mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 21:21:22 +00:00
f83e9701e9
* Optimize GEMM on MI200/300: 1. Add new blockwise gemm pipeline 2. Add irregular splitk intances * clang format + typo fix * Fix a bug * initial commit * Add more instances to irregular splitk * blkgemm pipeline v1~4 prototype * Sanity Checked. Known issue: 1. Poor performance of splitk 2. Register spill on blkgemmpipeline v3 * Sanity and Performance fix: 1. fix a bug related to sanity in grouped b2c mapping 2. fix a bug related to sanity and performance in splitk offset * Sanity and API update: 1. Remove prefetch stage 2. Fix valid check bug 3, Add first gemm_universal instance into ckProfiler * Add NN instances for gemm universal * 1. Add NT instances for gemm_universal 2. Fix a bug about Kpadding in gemm_universal * Fix a bug regarding padding Odd K number * remove kernel print * Fix KPadding bug... * Update safety check * another try to fix kpadding.. * Sanity checked * new instances.. * clang format+typo fix * remove clang format script's change * Add non-hotloop compile option * 1. Add fp16xfp8 example 2. pull packed convert f8 from pr1150 * Some miscs.. opt and fix * Add pipeline description docs * Split universal gemm instance library to cut profiler compiling time * uncomment cmakefile * Fix a bug caused by blockwise_gemm_pipe_v2 * reduce default splitk to 1 * Add 224x256x64 tile size * update, including: 1. Experiment pipeline 5~7 2. Optimization for pipeline 4 3. Organized instance library * temp save * temp save * Permuted lds layout, sanity and function checked * clang format * Move OOB check from RunRead to RunWrite, for better software pipeline. TODO: agpr spill when NN layout * clangformat * A/B splitpipe scheduler for v3 * Fix two bugs * bug fix * fix a bug in oob check * Example for mixed fp16_fp8 gemm * Clean experimental code blocks * Add mixed precision gemm into profiler * tempsave * optimize m/n major lds layout * Add RRR GEMM mixed precision instances * Optimize f8 matrix transpose * Add test_gemm_universal * A/B spilt schedule for blkpip v5 * Take ds_read2 into iglp scheduling scheme * format * fixed cmake * Add llvm-option into CI cmake flag --------- Co-authored-by: Jing Zhang <jizhan@amd.com>
49 lines
1.6 KiB
C++
49 lines
1.6 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2023, 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,
|
|
128, 256,
|
|
128, 16, 16,
|
|
16, 16,
|
|
4, 8,
|
|
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>,
|
|
2, 16, 16, 1,
|
|
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>,
|
|
2, 16, 16, 1,
|
|
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); }
|