ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-18 12:00:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '2b684f0a7d2317b1b1f001716acb62f566cc71ee' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-09-29 16:12:12 +00:00
parent 091c5200ce
commit 2e7d600076
22 changed files with 74 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
example/35_splitK_gemm/gemm_xdl_splitk_reduce_bf16.cpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#include "common.hpp"
@@ -35,13 +35,13 @@ using DeviceGemmV2Instance =
256,
128, 128, 64,
8, 4,
32, 32,
2, 2,
16, 16,
4, 4,
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>,
2, 8, 8, 0,
S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>,
1, 8, 4, 0,
1, 1, S<1, 32, 1, 8>, 8,
1, 1, S<1, 32, 1, 8>, 4,
ck::BlockGemmPipelineScheduler::Intrawave,ck::BlockGemmPipelineVersion::v3>;
// clang-format on

8
example/35_splitK_gemm/gemm_xdl_splitk_reduce_bf16A_i8B.cpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#include "common.hpp"
@@ -35,13 +35,13 @@ using DeviceGemmV2Instance =
256,
128, 128, 64,
8, 4,
32, 32,
2, 2,
16, 16,
4, 4,
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>,
2, 8, 8, 0,
S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>,
1, 8, 4, 0,
1, 1, S<1, 32, 1, 8>, 8,
1, 1, S<1, 32, 1, 8>, 4,
ck::BlockGemmPipelineScheduler::Intrawave,ck::BlockGemmPipelineVersion::v3, ReduceDataType>;
// clang-format on

8
example/35_splitK_gemm/gemm_xdl_splitk_reduce_multi_d_bf16.cpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#include "common.hpp"
@@ -35,13 +35,13 @@ using DeviceGemmV2Instance =
256,
128, 128, 64,
8, 4,
32, 32,
2, 2,
16, 16,
4, 4,
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>,
2, 8, 8, 0,
S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>,
1, 8, 4, 0,
1, 1, S<1, 32, 1, 8>, 8,
1, 1, S<1, 32, 1, 8>, 4,
ck::BlockGemmPipelineScheduler::Intrawave,ck::BlockGemmPipelineVersion::v3, ReduceDataType>;
// clang-format on

8
example/35_splitK_gemm/gemm_xdl_splitk_reduce_multi_d_fp16.cpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#include "common.hpp"
@@ -35,13 +35,13 @@ using DeviceGemmV2Instance =
256,
128, 128, 64,
8, 4,
32, 32,
2, 2,
16, 16,
4, 4,
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>,
2, 8, 8, 0,
S<16, 16, 1>, S<0, 2, 1>, S<0, 2, 1>,
1, 8, 4, 0,
1, 1, S<1, 32, 1, 8>, 8,
1, 1, S<1, 32, 1, 8>, 4,
ck::BlockGemmPipelineScheduler::Intrawave,ck::BlockGemmPipelineVersion::v2, ReduceDataType>;
// clang-format on