackendPassManager]: nc_parallel_pass finished after 1.495 seconds 2025-11-09T20:55:11Z INFO 293 [BackendPassManager]: curr_vmrss: 695mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z USER 293 [BackendPassManager]: Running vnc_remote_addr_map 2025-11-09T20:55:11Z INFO 293 [BackendPassManager]: Inputs to vnc_remote_addr_map: modules=2 functions=2 allocs=17918 blocks=2 instructions=63473 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 [BackendPassManager]: vnc_remote_addr_map finished after 0.009 seconds 2025-11-09T20:55:11Z INFO 293 [BackendPassManager]: curr_vmrss: 695mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 [BackendPassManager]: Output has 2 module(s), 2 function(s), 17918 memory location(s), 2 block(s), and 63473 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 [BackendPassManager]: Running vnc_link 2025-11-09T20:55:11Z INFO 293 [BackendPassManager]: Inputs to vnc_link: modules=2 functions=2 allocs=17918 blocks=2 instructions=63473 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z INFO 293 [VncLink]: Found 0 remote updates 2025-11-09T20:55:11Z USER 293 [BackendPassManager]: vnc_link finished after 0.002 seconds 2025-11-09T20:55:11Z INFO 293 [BackendPassManager]: curr_vmrss: 695mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:11Z INFO 293 [BackendPassManager]: Output has 2 module(s), 2 function(s), 17918 memory location(s), 2 block(s), and 63473 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 [BackendPassManager]: Running mod_parallel_pass 2025-11-09T20:55:11Z INFO 293 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=63473 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z USER 293 (nc00/sg00) [ModuleForkPass]: Running birverifier 2025-11-09T20:55:11Z USER 293 (nc01/sg00) [ModuleForkPass]: Running birverifier 2025-11-09T20:55:11Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=9361 blocks=1 instructions=32844 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:11Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to birverifier: modules=1 functions=1 allocs=8557 blocks=1 instructions=30629 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:12Z USER 293 (nc00/sg00) [ModuleForkPass]: birverifier finished after 0.373 seconds 2025-11-09T20:55:12Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 697mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:12Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 32844 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:12Z USER 293 (nc01/sg00) [ModuleForkPass]: birverifier finished after 0.479 seconds 2025-11-09T20:55:12Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 697mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:12Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 30629 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:12Z USER 293 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:55:12Z USER 293 [BackendPassManager]: mod_parallel_pass finished after 0.484 seconds 2025-11-09T20:55:12Z INFO 293 [BackendPassManager]: curr_vmrss: 697mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:12Z USER 293 [BackendPassManager]: Running subgraph_parallel_pass 2025-11-09T20:55:12Z INFO 293 [BackendPassManager]: Inputs to subgraph_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=63473 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:12Z USER 293 (sg00) [SubgraphForkPass]: Running lnc_verifier 2025-11-09T20:55:12Z INFO 293 (sg00) [SubgraphForkPass]: Inputs to lnc_verifier: modules=2 functions=2 allocs=17918 blocks=2 instructions=63473 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:12Z USER 293 (sg00) [SubgraphForkPass]: lnc_verifier finished after 0.029 seconds 2025-11-09T20:55:12Z INFO 293 (sg00) [SubgraphForkPass]: curr_vmrss: 697mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:12Z INFO 293 (sg00) [SubgraphForkPass]: Output has 2 module(s), 2 function(s), 17918 memory location(s), 2 block(s), and 63473 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:12Z USER 293 [SubgraphForkPass]: Compilation status: Total subgraphs: 1, Passed: 1, Failed: 0 2025-11-09T20:55:12Z USER 293 [BackendPassManager]: subgraph_parallel_pass finished after 0.034 seconds 2025-11-09T20:55:12Z INFO 293 [BackendPassManager]: curr_vmrss: 697mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:12Z USER 293 [BackendPassManager]: Running mod_parallel_pass 2025-11-09T20:55:12Z INFO 293 [BackendPassManager]: Inputs to mod_parallel_pass: modules=2 functions=2 allocs=17918 blocks=2 instructions=63473 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:12Z USER 293 (nc00/sg00) [ModuleForkPass]: Running codegen 2025-11-09T20:55:12Z USER 293 (nc01/sg00) [ModuleForkPass]: Running codegen 2025-11-09T20:55:12Z INFO 293 (nc00/sg00) [ModuleForkPass]: Inputs to codegen: modules=1 functions=1 allocs=9361 blocks=1 instructions=32844 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:12Z INFO 293 (nc01/sg00) [ModuleForkPass]: Inputs to codegen: modules=1 functions=1 allocs=8557 blocks=1 instructions=30629 Max writers: 151 Max Readers: 4215 2025-11-09T20:55:12Z INFO 293 (nc01/sg00) [Codegen]: Total un-allocated DRAM tensors by kind: 2025-11-09T20:55:12Z INFO 293 (nc00/sg00) [Codegen]: Total un-allocated DRAM tensors by kind: 2025-11-09T20:55:12Z INFO 293 (nc01/sg00) [Codegen]: ┌────────────────┬─────────────┐ │ TensorKind │ Size (GB) │ ├────────────────┼─────────────┤ │ ExternalInput │ 1.16503 │ │ ExternalOutput │ 1.49012e-08 │ │ Const │ 0.000795126 │ └────────────────┴─────────────┘ 2025-11-09T20:55:12Z INFO 293 (nc00/sg00) [Codegen]: ┌────────────────┬─────────────┐ │ TensorKind │ Size (GB) │ ├────────────────┼─────────────┤ │ ExternalInput │ 1.16503 │ │ ExternalOutput │ 1.49012e-08 │ │ Const │ 0.000798948 │ └────────────────┴─────────────┘ 2025-11-09T20:55:13Z INFO 293 (nc01/sg00) [Codegen]: Instruction Stats: 2025-11-09T20:55:13Z INFO 293 (nc01/sg00) [Codegen]: ┌─────────────────────┬───────┐ │ Opcode │ Count │ ├─────────────────────┼───────┤ │ MATMUL │ 21646 │ │ LDWEIGHTS │ 21646 │ │ ACTIVATE │ 1897 │ │ CAST │ 1843 │ │ EVENT_SEMAPHORE │ 1412 │ │ TENSOR_TENSOR │ 1081 │ │ UNKNOWN(0xd4) │ 989 │ │ UNKNOWN(0xd8) │ 637 │ │ COPY │ 500 │ │ PSEUDO_DMA_TRIGGER │ 444 │ │ TENSOR_SCALAR │ 254 │ │ MEMSET │ 227 │ │ TENSOR_SCALAR_ADDR │ 225 │ │ ACT_TABLE_LOAD │ 141 │ │ UNKNOWN(0xda) │ 120 │ │ IOTA │ 84 │ │ LOAD_MASK_SELECT │ 70 │ │ UNKNOWN(0xd9) │ 59 │ │ RECIPROCAL │ 56 │ │ STREAM_TRANSPOSE │ 56 │ │ TENSOR_REDUCE │ 56 │ │ UNKNOWN(0xe8) │ 28 │ │ STREAM_SHUFFLE │ 14 │ │ PSEUDO_BRANCH_LABEL │ 5 │ │ MOVE │ 3 │ └─────────────────────┴───────┘ 2025-11-09T20:55:13Z INFO 293 (nc01/sg00) [Codegen]: ┌────────────┬───────┐ │ Engine │ Count │ ├────────────┼───────┤ │ Unassigned │ 0 │ │ GPSIMD │ 3020 │ │ Scalar │ 4454 │ │ Tensor │ 43623 │ │ SyncDMA │ 0 │ │ Vector │ 2266 │ │ Sync │ 135 │ │ All │ 0 │ └────────────┴───────┘ 2025-11-09T20:55:13Z USER 293 (nc01/sg00) [Codegen]: isa_gen finished after 0.627 seconds 2025-11-09T20:55:13Z INFO 293 (nc01/sg00) [Codegen]: Number of DMA descriptors on each queue instance: ┌───────────────────┬────────────────┐ │ Queue Instance │ RT Descriptors │ ├───────────────────┼────────────────┤ │ qActSpillReload0 │ 1080 │ │ qDVESpillReload0 │ 472 │ │ qPoolSpillReload0 │ 32795 │ │ qSPIO0 │ 20 │ │ qSPSpillReload0 │ 86295 │ └───────────────────┴────────────────┘ Total descriptors: 120662 (0.001798 GB) 2025-11-09T20:55:13Z INFO 293 (nc01/sg00) [Codegen]: Number of DMA engines used by each queue: ┌───────────────────┬──────────────────────┐ │ Queue │ DMA Engines │ ├───────────────────┼──────────────────────┤ │ qSPIO0 │ 16 │ │ qSPDynamicHW │ 16 │ │ qPoolDynamic │ 16 │ │ qActDynamicHW │ 16 │ │ qSPSpillReload0 │ 16 │ │ qPoolSpillReload0 │ 16 │ │ qActSpillReload0 │ 16 │ │ qDVESpillReload0 │ 16 │ ├───────────────────┼──────────────────────┤ │ TOTAL │ 128 (must be <= 176) │ └───────────────────┴──────────────────────┘ 2025-11-09T20:55:13Z INFO 293 (nc01/sg00) [Codegen]: Tensors with largest descriptor count: ┌──────────────────────────┬───────────────┬──────────┬──────────────────┐ │ Tensor Name │ Kind │ Src Type │ Descriptor Count │ ├──────────────────────────┼───────────────┼──────────┼──────────────────┤ │ dot.186-buffer-65170 │ Internal │ bfloat16 │ 1 │ │ t31302_33513_i0_remote_0 │ Internal │ bfloat16 │ 1 │ │ 26800.44522_i266 │ Internal │ float32 │ 1 │ │ 26800.44522_i281 │ Internal │ float32 │ 1 │ │ t32633_34148_i0_remote_0 │ Internal │ bfloat16 │ 1 │ │ broadcast_in_dim.17_i1 │ Internal │ int32 │ 2 │ │ input2 │ ExternalInput │ int32 │ 2 │ │ split_1 │ Internal │ float32 │ 2 │ │ split_2 │ Internal │ int32 │ 2 │ │ convert.656 │ Internal │ float32 │ 149 │ └──────────────────────────┴───────────────┴──────────┴──────────────────┘ 2025-11-09T20:55:13Z INFO 293 (nc00/sg00) [Codegen]: Instruction Stats: 2025-11-09T20:55:13Z INFO 293 (nc00/sg00) [Codegen]: ┌─────────────────────┬───────┐ │ Opcode │ Count │ ├─────────────────────┼───────┤ │ MATMUL │ 22406 │ │ LDWEIGHTS │ 22406 │ │ ACTIVATE │ 1960 │ │ CAST │ 1843 │ │ EVENT_SEMAPHORE │ 1806 │ │ TENSOR_TENSOR │ 1085 │ │ UNKNOWN(0xd4) │ 1060 │ │ COPY │ 717 │ │ PSEUDO_DMA_TRIGGER │ 640 │ │ UNKNOWN(0xd8) │ 637 │ │ TENSOR_SCALAR_ADDR │ 338 │ │ TENSOR_SCALAR │ 261 │ │ MEMSET │ 239 │ │ POOL_BUFFER_LOAD │ 192 │ │ GATHER │ 192 │ │ UNKNOWN(0xda) │ 177 │ │ IOTA │ 170 │ │ ACT_TABLE_LOAD │ 142 │ │ DVE_READ_INDICES │ 128 │ │ MATCH_REPLACE8 │ 128 │ │ MATCH_VALUE_LOAD │ 128 │ │ MAX8 │ 128 │ │ LOAD_MASK_SELECT │ 83 │ │ TENSOR_REDUCE │ 64 │ │ UNKNOWN(0xd9) │ 59 │ │ RECIPROCAL │ 59 │ │ STREAM_TRANSPOSE │ 57 │ │ UNKNOWN(0xe8) │ 30 │ │ STREAM_SHUFFLE │ 26 │ │ PSEUDO_BRANCH_LABEL │ 5 │ │ MOVE │ 3 │ │ UNKNOWN(0xe5) │ 2 │ │ NOP │ 1 │ │ TENSOR_SCALAR │ 1 │ │ RNG │ 1 │ └─────────────────────┴───────┘ 2025-11-09T20:55:13Z INFO 293 (nc00/sg00) [Codegen]: ┌────────────┬───────┐ │ Engine │ Count │ ├────────────┼───────┤ │ Unassigned │ 0 │ │ GPSIMD │ 3963 │ │ Scalar │ 4811 │ │ Tensor │ 45147 │ │ SyncDMA │ 0 │ │ Vector │ 3077 │ │ Sync │ 181 │ │ All │ 0 │ └────────────┴───────┘ 2025-11-09T20:55:13Z USER 293 (nc01/sg00) [Codegen]: dma_desc_gen finished after 0.031 seconds 2025-11-09T20:55:13Z INFO 293 (nc01/sg00) [Codegen]: Generating debug info 2025-11-09T20:55:13Z USER 293 (nc00/sg00) [Codegen]: isa_gen finished after 0.660 seconds 2025-11-09T20:55:13Z INFO 293 (nc00/sg00) [Codegen]: Number of DMA descriptors on each queue instance: ┌───────────────────┬────────────────┐ │ Queue Instance │ RT Descriptors │ ├───────────────────┼────────────────┤ │ qActSpillReload0 │ 87188 │ │ qDVESpillReload0 │ 86548 │ │ qPoolSpillReload0 │ 43565 │ │ qSPIO0 │ 31 │ │ qSPSpillReload0 │ 86250 │ └───────────────────┴────────────────┘ Total descriptors: 303582 (0.00452372 GB) 2025-11-09T20:55:13Z INFO 293 (nc00/sg00) [Codegen]: Number of DMA engines used by each queue: ┌───────────────────┬──────────────────────┐ │ Queue │ DMA Engines │ ├───────────────────┼──────────────────────┤ │ qSPIO0 │ 16 │ │ qSPDynamicHW │ 16 │ │ qPoolDynamic │ 16 │ │ qActDynamicHW │ 16 │ │ qSPSpillReload0 │ 16 │ │ qPoolSpillReload0 │ 16 │ │ qActSpillReload0 │ 16 │ │ qDVESpillReload0 │ 16 │ ├───────────────────┼──────────────────────┤ │ TOTAL │ 128 (must be <= 176) │ └───────────────────┴──────────────────────┘ 2025-11-09T20:55:13Z INFO 293 (nc00/sg00) [Codegen]: Tensors with largest descriptor count: ┌─────────────────────┬──────────┬──────────┬──────────────────┐ │ Tensor Name │ Kind │ Src Type │ Descriptor Count │ ├─────────────────────┼──────────┼──────────┼──────────────────┤ │ concatenate.18 │ Internal │ bfloat16 │ 3 │ │ concatenate.16 │ Internal │ bfloat16 │ 3 │ │ concatenate.22 │ Internal │ bfloat16 │ 3 │ │ concatenate.3 │ Internal │ bfloat16 │ 3 │ │ concatenate.15 │ Internal │ bfloat16 │ 3 │ │ concatenate.2 │ Internal │ bfloat16 │ 3 │ │ concatenate.17 │ Internal │ bfloat16 │ 3 │ │ get_tuple_element.5 │ Internal │ float32 │ 3 │ │ concatenate.21 │ Internal │ bfloat16 │ 3 │ │ convert.656 │ Internal │ float32 │ 149 │ └─────────────────────┴──────────┴──────────┴──────────────────┘ 2025-11-09T20:55:13Z USER 293 (nc00/sg00) [Codegen]: dma_desc_gen finished after 0.039 seconds 2025-11-09T20:55:13Z INFO 293 (nc00/sg00) [Codegen]: Generating debug info 2025-11-09T20:55:13Z WARNING 293 (nc01/sg00) [Codegen]: Found 111 instructions with more than 100 dependencies. For each such instruction, skipping writing more than 100 dependencies into the built-in NEFF debug info to prevent excessive compile time and NEFF size. For those instructions, the Neuron profiler will not display the skipped dependencies. 2025-11-09T20:55:13Z USER 293 (nc01/sg00) [Codegen]: debug_info_gen finished after 0.421 seconds 2025-11-09T20:55:13Z USER 293 (nc01/sg00) [ModuleForkPass]: codegen finished after 1.151 seconds 2025-11-09T20:55:13Z INFO 293 (nc01/sg00) [ModuleForkPass]: curr_vmrss: 760mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:13Z INFO 293 (nc01/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 8557 memory location(s), 1 block(s), and 30629 instruction(s). Max writers: 151 Max Readers: 4215 2025-11-09T20:55:13Z WARNING 293 (nc00/sg00) [Codegen]: Found 112 instructions with more than 100 dependencies. For each such instruction, skipping writing more than 100 dependencies into the built-in NEFF debug info to prevent excessive compile time and NEFF size. For those instructions, the Neuron profiler will not display the skipped dependencies. 2025-11-09T20:55:13Z USER 293 (nc00/sg00) [Codegen]: debug_info_gen finished after 0.464 seconds 2025-11-09T20:55:13Z USER 293 (nc00/sg00) [ModuleForkPass]: codegen finished after 1.190 seconds 2025-11-09T20:55:13Z INFO 293 (nc00/sg00) [ModuleForkPass]: curr_vmrss: 735mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:13Z INFO 293 (nc00/sg00) [ModuleForkPass]: Output has 1 module(s), 1 function(s), 9361 memory location(s), 1 block(s), and 32844 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:13Z USER 293 [ModuleForkPass]: Compilation status: Total modules: 2, Passed: 2, Failed: 0 2025-11-09T20:55:13Z USER 293 [BackendPassManager]: mod_parallel_pass finished after 1.223 seconds 2025-11-09T20:55:13Z INFO 293 [BackendPassManager]: curr_vmrss: 687mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:13Z USER 293 [BackendPassManager]: Running hbm_usage 2025-11-09T20:55:13Z INFO 293 [BackendPassManager]: Inputs to hbm_usage: modules=2 functions=2 allocs=17918 blocks=2 instructions=63473 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:13Z INFO 293 (nc00/sg00) [HBMUsage]: ┌───────────────┬──────────┬───────────────────┐ │ DMA Ring Type │ I/O Size │ Spill/Reload Size │ ├───────────────┼──────────┼───────────────────┤ │ Copy │ 352.000B │ 371.562KB │ │ CCE │ 0.000B │ 673.312KB │ │ Transpose │ 0.000B │ 0.000B │ │ Replicate │ 0.000B │ 0.000B │ │ Overhead │ 2.000KB │ 158.000KB │ └───────────────┴──────────┴───────────────────┘ 2025-11-09T20:55:13Z INFO 293 (nc00/sg00) [HBMUsage]: ┌─────────────────────┬───────────┐ │ DRAM Memory Usage │ Size │ ├─────────────────────┼───────────┤ │ Total: │ 1.173GB │ │ Model Code │ 3.490MB │ │ Model Constants │ 837.758KB │ │ Unallocated Tensors │ 1.165GB │ │ Allocated Tensors │ 2.473MB │ │ DMA Ring IO │ 2.344KB │ │ DMA Ring Spill │ 1.175MB │ └─────────────────────┴───────────┘ 2025-11-09T20:55:13Z INFO 293 (nc01/sg00) [HBMUsage]: ┌───────────────┬──────────┬───────────────────┐ │ DMA Ring Type │ I/O Size │ Spill/Reload Size │ ├───────────────┼──────────┼───────────────────┤ │ Copy │ 224.000B │ 145.656KB │ │ CCE │ 0.000B │ 505.312KB │ │ Transpose │ 0.000B │ 0.000B │ │ Replicate │ 0.000B │ 0.000B │ │ Overhead │ 1.000KB │ 110.000KB │ └───────────────┴──────────┴───────────────────┘ 2025-11-09T20:55:13Z INFO 293 (nc01/sg00) [HBMUsage]: ┌─────────────────────┬───────────┐ │ DRAM Memory Usage │ Size │ ├─────────────────────┼───────────┤ │ Total: │ 1.172GB │ │ Model Code │ 3.265MB │ │ Model Constants │ 833.750KB │ │ Unallocated Tensors │ 1.165GB │ │ Allocated Tensors │ 2.473MB │ │ DMA Ring IO │ 1.219KB │ │ DMA Ring Spill │ 760.969KB │ └─────────────────────┴───────────┘ 2025-11-09T20:55:13Z INFO 293 [HBMUsage]: Total estimated HBM usage is: 1.179GB 2025-11-09T20:55:13Z USER 293 [BackendPassManager]: hbm_usage finished after 0.013 seconds 2025-11-09T20:55:13Z INFO 293 [BackendPassManager]: curr_vmrss: 687mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:13Z INFO 293 [BackendPassManager]: Output has 2 module(s), 2 function(s), 17918 memory location(s), 2 block(s), and 63473 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:13Z USER 293 [BackendPassManager]: Running neff_packager 2025-11-09T20:55:13Z INFO 293 [BackendPassManager]: Inputs to neff_packager: modules=2 functions=2 allocs=17918 blocks=2 instructions=63473 Max writers: 151 Max Readers: 4719 2025-11-09T20:55:13Z WARNING 293 [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 2025-11-09T20:55:13Z WARNING 293 [NeffFileWriter]: writeKelp missing file /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/neuronxcc-sij89sjf/metrics.json 2025-11-09T20:55:14Z INFO 293 [NeffFileWriter]: Neff will be written to: /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/model.MODULE_5e3d0ce8963512f9ea2d+937cd7a2.neff 2025-11-09T20:55:14Z INFO 293 [NeffFileWriter]: IR signature: 7476295f3e4593fcb0ad1fcc7c8aa870 for neff artifacts 2025-11-09T20:55:14Z USER 293 [BackendPassManager]: neff_packager finished after 0.382 seconds 2025-11-09T20:55:14Z INFO 293 [BackendPassManager]: curr_vmrss: 688mb, ru_maxrss: 800mb (delta=0mb) 2025-11-09T20:55:14Z INFO 293 [BackendPassManager]: Output has 2 module(s), 2 function(s), 17918 memory location(s), 2 block(s), and 63473 instruction(s). Max writers: 151 Max Readers: 4719 2025-11-09T20:55:14Z INFO 293 [BackendDriver]: HBM scratchpad usage summary (post-allocation): ┌──────┬───────────┬────────────────────────────────────────────────────────────┬─────────────┐ │ Core │ Subgraph │ Description │ Value │ ├──────┼───────────┼────────────────────────────────────────────────────────────┼─────────────┤ │ nc00 │ sg00 │ Peak scratchpad usage: local │ 0.000069 GB │ │ nc00 │ sg00 │ Peak scratchpad usage: local and shared │ 0.002415 GB │ │ nc00 │ sg00 │ Total size of allocated tensors: local │ 0.000092 GB │ │ nc00 │ sg00 │ Total size of allocated tensors: shared │ 0.002617 GB │ │ nc00 │ Max │ Peak scratchpad usage: local │ 0.000069 GB │ │ nc00 │ Max │ Peak scratchpad usage: local and shared │ 0.002415 GB │ │ nc00 │ Post-link │ Peak scratchpad usage after intermediate tensor allocation │ 0.000000 GB │ │ nc00 │ Post-link │ Total size of allocated intermediate tensors │ 0.000000 GB │ ├──────┼───────────┼────────────────────────────────────────────────────────────┼─────────────┤ │ nc01 │ sg00 │ Peak scratchpad usage: local │ 0.000072 GB │ │ nc01 │ sg00 │ Total size of allocated tensors: local │ 0.000072 GB │ │ nc01 │ Max │ Peak scratchpad usage: local │ 0.000072 GB │ ├──────┼───────────┼────────────────────────────────────────────────────────────┼─────────────┤ │ Max │ Max │ Peak scratchpad usage │ 0.002415 GB │ │ Max │ Max │ Peak scratchpad usage (page-aligned) │ 0.500000 GB │ └──────┴───────────┴────────────────────────────────────────────────────────────┴─────────────┘ 2025-11-09T20:55:14Z INFO 293 [BackendDriver]: Largest tensors at peak scratchpad usage, core=nc00, subgraph=sg00, addr_space=local (complete data located at nc00/sg00/memory_analysis_after_coloring_allocator_dram_shared_DRAM_Local_hwm_allocations.csv): ┌────────────────────────────────────────────────────────────────┬─────────┬───────────────┬─────────────┐ │ Tensor Name │ Type │ # Sub-tensors │ Total Size │ ├────────────────────────────────────────────────────────────────┼─────────┼───────────────┼─────────────┤ │ split_3 │ float32 │ 1 │ 0.062500 MB │ │ split_0 │ uint8 │ 1 │ 0.003906 MB │ │ split_2 │ int32 │ 1 │ 0.003906 MB │ └────────────────────────────────────────────────────────────────┴─────────┴───────────────┴─────────────┘ 2025-11-09T20:55:14Z INFO 293 [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 │ ├────────────────────────────────────────────────────────────────┼──────────┼───────────────┼─────────────┤ │ convert.656 │ float32 │ 1 │ 0.582031 MB │ │ all_reduce.111 │ bfloat16 │ 1 │ 0.015625 MB │ │ all_reduce.112 │ bfloat16 │ 1 │ 0.003906 MB │ │ get_tuple_element.1 │ float32 │ 1 │ 0.003906 MB │ │ get_tuple_element.2 │ uint32 │ 1 │ 0.003906 MB │ └────────────────────────────────────────────────────────────────┴──────────┴───────────────┴─────────────┘ 2025-11-09T20:55:14Z INFO 293 [BackendDriver]: Largest tensors at peak scratchpad usage, core=nc01, subgraph=sg00, addr_space=local (complete data located at nc01/sg00/memory_analysis_after_coloring_allocator_dram_shared_DRAM_Local_hwm_allocations.csv): ┌────────────────────────────────────────────────────────────────┬─────────┬───────────────┬─────────────┐ │ Tensor Name │ Type │ # Sub-tensors │ Total Size │ ├────────────────────────────────────────────────────────────────┼─────────┼───────────────┼─────────────┤ │ split_3 │ float32 │ 1 │ 0.062500 MB │ │ split_0 │ uint8 │ 1 │ 0.003906 MB │ │ split_1 │ float32 │ 1 │ 0.003906 MB │ │ split_2 │ int32 │ 1 │ 0.003906 MB │ └────────────────────────────────────────────────────────────────┴─────────┴───────────────┴─────────────┘ 2025-11-09T20:55:14Z INFO 293 [BackendDriver]: Backend completed successfully, tearing down. 2025-11-09T20:55:14Z INFO 252 [job.WalrusDriver.0]: VNCBackend: completed successfully. 2025-11-09T20:55:14Z INFO 252 [pipeline.Pipeline.0]: Finished job job.WalrusDriver.0 2025-11-09T20:55:14Z INFO 252 [pipeline.Pipeline.0]: Starting job job.BIRLinker.0 2025-11-09T20:55:14Z INFO 252 [job.BIRLinker.0]: Replay this job by calling: /opt/conda/bin/neuronx-cc compile --framework XLA --state '{"model": ["/models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/model.MODULE_5e3d0ce8963512f9ea2d+937cd7a2.hlo_module.pb"], "tensormap": "tensor_map.json", "bir": "bir.json", "lorean_sg_key": null, "input_name_map": null, "output_name_map": null, "constant_tensors": null, "state_dir": "/models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/neuronxcc-sij89sjf/nc00/sg00", "state_id": "nc00/sg00"}' --pipeline BIRLinker 2025-11-09T20:55:14Z INFO 252 [job.BIRLinker.0]: BIRLinker cwd: /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/neuronxcc-sij89sjf 2025-11-09T20:55:14Z INFO 252 [job.BIRLinker.0]: Linking already done. 2025-11-09T20:55:14Z INFO 252 [pipeline.Pipeline.0]: Finished job job.BIRLinker.0 2025-11-09T20:55:14Z INFO 252 [pipeline.Pipeline.0]: Starting job job.Kelper.0 2025-11-09T20:55:14Z INFO 252 [job.Kelper.0]: Skipping neff generation which was already performed by neff_packager 2025-11-09T20:55:14Z INFO 252 [pipeline.Pipeline.0]: Finished job job.Kelper.0 2025-11-09T20:55:14Z INFO 252 [pipeline.Pipeline.0]: Starting job job.NeffWrapper.0 2025-11-09T20:55:14Z INFO 252 [job.NeffWrapper.0]: Job NeffWrapper len(in_states) 1 2025-11-09T20:55:14Z INFO 252 [job.NeffWrapper.0]: Processing input #0 2025-11-09T20:55:14Z INFO 252 [job.NeffWrapper.0]: Start NeffWrapper 2025-11-09T20:55:14Z INFO 252 [job.NeffWrapper.0]: Executing: /opt/conda/lib/python3.11/site-packages/neuronxcc/starfish/bin/hlo-neff-wrapper --hlo /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/model.MODULE_5e3d0ce8963512f9ea2d+937cd7a2.hlo_module.pb --neff /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/model.MODULE_5e3d0ce8963512f9ea2d+937cd7a2.neff --io_transposes /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/neuronxcc-sij89sjf/io_transposes.json --output /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/wrapped_neff.hlo --netlist /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/neuronxcc-sij89sjf/hlo_netlist.json 2025-11-09T20:55:15Z INFO 252 [job.NeffWrapper.0]: Could not open file: /models/Qwen3-1.7B-compiled/token_generation_model/_tp0_bk0/neuronxcc-sij89sjf/hlo_netlist.json Hlo neff wrapper finished successfully. Have a wonderful day :D 2025-11-09T20:55:15Z INFO 252 [job.NeffWrapper.0]: Job #0 finished 2025-11-09T20:55:15Z INFO 252 [pipeline.Pipeline.0]: Finished job job.NeffWrapper.0 2025-11-09T20:55:15Z INFO 252 [pipeline.Pipeline.0]: Finished pipeline Pipeline 2025-11-09T20:55:15Z INFO 252 [pipeline.Pipeline.0]: Job #0 finished 2025-11-09T20:55:15Z INFO 240 [root]: Subcommand returned with exitcode=0