Files
project_6/muh/schema/rle_encode.yaml

156 lines
3.1 KiB
YAML
Raw Normal View History

# muh schema for rle_encode
# Auto-extracted from cub/cub/device/dispatch/tuning/tuning_rle_encode.cuh
# Generated by muh/extract.py
algorithm: rle_encode
source: cub/cub/device/dispatch/tuning/tuning_rle_encode.cuh
parameters:
threads_per_block:
type: int
range:
- 32
- 1024
step: 32
items_per_thread:
type: int
range:
- 1
- 32
step: 1
load_algorithm:
type: enum
values:
- BLOCK_LOAD_DIRECT
- BLOCK_LOAD_VECTORIZE
- BLOCK_LOAD_TRANSPOSE
- BLOCK_LOAD_WARP_TRANSPOSE
- BLOCK_LOAD_WARP_TRANSPOSE_TIMESLICED
- BLOCK_LOAD_STRIPED
load_modifier:
type: enum
values:
- LOAD_DEFAULT
- LOAD_CA
- LOAD_CG
- LOAD_CS
- LOAD_CV
- LOAD_LDG
scan_algorithm:
type: enum
values:
- BLOCK_SCAN_RAKING
- BLOCK_SCAN_RAKING_MEMOIZE
- BLOCK_SCAN_WARP_SCANS
lookback_delay.kind:
type: enum
values:
- no_delay
- fixed_delay
- exponential_backoff
- exponential_backoff_jitter
- exponential_backoff_jitter_window
- exponential_backon_jitter_window
- exponential_backon_jitter
- exponential_backon
lookback_delay.delay:
type: int
range:
- 0
- 2000
step: 50
lookback_delay.l2_write_latency:
type: int
range:
- 0
- 2000
step: 50
length_size:
type: int
range:
- 1
- 1024
step: 1
note: unknown_range
key_size:
type: int
range:
- 1
- 1024
step: 1
note: unknown_range
reference_tunings:
sm80:
-
threads: 256
items: 14
load_algorithm: BLOCK_LOAD_DIRECT
-
threads: 256
items: 13
load_algorithm: BLOCK_LOAD_DIRECT
-
threads: 256
items: 13
load_algorithm: BLOCK_LOAD_DIRECT
-
threads: 224
items: 9
load_algorithm: BLOCK_LOAD_WARP_TRANSPOSE
-
threads: 128
items: 7
load_algorithm: BLOCK_LOAD_WARP_TRANSPOSE
sm90:
-
threads: 256
items: 13
load_algorithm: BLOCK_LOAD_DIRECT
-
threads: 128
items: 22
load_algorithm: BLOCK_LOAD_DIRECT
-
threads: 192
items: 14
load_algorithm: BLOCK_LOAD_WARP_TRANSPOSE
-
threads: 128
items: 19
load_algorithm: BLOCK_LOAD_WARP_TRANSPOSE
-
threads: 128
items: 11
load_algorithm: BLOCK_LOAD_WARP_TRANSPOSE
sm100:
-
threads: 256
items: 14
load_algorithm: BLOCK_LOAD_DIRECT
load_modifier: LOAD_CA
-
threads: 224
items: 14
load_algorithm: BLOCK_LOAD_DIRECT
load_modifier: LOAD_DEFAULT
-
threads: 256
items: 14
load_algorithm: BLOCK_LOAD_DIRECT
load_modifier: LOAD_CA
-
threads: 224
items: 9
load_algorithm: BLOCK_LOAD_WARP_TRANSPOSE
load_modifier: LOAD_DEFAULT
-
threads: 128
items: 11
load_algorithm: BLOCK_LOAD_WARP_TRANSPOSE
-
nominal_4B_items_per_thread: 6
bi_v100:
status: pending_benchmark
note: Run muh benchmark on Iluvatar BI-V100 to fill these values
threads_per_block: TBD
items_per_thread: TBD