mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-04 13:41:24 +00:00
24d996aae1
* CK-Tile GEMM with memory bound pipeline. * Memory bound gemm pipeline. * Fix not closed namespace. * Block gemm mem pipeline draft. * Do not use ck_tile:: within ck_tile namespace. * Refactoring & Move Layout info to pipeline problem. * Get hot loop and TailNum information before lunching kernel. * Fixes in pipeline. * Add comment to load_tile_raw and change variable naming style. * Few small changes & formatting. * Do not use macro. * Add gtests. * Use AccDataType for Output of MFMA instruction. * Formatting. * Refactor gemm examples. * Switch over to current block gemm. * Use currently available pipeline policy. * Refactoring and review comment.s * Fixes after merge. * Add missing include. * Add load tile overload which accepts output tensor as parameter. * This give 8% perf boost at the cost of using more registers. * Rename example. * Small changes. * Fix compilation err and lower K. * Support different layouts for A/B * Fix vector size for different layouts. * Rename Alignment into VectorSize * Unblock tests.
30 lines
1008 B
C++
30 lines
1008 B
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#include <tuple>
|
|
|
|
#include "gtest/gtest.h"
|
|
|
|
#include "ck_tile/host.hpp"
|
|
#include "test_gemm_mem_pipeline_util.hpp"
|
|
|
|
using F16 = ck_tile::half_t;
|
|
using F32 = float;
|
|
|
|
using Row = ck_tile::tensor_layout::gemm::RowMajor;
|
|
using Col = ck_tile::tensor_layout::gemm::ColumnMajor;
|
|
|
|
// clang-format off
|
|
using KernelTypes = ::testing::Types<
|
|
// ALayout, BLayout, CLayout, ADataType, BDataType, AccDataType, CDataType
|
|
std::tuple< Row, Col, Row, F16, F16, F32, F16>,
|
|
std::tuple< Col, Row, Row, F16, F16, F32, F16>,
|
|
std::tuple< Row, Row, Row, F16, F16, F32, F16>,
|
|
std::tuple< Col, Col, Row, F16, F16, F32, F16>
|
|
>;
|
|
// clang-format on
|
|
|
|
TYPED_TEST_SUITE(TestCkTileGemmMemPipeline, KernelTypes);
|
|
|
|
#include "test_gemm_mem_pipeline_ut_cases.inc"
|