mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 13:11:25 +00:00
* Use dictionary to config all the functions * Add init codegen logic for fmha fwd appendkv * Call HIP_CHECK_ERROR() macro to get real source info * Setup meaningfull arguments * Sync kernel name with the codegen * Add knew/vnew tensors to the kernel argument * Fix wrong K values after appending * Fix vnew append errro * Extract common logics * Fix Vnew tile dstr for row major case * Conditionally add fwd_splitkv API in fmha_fwd example * Conditionally add call to fmha_fwd_splitkv() * Remove "EXAMPLE_" prefix of cmake variables * Regsiter API handlers automatically * Early return if 0 < s_k_new is not supported * Show message if we are ignoring option * Unify CMakeLists.txt coding style * Set num_splits=1 if split-kv is not supported * Add length/stride getters for HostTensor * Add RoPE example utilities * Add reference_rotary_position_embedding() (not implemented) * Finish reference_rotary_position_embedding() impl * Fix typo of HostTensor<>::get_length() * Fix compilation errors * Fix wrong answer when interleaved=false * Fix wrong answer when interleaved=true * Append K/V in the host verification code * Simplify K appending logics * Simplify v_host_ref definition * Reduce input/output dimensions * Rename function: add "batched" prefix * Apply RoPE on host side * Rename RoPE utility function * Fix wrong tensor size * Avoid invoking deprecated method 'find_module' * Pass RoPE kernel args * Create Rotary Cos/Sin tile windows in kernel * Add compute data type alias for RoPE * Randomly generate seqlen_knew if needed * Fix seqlen_knew enabling check logic * Add minimum seqlen_k to generate compliance kvcache * Fix compilation error in debug mode * Fix wrong boundaries * Fix wrong seqlen_k for kvcache * Rename variables used in distributio encoding * Fix rotary cos/sin tensor/tile size * Add constraint to the rotary_dim option * Remove unused inner namespace * Add dram distribution for rotary_cos/rotary_sin (interleaved) * Only apply interleaved RoPE on Knew for now * Fix wrong thread starting offset * Instantiate multiple kernels for RoPE approaches * Clean-up pipeline * Fix error in RoPE host reference * Handle RoPE half-rotated logics * Support 8x rotary_dim under half-rotated RoPE * Add comment * Apply elementwise function to the loaded tiles * Unify parameter/variable naming style * Remove constness from q_ptr * Add code blocks for q_tile * Apply RoPE to q_tile * Remove debug print code in kernel * Fix wrong knew/vnew appending positions * Use better naming for tile indices * Add make_tile_window() for adding distribution only * Skip code if # of block is more than needed * Move thread locating logics into policy * Remove always true static_assert() * Rename header * Rename RotaryEmbeddingEnum * Extract rotary embedding logic out * Re-order parameters * Align naming of some tile size constants * Rename more tile size constants * Fix wrong grid size * Fix wrong shape of knew_host/vnew_host * Fix wrong index into knew_host/vnew_host * Fix wrong rotary_cos/rotary_sin memory size for Q * Extract Q/Knew vector size to helper methods * Use different rotary_cos/rotary_sin distr for Q/Knew * Update host/device specifiers * Fix wrong data type for Q rotary_cos/rotary_sin * Remove RoPEComputeDataType type alias * Shift rotary_cos/rotary_sin by cache_seqlen_k * Add comment for why I just 't' for all padding flags * Align commit message to the real comment * Fix wrong pipeline * Rename utility function * Disable host verification if API not exist * Fix wrong rope key for fp8 pipeline * Allow only apply RoPE on Q (without append KV) * Add append-kv smoke tests * Remove debug statements * Remove more debug statements * Re-arrange the 'set +x' command * Remove no-longer used method in pipeline * Add missing init code * Refine pipeline padding settings * Enlarge rotary_dim limit (8 -> 16) * Enlarge KPerThread for rotary_interleaved=false * Update rotary_dim range in smoke_test_fwd.sh * Add template argument 'kIsPagedKV' for splitkv kernels * Launch splitkv kernel if given page_block_size * Fix wrong kernel name * Fix seqlen_k_min for pre-fill case (1 -> 0) * Add copy_const<> type trait * Add another make_tile_window() * Introduce 'TileWindowNavigator' types * Simplify TileWindowNavigator interfaces * Fix tile window navigation bugs * Disable calling fmha_fwd() * Remove ununnecessary data members * Simplify more make_tile_window() overloads * Move V tile through TileWindowNavigator * Fix uneven split checking logic * Move code after decide seqlen_q/seqlen_k * Make sure we always start reading complete tile * Use 128 as minimus page_block_size * Fix wrong origin for bias * Add batch_stride_k/batch_stride_v in group mode * Unify origin * Add missing kernel arguments for group mode * Add paged-kv codegen logic for appendkv kernels * Add block_table kernel args for appendkv kernel * Add tile navigators to the appendkv kernel * Fix wrong tensor descriptor lengths * Pass re-created tile window to pipeline * Fix wrong strides for appendkv kernel * Allow transit tile_window to another page-block * Handle cross-page-block write * Donot perform write again if already in last page-block * Always add fmha_fwd() api * Add missing group mode argument * Remove debug macro usages * Rename option s_k_new to s_knew * Separate splitkv/non-splitkv args/traits * Remove fmha_fwd_dispatch() * Fix compilation errors * Remove dropout code in splitkv kernel * Allow problem types without define kHasDropout attr * Use generic lambda to init traits objects * Separate more non-splitkv & splitkv traits/args * Display more info for specific kernels * Show more detailed warning message * Rename 'max_num_blocks' to 'max_num_page_blocks' * Remove no-longer used pipeline files * Wrap code by #if directives * Move functors to the begining of validation code * Use generic lambda to init all the api traits/args * Fix wrong seqlen for kvcache * Add missing comment * Rename TileWindowNavigator to PageBlockNavigator * Only expose necessary methods (not attributes) * Re-order pipeline paremeters * Refine smoke_test_fwd.sh * Fix wrong arugment count * Make tile window directly via PageBlockNavigator * Remove unused template paremeter * Remove group mode from appendkv kernel * Fix skcheck logic * Fix wrong syntax in skcheck expr * Use meaningful options in smoke test * Remove options * Fix formatting * Fix more format * Re-organize bash functions * Pass cache_batch_idx to kernels * Support cache_batch_idx in example * Fix compilation error * Add more appendkv test * Add more case for appendkv * Fix unexisted attribute * Remove 0 < seqlen_knew constraint * Clarify the case in warning message * Remove macro checking * Force batch mode when invoking appendkv & splitkv apis * Fix mode overriding logics * Fix wrong parameter name * Randomize seqlen_k if use kvcache * Use randomized seqlen_k for kvcache * Avoid using too small rotary_cos & rotary_sin * Rename parameter * Add seqlen_q & seqlen_k rules * Add comment * Add more comments * Fix compilation errors * Fix typo in comment * Remove type argument * Avoid seqlen_k=0 for kvcache * Revert "Avoid seqlen_k=0 for kvcache" This reverts commit21c4df89e4. * Fix wrong uneven split checking logics * Only randomize kvcache seqlen_k if 1 < batch * Return earlier if split is empty * Revert "Only randomize kvcache seqlen_k if 1 < batch" This reverts commitb9a4ab0d7e. * Re-order seqlen_k_start adjustment logics * Fix compilation errors * Re-format script * Find executable from folder automatically * Fix kvcache seqlen_k generating logic * Make comment more clear * Fix wrong knew/vew appending logic on host * Add s_barrier to sync threads * Revert "Add s_barrier to sync threads" This reverts commitd3f550f30c. * Support only using 1 row of rotary_cos/rotary_sin * Rotate Q in different way * Unify tensor view creation logics * Fix wrong argument * Add mask to switch how we use the rotary_cos/sin * Move attr from traits to problem * Move has_mask to fmha_fwd_appendkv_args * Support use uint32_t as SAD operand in Alibi<> * Use sad_u32() in splitkv kernels * Store tensor views in PageBlockNavigator * Use stored tensor view to update tile windows * Enlarge tensor view size * Remove debug code * Fix wrong tensor view size * Wrap tensor view into PageBlockNavigator * Add DataType member to PageBlockNavigator * Remove unnecessary member functions * Refind macro use * Fix typo * Add blank line between directives and actual code * Re-format files * Remove type in comment --------- Co-authored-by: carlushuang <carlus.huang@amd.com> Co-authored-by: rocking <ChunYu.Lai@amd.com>
112 lines
3.5 KiB
Python
112 lines
3.5 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
|
|
import pkgutil
|
|
import sys
|
|
from typing import List, Optional
|
|
|
|
import codegen.ops
|
|
from codegen.cmake_config import *
|
|
|
|
|
|
class HandlerId(IntEnum):
|
|
LIST_BLOBS = 0
|
|
WRITE_BLOBS = 1
|
|
|
|
# inspect all modules under 'codegen.ops' and register API handlers
|
|
ops = []
|
|
for importer, module_name, _ in pkgutil.iter_modules(codegen.ops.__path__):
|
|
full_module_name = '%s.%s' % (codegen.ops.__name__, module_name)
|
|
if full_module_name not in sys.modules:
|
|
ops.append(importer.find_spec(module_name).loader.load_module(module_name))
|
|
unwanted_prefix = 'fmha_'
|
|
handlers = dict(
|
|
[(op.__name__[len(unwanted_prefix):] if op.__name__.startswith(unwanted_prefix) else op.__name__,
|
|
(op.list_blobs, op.write_blobs)) for op in ops]
|
|
)
|
|
assert 0 < len(handlers)
|
|
|
|
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)
|