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

algorithm: batch_memcpy
source: cub/cub/device/dispatch/tuning/tuning_batch_memcpy.cuh
parameters:
  threads_per_block:
    type: int
    range:
      - 32
      - 1024
    step: 32
  buffers_per_thread:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  bytes_per_thread:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  block_level_tile_size:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  warp_level_threshold:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  block_level_threshold:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  buffer_lookback_delay:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  block_lookback_delay:
    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