ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 14:59:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK][Examples] Extending support for rdna3/4 in following examples: (#2884)

Browse Source 
* [CK][Examples] Extending support for rdna3/4 in following examples:
-example_gemm_xdl_splitk_reduce_multi_d_fp16
-example_gemm_xdl_splitk_reduce_multi_d_bf16
-example_gemm_xdl_splitk_reduce_bf16A_i8B
-example_gemm_xdl_splitk_reduce_bfp16
-example_splitk_gemm_bias_e_permute_xdl_fp32
-example_gemm_add_multiply_xdl_fp16
-example_complex_contraction_bilinear_xdl_fp32
-example_grouped_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16
-example_batched_gemm_bias_e_permute_xdl_fp16
-example_gemm_xdl_fp16
-example_gemm_xdl_fp16_av2
-example_gemm_xdl_wavelet_fp16
-example_gemm_add_add_fastgelu_xdl_bf16
-example_gemm_add_add_fastgelu_xdl_fp16
-example_gemm_add_add_fastgelu_xdl_fp32
-example_grouped_gemm_xdl_fp32
-example_grouped_gemm_xdl_fp16
-example_grouped_gemm_xdl_bf16
-example_cgemm_xdl_bf16
-example_cgemm_xdl_fp16

Signed-off-by: Michal Kulikowski <Michal.Kulikowski@amd.com>

* [CK][Examples] Extending support for rdna3/4 in following examples:
-example_gemm_xdl_splitk_reduce_multi_d_fp16
-example_gemm_xdl_splitk_reduce_multi_d_bf16
-example_gemm_xdl_splitk_reduce_bf16A_i8B
-example_gemm_xdl_splitk_reduce_bfp16
-example_splitk_gemm_bias_e_permute_xdl_fp32
-example_gemm_add_multiply_xdl_fp16
-example_complex_contraction_bilinear_xdl_fp32
-example_grouped_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16
-example_batched_gemm_bias_e_permute_xdl_fp16
-example_gemm_xdl_fp16
-example_gemm_xdl_fp16_av2
-example_gemm_xdl_wavelet_fp16
-example_gemm_add_add_fastgelu_xdl_bf16
-example_gemm_add_add_fastgelu_xdl_fp16
-example_gemm_add_add_fastgelu_xdl_fp32
-example_grouped_gemm_xdl_fp32
-example_grouped_gemm_xdl_fp16
-example_grouped_gemm_xdl_bf16
-example_cgemm_xdl_bf16
-example_cgemm_xdl_fp16

Signed-off-by: Michal Kulikowski <Michal.Kulikowski@amd.com>

---------

Signed-off-by: Michal Kulikowski <Michal.Kulikowski@amd.com>
This commit is contained in:
Michał Kulikowski
2025-09-29 18:05:04 +02:00
committed by GitHub
parent 0f04f020d9
commit 2b684f0a7d
22 changed files with 74 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
example/01_gemm/gemm_xdl_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"
@@ -37,7 +37,7 @@ using DeviceGemmInstance1 = ck::tensor_operation::device::DeviceGemm_Xdl_CShuffl
// ######| | | | Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Spacialization| Prefetch| Size| Block| Block| Block| | | XDL| XDL| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
// ######| | | | | | | | | Operation| Operation| Operation| | Stage| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
// ######| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AccDataType, CShuffleDataType, AElementOp, BElementOp, CElementOp, GemmDefault, 1, 256, 256, 128, 32, 8, 2, 32, 32, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 2, S<1, 16, 1, 16>, 8, ck::LoopScheduler::Interwave, ck::PipelineVersion::v1>;
< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AccDataType, CShuffleDataType, AElementOp, BElementOp, CElementOp, GemmDefault, 1, 256, 256, 128, 32, 8, 2, 16, 16, 8, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 2, S<1, 16, 1, 16>, 4, ck::LoopScheduler::Interwave, ck::PipelineVersion::v1>;
// clang-format on
using DeviceGemmInstance = DeviceGemmInstance1;

8
example/01_gemm/gemm_xdl_fp16_v2.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"
@@ -33,13 +33,13 @@ using DeviceGemmInstance =
2, 256,
256, 256,
32, 8, 4,
32, 32,
4, 4,
16, 16,
8, 8,
S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>,
2, 8, 8, 0,
S<8, 32, 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::LoopScheduler::Default, ck::PipelineVersion::v1>;
// clang-format on

4
example/01_gemm/gemm_xdl_wavelet_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"
@@ -29,7 +29,7 @@ using DeviceGemmInstance = ck::tensor_operation::device::DeviceGemm_Xdl_WaveletM
// ######| | | | Type| Type| Type| DataType| Type| Elementwise| Elementwise| Elementwise| Spacialization| Prefetch| ThreadGroupSize| ThreadGroupSize| Block| Block| Block| | | XDL| XDL| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MWaveMPerXdl| ScalarPerVector|
// ######| | | | | | | | | Operation| Operation| Operation| | Stage| | | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
// ######| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
< ALayout, BLayout, CLayout, ADataType, BDataType, AccDataType, F16, CDataType, AElementOp, BElementOp, CElementOp, GemmDefault, 1, 256, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1,8>, 8>;
< ALayout, BLayout, CLayout, ADataType, BDataType, AccDataType, F16, CDataType, AElementOp, BElementOp, CElementOp, GemmDefault, 1, 256, 256, 256, 128, 32, 8, 8, 16, 16, 8, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1,8>, 4>;
// clang-format on
using DeviceGemmInstance = DeviceGemmInstance;