mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-04 13:41:24 +00:00
* FA fwd dropout * FA bwd * epilogue reuse * CMakeLists update * [CK_TILE] support alibi (#1269) * add alibi support * fix code * update code based on comment * Support more hdim * fix fp8 bias * support seqlen_k=0 case * remove unused printf * fix format --------- Co-authored-by: rocking <ChunYu.Lai@amd.com> * now fwd/bwd can build * bwd alibi * add bwd validation stream_config * update generated filenames * update bwd kernel launch * CK_TILE_HOST_DEVICE in philox * Transpose -> transpose * format * format * format * Generate the instance for FA required * format * fix error in WarpGemm * Add num_splits option and dummy split-kv api method * Generate fmha_fwd_splitkv() * Add SplitKV kernel codegen logics * Add SplitKV combine kernel codegen logics * Fix mismatched return type * Clean-up code * Replace sentinel value before storing * Fix wrong layout of LSE/LSEacc/Oacc * Format codes * Fix o_acc memory error * Fix wrong kBlockSize used in policy * Reduce # of combine kernels * Fix split-kv combine kernel name * Fix wrong LDS indexing logics * Fix wrong loop counter step logic * Undo vector size changes * Remove no-longer used field * Remove in-consistent comment * Remove debug statements in example * Remove more debug statements * Add constness to local variables * Clearn up generate.py * Fix unstable clang-format comment * Remove unused include directive * Use shorter template parameter name * Enable non-split-kv blobs * Update license date * Print num_splits conditionally * Undo disabling data types * Remove unnessary tile size for fp8 * Fix wrong pipeline args for fp8 * Fix example output format * Remove more debug code in combine pipeline * Add stride kernel arguments for LSE/O acc workspace * Re-order split-kv pipeline call operator arguments * Pass LSE/O strides in kernel argument * Re-order pipeline call operator arguments * Use tensor_descriptor to locate LSEacc elements * Support providing invalid element for tensor view * Set invalid element value for LSEacc tensor view * Remove hand-written store_tile() code * Remove necessary value-overwrite logic * Add transposed lds descriptor * Support load_tile() for tile_window_with_static_lengths<> * Undo removing necessary value-overwrite logic * Use read descriptor to locate lds elements * Simplify pipeline source code * Add constraint to kMaxSplits * Default use kMaxSplits=64 in generate.py * Revert "Add constraint to kMaxSplits" This reverts commit0a2132d758. * Revert "Default use kMaxSplits=64 in generate.py" This reverts commitc7d9c80b77. * Decide alignment by the padding parameter * Remove no-longer used utility functions * Remove not-working code * Add comment & remove no-longer used code * Fix computation errors * Add heuristic to override num_splits option * Add constraint to kMaxSplits * Fix compilation error * Clean up pipeline code * Wrap pointer access as lambda function * Rename confusing methods * Use kLogMasSplits as template parameter * Finish splitkv combine kernel codegen * Update kMaxSplits limit * Use smaller kM0 for splitkv combine kernel * Ignore droupout flag in splitkv pipeline * Unify flag usage * Add back flag kStoreLSE * Merge lambda calls in pipeline * Fix compilation errors * Avoid all empty splits * Always check for empty loop in splitkv pipelines * Re-order parameters * Remove redundant p_drop option check * Add traits/problem for fwd splitkv kernel * Conditionally enable uneven split boundary checks * Add comment for the splitkv traits field * Change even split criteria * Re-order statements * Refine occupancy value for hdim=128&256 * Refine occupancy value for hdim=32&64 * Remove redundant kernel argument * Separate fmha bwd codegen logics * Separate fmha fwd codegen logics * Remove redundant direction parameter in fwd&bwd codegen logics * Support generate multiple APIs for an example * Let 'api' an alias of 'direction' option * Remove choices for the 'direction' option * Use dictionary to config all the functions * Move fmha splitkv codegen logics to other file * Add fwd_splitkv api for tile_example_fmha_fwd --------- Co-authored-by: danyao12 <danyao12> Co-authored-by: carlushuang <carlus.huang@amd.com> Co-authored-by: rocking <ChunYu.Lai@amd.com> Co-authored-by: Jing Zhang <jizhan@amd.com>
106 lines
3.2 KiB
Python
106 lines
3.2 KiB
Python
# SPDX-License-Identifier: MIT
|
|
# Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
|
|
# generate kernel instances to speed up compilation
|
|
|
|
import argparse
|
|
from enum import IntEnum
|
|
from pathlib import Path
|
|
from typing import List, Optional
|
|
|
|
from codegen.cmake_config import *
|
|
from codegen.ops import (
|
|
fmha_fwd,
|
|
fmha_fwd_splitkv,
|
|
fmha_bwd
|
|
)
|
|
|
|
|
|
class HandlerId(IntEnum):
|
|
LIST_BLOBS = 0
|
|
WRITE_BLOBS = 1
|
|
|
|
handlers = {
|
|
'fwd' : (fmha_fwd.list_blobs, fmha_fwd.write_blobs),
|
|
'fwd_splitkv' : (fmha_fwd_splitkv.list_blobs, fmha_fwd_splitkv.write_blobs),
|
|
'bwd' : (fmha_bwd.list_blobs, fmha_bwd.write_blobs),
|
|
}
|
|
|
|
def write_blobs(output_dir: Optional[str], api_list : List[str], kernel_filter : Optional[str], receipt, mask_impl) -> None:
|
|
if output_dir is None:
|
|
output_dir = Path(__file__).parent
|
|
else:
|
|
output_dir = Path(output_dir) / GEN_DIR
|
|
|
|
output_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
for api in api_list:
|
|
handler = handlers[api][HandlerId.WRITE_BLOBS]
|
|
handler(output_dir, kernel_filter, receipt, mask_impl)
|
|
|
|
# list all the files that will be generated
|
|
def list_blobs(output_file : Optional[str], api_list : List[str], kernel_filter : Optional[str], receipt, mask_impl) -> None:
|
|
assert output_file is not None
|
|
file_path = Path(output_file)
|
|
|
|
for api in api_list:
|
|
handler = handlers[api][HandlerId.LIST_BLOBS]
|
|
handler(file_path, kernel_filter, receipt, mask_impl)
|
|
|
|
if __name__ == "__main__":
|
|
parser = argparse.ArgumentParser(
|
|
prog="generate",
|
|
description="gen API for CK fmha kernel",
|
|
)
|
|
parser.add_argument(
|
|
"-d",
|
|
"--direction", # we keep 'direction' option for backward compatibility
|
|
"-a",
|
|
"--api",
|
|
default='fwd',
|
|
required=False,
|
|
help="supply API(s) to generate (default: fwd). separated by comma."
|
|
)
|
|
parser.add_argument(
|
|
"-o",
|
|
"--output_dir",
|
|
required=False,
|
|
help="write all the blobs into a directory"
|
|
)
|
|
parser.add_argument(
|
|
"-l",
|
|
"--list_blobs",
|
|
required=False,
|
|
help="list all the kernels to a file"
|
|
)
|
|
# TODO: if using filter, must apply same value to output_dir and list_blobs
|
|
parser.add_argument(
|
|
"-f",
|
|
"--filter",
|
|
required=False,
|
|
help="filter out kernels that need to generate, using fnmatch module"
|
|
)
|
|
|
|
parser.add_argument(
|
|
"-m",
|
|
"--mask",
|
|
default="simplified",
|
|
required=False,
|
|
help="mask implementation, simplified/generic"
|
|
)
|
|
|
|
parser.add_argument(
|
|
"-r",
|
|
"--receipt",
|
|
default=0,
|
|
required=False,
|
|
help="codegen receipt. 0: generate only 8xhdim coverage\n" + \
|
|
" 1: generate more instance to cover all hdim\n" + \
|
|
" 2: Only generate instance for Flash attention integration"
|
|
)
|
|
|
|
args = parser.parse_args()
|
|
api_list = args.direction.split(',')
|
|
if args.list_blobs is not None:
|
|
list_blobs(args.list_blobs, api_list, args.filter, int(args.receipt), mask_impl=args.mask)
|
|
else:
|
|
write_blobs(args.output_dir, api_list, args.filter, int(args.receipt), mask_impl=args.mask) |