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

algorithm: topk
source: cub/cub/device/dispatch/tuning/tuning_topk.cuh
parameters:
  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
  scan_algorithm:
    type: enum
    values:
      - BLOCK_SCAN_RAKING
      - BLOCK_SCAN_RAKING_MEMOIZE
      - BLOCK_SCAN_WARP_SCANS
  bits_per_pass:
    type: int
    range:
      - 4
      - 11
    step: 1
  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