Files
composable_kernel/example/01_gemm/gemm_xdl_fp8_v3.cpp
Haocong WANG 8c90f25be3 [GEMM] F8 GEMM, performance optimized. (#1384)
* add ab_scale init support

* enabled interwave

* add scale type; update isSupport

* adjust example

* clean

* enable f8 pure gemm rcr ckprofiler

* Add gemm_multiply_multiply instances

* clang format

* Optimize for ScaleBlockMNK=128

* enable abscale f8 gemm ck profiler

* Add pure f8 gemm test suite

* Reverting to the state of project at f60fd77

* update copyright

* clang format

* update copyright

---------

Co-authored-by: root <jizhan@amd.com>
2024-07-19 22:06:52 +08:00

49 lines
1.6 KiB
C++

// SPDX-License-Identifier: MIT
// Copyright (c) 2023-2024, Advanced Micro Devices, Inc. All rights reserved.
#include "common.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_v3.hpp"
using ADataType = ck::f8_t;
using BDataType = ck::f8_t;
using AccDataType = float;
using CShuffleDataType = ck::half_t;
using CDataType = ck::half_t;
using ALayout = Row;
using BLayout = Col;
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 DeviceGemmV2Instance =
ck::tensor_operation::device::DeviceGemm_Xdl_CShuffleV3<
ALayout, BLayout, CLayout,
ADataType, BDataType, CDataType, AccDataType, CShuffleDataType,
PassThrough, PassThrough, PassThrough, GemmDefault,
256,
224, 256,
128, 16, 16,
16, 16,
7, 8,
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>,
2, 16, 16, 0,
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>,
2, 16, 16, 0,
1, 2, S<1, 32, 1, 8>, 8,
ck::BlockGemmPipelineScheduler::Intrawave,ck::BlockGemmPipelineVersion::v3, ck::f8_t>;
// clang-format on
using ReferenceGemmInstance = ck::tensor_operation::host::
ReferenceGemm<ADataType, BDataType, CDataType, AccDataType, AElementOp, BElementOp, CElementOp>;
#include "run_gemm_example_v2.inc"
int main(int argc, char* argv[]) { return !run_gemm_splitk_example(argc, argv); }