ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-04 05:31:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK_TILE] Grouped GEMM tile loop (#2146)

Browse Source 
* Add trait to use a persistent kernel and split the entrypoints in grouped gemm

* Some helper functions for persistent kernel case

* Get max occupancy grid using device properties

* Implement tile loop in main entry point to grouped gemm

* Enable GridSize() on device

* Handle offset tile index using real current block index

* Add persistent kernel choice to grouped gemm example

* Use a for-loop for iterating over the group

* Reduce VGPR spills by early-exit

* Enable persistent kernel choice in grouped_gemm example

* Add persistent kernel option to grouped_gemm test

* Fix formatting with remod.py

* Remove GridUpdateBlocks as blocks are now iteratively computed

* Add comment about VGPR spilling

* Fix formatting

* Use CK_TILE_HOST instead of __host__

* Enable all Row/Col combinations in grouped gemm unit test

* Add some KBatch=2 cases to grouped gemm tests

* Fix SplitK for grouped gemm

* Enable pipeline hotloop/tailnumber selection in-kernel for grouped gemm

* Add type traits

* Split examples to regular and tileloop

* Formatting

* Use hipExtStreamGetCUMask to get current active CUs for the given stream

* Align test and example kernel config, and disable validation for splitk repeats

* Remove debug options from CMakeLists.txt

* Separate the code paths for persistent/non-persistent in test

* Fix formatting

* Address review comments

---------

Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
This commit is contained in:
Sami Remes
2025-05-20 17:18:57 +03:00
committed by GitHub
parent c4929225f6
commit d1e6f0982d
15 changed files with 908 additions and 146 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
test/ck_tile/grouped_gemm/test_grouped_gemm.cpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
#include <tuple>
@@ -8,19 +8,27 @@
#include "ck_tile/host.hpp"
#include "test_grouped_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;
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;
using True = ck_tile::bool_constant<true>;
using False = ck_tile::bool_constant<false>;
// 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>
// ALayout, BLayout, CLayout, ADataType, BDataType, AccDataType, CDataType, Persistent
std::tuple< Row, Col, Row, F16, F16, F32, F16, True>,
std::tuple< Row, Col, Row, F16, F16, F32, F16, False>,
std::tuple< Row, Col, Row, F16, F16, F32, F16, True>,
std::tuple< Row, Col, Row, F16, F16, F32, F16, False>,
std::tuple< Col, Col, Row, F16, F16, F32, F16, True>,
std::tuple< Col, Col, Row, F16, F16, F32, F16, False>,
std::tuple< Row, Row, Row, F16, F16, F32, F16, True>,
std::tuple< Row, Row, Row, F16, F16, F32, F16, False>,
std::tuple< Col, Row, Row, F16, F16, F32, F16, True>,
std::tuple< Col, Row, Row, F16, F16, F32, F16, False>
>;
// clang-format on