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

algorithm: merge_sort
source: cub/cub/device/dispatch/tuning/tuning_merge_sort.cuh
parameters:
  ItemsPerThread:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  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
  store_algorithm:
    type: enum
    values:
      - BLOCK_STORE_DIRECT
      - BLOCK_STORE_WARP_TRANSPOSE
      - BLOCK_STORE_WARP_TRANSPOSE_TIMESLICED
      - BLOCK_STORE_STRIPED
  key_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