ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-18 03:49:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '4d629cd2b0bb0b4b210881be0db398bcd382f444' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-11-14 02:43:22 +00:00
parent a96aded2b1
commit 897c2bd422
7 changed files with 223 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
example/ck_tile/18_flatmm/flatmm_basic.cpp
View File

@@ -47,7 +47,7 @@ static constexpr inline auto is_row_major(Layout layout_)
// mfma_type, 0:32x32, 1:16x16
template <typename FlatmmConfig, typename T>
auto shuffle_b(const ck_tile::HostTensor<T>& t)
auto shuffle_b_v0(const ck_tile::HostTensor<T>& t)
{
assert(t.get_lengths().size() == 2);
int n_ = t.get_lengths()[1];

2
example/ck_tile/18_flatmm/run_flatmm_example.inc
View File

@@ -103,7 +103,7 @@ int run_flatmm_example_with_layouts(int argc,
}
else
{
return shuffle_b<FlatmmConfig>(b_origin_host);
return shuffle_b_v0<FlatmmConfig>(b_origin_host);
}
}();
ck_tile::DeviceMem b_shuffle_dev_buf(b_shuffle_host.get_element_space_size_in_bytes());