ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-21 13:29:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '9fcc1ee9fd9730efd865f530afde505f2556954d' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-08-18 17:12:50 +00:00
parent d436787ed0
commit 68b20e1d4f
113 changed files with 610 additions and 531 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
test/ck_tile/reduce/test_reduce2d.cpp
View File

@@ -82,18 +82,18 @@ class TestCkTileReduce : public ::testing::Test
throw std::runtime_error("Wrong! Arguments not supported!\n");
}
ck_tile::launch_kernel(ck_tile::stream_config{nullptr, false, 0},
ck_tile::make_kernel<kBlockSize, kBlockPerCu>(
Kernel{},
kGridSize,
kBlockSize,
0,
static_cast<XDataType*>(d_x_mem.GetDeviceBuffer()),
static_cast<YDataType*>(d_y_mem.GetDeviceBuffer()),
input_shape_tuple,
input_strides_tuple,
kept_dims,
reduce_dims));
ck_tile::launch_kernel(
ck_tile::stream_config{nullptr, false, 0},
ck_tile::make_kernel<kBlockPerCu>(Kernel{},
kGridSize,
kBlockSize,
0,
static_cast<XDataType*>(d_x_mem.GetDeviceBuffer()),
static_cast<YDataType*>(d_y_mem.GetDeviceBuffer()),
input_shape_tuple,
input_strides_tuple,
kept_dims,
reduce_dims));
// Get results back
d_y_mem.FromDevice(h_y.data());