ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-20 04:49:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Implement direct loads split-K GEMM kernel (#1137)

Browse Source 
* WIP: Implement direct loads split-K GEMM kernel

* Clean the review

---------

Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com>

[ROCm/composable_kernel commit: 6951858221]
This commit is contained in:
Bartlomiej Wroblewski
2024-02-07 01:08:34 +01:00
committed by GitHub
parent 0dcd795390
commit c4cc7d0b84
9 changed files with 1614 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
library/include/ck/library/tensor_operation_instance/gpu/gemm_splitk.hpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
@@ -36,6 +36,11 @@ void add_device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instances(
std::vector<std::unique_ptr<
DeviceGemmSplitK<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
void add_device_gemm_xdl_splitk_lds_direct_load_f16_f16_f16_mk_nk_mn_instances(
std::vector<std::unique_ptr<
DeviceGemmSplitK<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
instances);
#endif
#ifdef CK_ENABLE_FP32
void add_device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instances(
@@ -192,6 +197,7 @@ struct DeviceOperationInstanceFactory<
is_same_v<CLayout, Row>)
{
add_device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instances(op_ptrs);
add_device_gemm_xdl_splitk_lds_direct_load_f16_f16_f16_mk_nk_mn_instances(op_ptrs);
}
else if constexpr(is_same_v<ALayout, Col> && is_same_v<BLayout, Row> &&
is_same_v<CLayout, Row>)