ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 10:09:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

CK-Tile Grouped GEMM refactor and post PR fixes (#1756)

Browse Source 
* Grouped gemm simple code refactor

* Offset invoker

* Invoke generic Run, and replace name of parrtitioner variable

* Tests fix type

* Removed namespaces

* Add template param to avoid implicit cast

* Remove generic function

* Constant value

* underline enum to int16_t

* Generalize partitioner function

* Remove whitespaces

* Rename function

* Using support

* Clang-format

* Clang-format

* Fn-partitioner description fn

* Typo

* Typo 2

* Better description

* Better description

* Refactor after review

* Use ctr instead of set fn

* Inovke ctr and typo

* Comments

* Remove unnecessary comment

* Review, remove modulo

[ROCm/composable_kernel commit: 3c93d3c444]
This commit is contained in:
Mateusz Ozga
2025-01-21 21:06:10 +01:00
committed by GitHub
parent dde428cdf9
commit 91b54b683e
17 changed files with 363 additions and 388 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
example/ck_tile/03_gemm/gemm_basic.cpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
#include <hip/hip_runtime.h>
@@ -49,7 +49,7 @@ float gemm_calc(const ck_tile::GemmHostArgs& args, const ck_tile::stream_config&
ck_tile::sequence<M_Warp, N_Warp, K_Warp>,
ck_tile::sequence<M_Warp_Tile, N_Warp_Tile, K_Warp_Tile>>;
using TilePartitioner = ck_tile::GemmTilePartitioner<CodegenGemmShape>;
using TilePartitioner = ck_tile::GemmTile2DPartitioner<CodegenGemmShape>;
using GemmEpilogue = std::conditional_t<
CShuffleEpilogue,
@@ -61,8 +61,8 @@ float gemm_calc(const ck_tile::GemmHostArgs& args, const ck_tile::stream_config&
kOutputRank,
1,
0,
TilePartitioner::kM,
TilePartitioner::kN>>,
TilePartitioner::MPerBlock,
TilePartitioner::NPerBlock>>,
ck_tile::Default2DEpilogue<
ck_tile::Default2DEpilogueProblem<AccDataType, CDataType, kPadM, kPadN>>>;