ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-21 13:29:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '68134b60e45612b54f6c3165e39078676b41928d' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-08-16 00:34:38 +00:00
parent 0c5b4ba101
commit 30421aa6c5
54 changed files with 1388 additions and 403 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
example/02_gemm_bilinear/gemm_bilinear_wmma_fp16.cpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#include <iostream>
#include <numeric>

2
example/02_gemm_bilinear/gemm_bilinear_wmma_int8.cpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#include <iostream>
#include <numeric>

2
example/02_gemm_bilinear/gemm_bilinear_xdl_fp16.cpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#include <iostream>
#include <numeric>

2
example/60_gemm_multi_ABD/gemm_multi_ABD_xdl_fp16.cpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#include <iostream>
#include <numeric>

2
example/61_contraction_multi_ABD/contraction_multi_ABD_xdl_fp16.cpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2023, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2023-2025, Advanced Micro Devices, Inc. All rights reserved.
#include <iostream>
#include <numeric>

21
example/ck_tile/03_gemm/gemm_utils.hpp
View File

@@ -172,6 +172,27 @@ struct GemmConfigComputeV3_2 : public GemmConfigBase
static constexpr int kBlockPerCu = 2;
};
template <typename PrecType>
struct GemmConfigComputeV3_WMMA : public GemmConfigBase
{
static constexpr ck_tile::index_t M_Tile = 128;
static constexpr ck_tile::index_t N_Tile = 128;
static constexpr ck_tile::index_t K_Tile = 64 / sizeof(PrecType);
static constexpr ck_tile::index_t M_Warp = 4;
static constexpr ck_tile::index_t N_Warp = 2;
static constexpr ck_tile::index_t K_Warp = 1;
static constexpr ck_tile::index_t M_Warp_Tile = 16;
static constexpr ck_tile::index_t N_Warp_Tile = 16;
static constexpr ck_tile::index_t K_Warp_Tile = 16;
static constexpr bool DoubleSmemBuffer = false;
static constexpr ck_tile::index_t Pipeline = CK_TILE_PIPELINE_COMPUTE_V3;
static constexpr int kBlockPerCu = 2;
};
template <typename PrecType>
struct GemmConfigComputeV4 : public GemmConfigBase
{

1
example/ck_tile/03_gemm/universal_gemm.cpp
View File

@@ -346,5 +346,4 @@ int main(int argc, char* argv[])
// Return a non-zero code to indicate failure
return EXIT_FAILURE;
}
return EXIT_SUCCESS;
}

0
example/ck_tile/17_grouped_gemm/grouped_gemm.cpp Executable file → Normal file
View File