mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-19 22:39:03 +00:00
70e4eb567f
* Add license header. * Reduce number of logged output. Add constant initialization. * Add functional tests for grouped_gemm with different kbatch value. * Add debug log informations + remove unused code. * Don't pass kbatch to CalculateKPadded. * Turn on logging in grouped gemm and gemm splitk profiler * Debug: limit number of test cases to run; * Log more information and initialize with constant value. * Turn on DEBUG_LOG * Add more debug log informations. * Limit the number of instances to compile. * Use GridwiseGemmPipeline * Use KBatch to calculate K0 * Multiple DebugLog messages. * Unit tests for multiple KBatch values. * Refactoring * Disable logging * extract out of if statement KBatch update. * Uncomment instances. * Disable DebugLog. * Use Kbatch when calculate KPadded. * Fix CGridDesc padding. * Use available helper functions. * Uncomment code commented for debuggin. * Remove unnecessary debug log messages. * Uncomment previously commented code for debug purposes. * Add KBatch info to profiler output summary log. * Add gtests for gemm splitk using ckProfiler API. * Add more test-cases for different data layout. * Add more test cases for gemm splitk * Remove old test. * Unit tests for MKNK ggemm interface. * Fix and add more unit-tests. * Constepxr everything! * Increase error threshold for fp16 and splitk. Since we're using fp16 atomic add for splitk there's a known precision loss. --------- Co-authored-by: Adam Osewski <aosewski@amd.com> Co-authored-by: zjing14 <zhangjing14@gmail.com>
35 lines
1.4 KiB
C++
35 lines
1.4 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#include <tuple>
|
|
#include <vector>
|
|
|
|
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
|
|
#include "ck/utility/data_type.hpp"
|
|
|
|
#include "gtest/gtest.h"
|
|
#include "test_grouped_gemm_util.hpp"
|
|
|
|
using F16 = ck::half_t;
|
|
using Row = ck::tensor_layout::gemm::RowMajor;
|
|
using Col = ck::tensor_layout::gemm::ColumnMajor;
|
|
|
|
using RRR_F16_F16_F16 = ck::test::TestGroupedGemm<std::tuple<Row, Row, Row, F16, F16, F16>>;
|
|
using RCR_F16_F16_F16 = ck::test::TestGroupedGemm<std::tuple<Row, Col, Row, F16, F16, F16>>;
|
|
|
|
using RRR_F16_F16_F16_LargeK = ck::test::TestGroupedGemm<std::tuple<Row, Row, Row, F16, F16, F16>>;
|
|
using RCR_F16_F16_F16_LargeK = ck::test::TestGroupedGemm<std::tuple<Row, Col, Row, F16, F16, F16>>;
|
|
|
|
const std::vector<int> KBATCH{1, 2, 3, 5, 8};
|
|
|
|
INSTANTIATE_TEST_SUITE_P(TestGroupedGemm_splitk_MK_KN, RRR_F16_F16_F16, testing::ValuesIn(KBATCH));
|
|
INSTANTIATE_TEST_SUITE_P(TestGroupedGemm_splitk_MK_NK, RCR_F16_F16_F16, testing::ValuesIn(KBATCH));
|
|
INSTANTIATE_TEST_SUITE_P(TestGroupedGemm_splitk_LargeK_MK_KN,
|
|
RRR_F16_F16_F16_LargeK,
|
|
testing::Values(32, 64));
|
|
INSTANTIATE_TEST_SUITE_P(TestGroupedGemm_splitk_LargeK_MK_NK,
|
|
RCR_F16_F16_F16_LargeK,
|
|
testing::Values(32, 64));
|
|
|
|
#include "test_grouped_gemm_ut_cases.inc"
|