Files
composable_kernel/example/01_gemm/gemm_xdl_fp16_v2.cpp
Michał Kulikowski 2b684f0a7d [CK][Examples] Extending support for rdna3/4 in following examples: (#2884)
* [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>
2025-09-29 09:05:04 -07:00

63 lines
2.4 KiB
C++

// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#include "common.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_v2.hpp"
using ADataType = ck::half_t;
using BDataType = ck::half_t;
using AccDataType = float;
using CShuffleDataType = ck::half_t;
using CDataType = ck::half_t;
using F16 = ck::half_t;
using F32 = float;
using ALayout = Row;
using BLayout = Row;
using CLayout = Row;
using AElementOp = PassThrough;
using BElementOp = PassThrough;
using CElementOp = PassThrough;
static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
// clang-format off
using DeviceGemmInstance =
ck::tensor_operation::device::DeviceGemm_Xdl_CShuffleV2<
ALayout, BLayout, CLayout,
F16, F16, F16, F32, F16,
PassThrough, PassThrough, PassThrough, GemmDefault,
2, 256,
256, 256,
32, 8, 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>, 4,
ck::LoopScheduler::Default, ck::PipelineVersion::v1>;
// clang-format on
using ReferenceGemmInstance = ck::tensor_operation::host::
ReferenceGemm<ADataType, BDataType, CDataType, AccDataType, AElementOp, BElementOp, CElementOp>;
using ReferenceGemmInstanceGPU = ck::tensor_operation::device::ReferenceGemm<ALayout,
BLayout,
CLayout,
ADataType,
BDataType,
CDataType,
AccDataType,
AElementOp,
BElementOp,
CElementOp>;
#include "run_gemm_example.inc"
int main(int argc, char* argv[]) { return !run_gemm_example(argc, argv); }