mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-15 10:37:44 +00:00
89093ac431
* 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>
[ROCm/composable_kernel commit: 39dc25a9b8]
30 lines
1003 B
C++
30 lines
1003 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_batched_gemm_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, Row, Row, F16, F16, F32, F16>,
|
|
//std::tuple< Col, Row, Row, F16, F16, F32, F16>,
|
|
std::tuple< Row, Col, Row, F16, F16, F32, F16>//,
|
|
//std::tuple< Col, Col, Row, F16, F16, F32, F16>
|
|
>;
|
|
// clang-format on
|
|
|
|
TYPED_TEST_SUITE(TestCkTileBatchedGemm, KernelTypes);
|
|
|
|
#include "test_batched_gemm_ut_cases.inc"
|