mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 02:02:46 +00:00
fa0b543b5e
* Add optimized blockwise gemm using ck wrapper
* Add basic gemm example
* Update docs
* Add tutorial for gemm using ck wrapper
* Add perf note
* edits
* Fix cmake
* Fixes
---------
Co-authored-by: Lisa Delaney <lisa.delaney@amd.com>
[ROCm/composable_kernel commit: 1e73adbc28]
15 lines
321 B
C++
15 lines
321 B
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include "ck/ck.hpp"
|
|
|
|
namespace ck {
|
|
namespace wrapper {
|
|
|
|
#define __CK_WRAPPER_LAUNCH_BOUNDS__ __launch_bounds__(CK_MAX_THREAD_PER_BLOCK, CK_MIN_BLOCK_PER_CU)
|
|
|
|
} // namespace wrapper
|
|
} // namespace ck
|