ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 18:17:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit 'b60af5bde965a2bb007bb582f7836b43ca647b81' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-09-30 16:14:10 +00:00
parent 631a25de61
commit ee9718a427
115 changed files with 2849 additions and 756 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
example/45_elementwise_normalization/elementwise_layernorm_blockwise.cpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#include <iostream>
#include <numeric>
@@ -98,8 +98,23 @@ int main(int argc, char* argv[])
exit(0);
}
ck::index_t M = 48 * 256;
ck::index_t N = 1024;
ck::index_t M = 48 * 256;
ck::index_t N = 1024;
if(argc == 1)
{
// use default case
}
else if(argc == 3)
{
M = std::stoi(argv[1]);
N = std::stoi(argv[2]);
}
else
{
std::cerr << "arg1 to 2: M, N" << std::endl;
return 1;
}
ck::index_t Stride = N;
auto f_host_tensor_descriptor1d = [](std::size_t len, std::size_t stride) {