mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 21:21:22 +00:00
39dc25a9b8
* Refactor universal gemm policy. * Adapt example to refactor changes. * Introduce static encoding pattern * Adding shuffled encoding patterns. * Fix err in reverse tuple. * Add transpose_tile2d * Small refactoring + doc * Enable reading on contiguous dimension in all layouts. * Transpose A/B register tile if needed for comp v3 pipeline. * Take contiguous dim size when calculating dram vector load size. * A/B smem pack size taken from WarpGemm attributes * Update B LDS layout and setup tile distribution pattern at class level. * Fix static assert. * Fix errors in examples. * Formatting & fix IsTranspose * Fix VectorSize & refactor. * Add error loging messages. * Fix VecLoadSize and TranspseC for mem pipeline. * Update unit-tests & disable mem pipeline. * Clang format * Update include/ck_tile/core/tensor/tile_window.hpp Co-authored-by: jakpiase <jakub.piasecki@amd.com> * Fix compilation and reviewers comments. * Refactor unit-test. Fallback to non-universal gemm. Need to use GemmPipelineAGmemBGmemCRegV1 for now, since GemmKernel is now supporting also non-K major vector reads. --------- Co-authored-by: jakpiase <jakub.piasecki@amd.com>
60 lines
2.2 KiB
C++
60 lines
2.2 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include <string>
|
|
|
|
#include "ck_tile/core.hpp"
|
|
#include "ck_tile/host/kernel_launch.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/grouped_gemm_kernel.hpp"
|
|
|
|
template <typename DataType>
|
|
struct GemmBasicTypeConfig;
|
|
|
|
template <>
|
|
struct GemmBasicTypeConfig<ck_tile::half_t>
|
|
{
|
|
using ADataType = ck_tile::half_t;
|
|
using BDataType = ck_tile::half_t;
|
|
using CDataType = ck_tile::half_t;
|
|
using AccDataType = float;
|
|
};
|
|
|
|
using Types = GemmBasicTypeConfig<ck_tile::half_t>;
|
|
|
|
// Specific type aliases for easy access
|
|
using ADataType = Types::ADataType;
|
|
using BDataType = Types::BDataType;
|
|
using AccDataType = Types::AccDataType;
|
|
using CDataType = Types::CDataType;
|
|
|
|
using grouped_gemm_kargs = ck_tile::GroupedGemmHostArgs;
|
|
|
|
auto create_args(int argc, char* argv[])
|
|
{
|
|
ck_tile::ArgParser arg_parser;
|
|
arg_parser.insert("Ms", "", "M dimensions - empty by default.")
|
|
.insert("Ns", "", "N dimensions - empty by default.")
|
|
.insert("Ks", "", "K dimensions - empty by default.")
|
|
.insert("stride_As", "", "Tensor A strides - it is empty by default.")
|
|
.insert("stride_Bs", "", "Tensor B strides - it is empty by default.")
|
|
.insert("stride_Cs", "", "Tensor C strides - it is empty by default.")
|
|
.insert("a_layout", "R", "A tensor data layout - Row by default.")
|
|
.insert("b_layout", "C", "B tensor data layout - Row by default.")
|
|
.insert("c_layout", "R", "C tensor data layout - Row by default.")
|
|
.insert("validate", "1", "0. No validation, 1. Validation on CPU.")
|
|
.insert("warmup", "10", "number of iterations before benchmark the kernel.")
|
|
.insert("repeat", "100", "number of iterations to benchmark the kernel.")
|
|
.insert("group_count", "16", "group count.");
|
|
|
|
bool result = arg_parser.parse(argc, argv);
|
|
return std::make_tuple(result, arg_parser);
|
|
}
|
|
|
|
std::size_t get_workspace_size(const std::vector<grouped_gemm_kargs>& gemm_descs);
|
|
|
|
float grouped_gemm(const std::vector<grouped_gemm_kargs>& gemm_descs,
|
|
const ck_tile::stream_config& s,
|
|
void* p_workspace_);
|