Files
project_6_89d52222/muh/schema/batched_topk.yaml

47 lines
1.1 KiB
YAML
Raw Normal View History

# muh schema for batched_topk
# Auto-extracted from cub/cub/device/dispatch/tuning/tuning_batched_topk.cuh
# Generated by muh/extract.py
algorithm: batched_topk
source: cub/cub/device/dispatch/tuning/tuning_batched_topk.cuh
parameters:
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
store_algorithm:
type: enum
values:
- BLOCK_STORE_DIRECT
- BLOCK_STORE_WARP_TRANSPOSE
- BLOCK_STORE_WARP_TRANSPOSE_TIMESLICED
- BLOCK_STORE_STRIPED
scan_algorithm:
type: enum
values:
- BLOCK_SCAN_RAKING
- BLOCK_SCAN_RAKING_MEMOIZE
- BLOCK_SCAN_WARP_SCANS
threads_per_block:
type: int
range:
- 32
- 1024
step: 32
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