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

algorithm: segmented_reduce
source: cub/cub/device/dispatch/tuning/tuning_segmented_reduce.cuh
parameters:
  threads_per_block:
    type: int
    range:
      - 32
      - 1024
    step: 32
  threads_per_warp:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  items_per_thread:
    type: int
    range:
      - 1
      - 32
    step: 1
  vec_size:
    type: int
    range:
      - 1
      - 8
    step: 1
  load_modifier:
    type: enum
    values:
      - LOAD_DEFAULT
      - LOAD_CA
      - LOAD_CG
      - LOAD_CS
      - LOAD_CV
      - LOAD_LDG
  offset_size:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  accum_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