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

algorithm: reduce
source: cub/cub/device/dispatch/tuning/tuning_reduce.cuh
parameters:
  threads_per_block:
    type: int
    range:
      - 32
      - 1024
    step: 32
  items_per_thread:
    type: int
    range:
      - 1
      - 32
    step: 1
  vec_size:
    type: int
    range:
      - 1
      - 8
    step: 1
  reduce_algorithm:
    type: enum
    values:
      - BLOCK_REDUCE_RAKING
      - BLOCK_REDUCE_RAKING_COMMUTATIVE_ONLY
      - BLOCK_REDUCE_WARP_REDUCTIONS
  load_modifier:
    type: enum
    values:
      - LOAD_DEFAULT
      - LOAD_CA
      - LOAD_CG
      - LOAD_CS
      - LOAD_CV
      - LOAD_LDG
  items:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  threads:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  items_per_vec_load:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  offset_size:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  accum_size:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
reference_tunings:
  sm100:
    -
      items: 15
      threads: 512
      items_per_vec_load: 2
    -
      items: 15
      threads: 512
      items_per_vec_load: 1
    -
      items: 16
      threads: 512
      items_per_vec_load: 2
    -
      items: 16
      threads: 640
      items_per_vec_load: 1
    -
      threads_per_block: 256
      items_per_thread: 16
      items_per_vec_load: 4
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