project_6/muh/schema/radix_sort.yaml

# muh schema for radix_sort
# Auto-extracted from cub/cub/device/dispatch/tuning/tuning_radix_sort.cuh
# Generated by muh/extract.py

algorithm: radix_sort
source: cub/cub/device/dispatch/tuning/tuning_radix_sort.cuh
parameters:
  threads_per_block:
    type: int
    range:
      - 32
      - 1024
    step: 32
  items_per_thread:
    type: int
    range:
      - 1
      - 32
    step: 1
  private_partitions:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  radix_bits:
    type: int
    range:
      - 4
      - 8
    step: 1
  scan_algorithm:
    type: enum
    values:
      - BLOCK_SCAN_RAKING
      - BLOCK_SCAN_RAKING_MEMOIZE
      - BLOCK_SCAN_WARP_SCANS
  rank_private_partitions:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  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
  threads:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  items:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  key_size:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  value_size:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  offset_size:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
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