project_6/muh/schema/transform.yaml

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

algorithm: transform
source: cub/cub/device/dispatch/tuning/tuning_transform.cuh
parameters:
  threads_per_block:
    type: int
    range:
      - 32
      - 1024
    step: 32
  items_per_thread_no_input:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  min_items_per_thread:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  max_items_per_thread:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  prefetch_byte_stride:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  unroll_factor:
    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
  store_vec_size:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  min_bytes_in_flight:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  copy_alignment:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  smem_size:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  tile_padding:
    type: int
    range:
      - 1
      - 1024
    step: 1
    note: unknown_range
  max_alignment:
    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