ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-02 20:51:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Added wmma support for gemm quantization: (#2841)

Browse Source 
- profiler for gemm quantization for DL/XDL
- tests for gemm quantization for DL/XDL
- implementation for gemm quantization for WMMA
- profiler/tests for gemm qunatization for WMMA

Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
This commit is contained in:
Wojciech Laskowski
2025-09-17 01:23:29 +02:00
committed by GitHub
parent 2723dbd332
commit f97b2a3f5d
21 changed files with 1167 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
test/quantization/gemm/test_gemm_quantization.cpp Normal file
View File

@@ -0,0 +1,40 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
#include "gtest/gtest.h"
#include "ck/ck.hpp"
#include "profiler/profile_gemm_quantization_impl.hpp"
#include "test_gemm_quantization_util.hpp"
using I8 = int8_t;
using I32 = int32_t;
using Row = ck::tensor_layout::gemm::RowMajor;
using Col = ck::tensor_layout::gemm::ColumnMajor;
template <typename Tuple>
class TestGemmQuantization : public ck::test::TestGemmQuantizationCommon<Tuple>
{
protected:
using ProfileCall = bool (*const)(int, int, bool, bool, int, int, int, int, int, int, float);
ProfileCall GetImpl() override
{
return &ck::profiler::profile_gemm_quantization_impl<
typename ck::test::TestGemmQuantizationCommon<Tuple>::ADataType,
typename ck::test::TestGemmQuantizationCommon<Tuple>::BDataType,
typename ck::test::TestGemmQuantizationCommon<Tuple>::AccDataType,
typename ck::test::TestGemmQuantizationCommon<Tuple>::EDataType,
typename ck::test::TestGemmQuantizationCommon<Tuple>::ALayout,
typename ck::test::TestGemmQuantizationCommon<Tuple>::BLayout,
typename ck::test::TestGemmQuantizationCommon<Tuple>::ELayout>;
}
};
using KernelTypes = ::testing::Types<std::tuple<I8, I8, I32, I8, Row, Row, Row>,
std::tuple<I8, I8, I32, I8, Row, Col, Row>,
std::tuple<I8, I8, I32, I8, Col, Row, Row>,
std::tuple<I8, I8, I32, I8, Col, Col, Row>>;
TYPED_TEST_SUITE(TestGemmQuantization, KernelTypes);
#include "test_gemm_quantization_ut_cases.inc"