leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 26 Packages Projects Releases Wiki Activity

v3.9 update (#2213)

Browse Source 
Co-authored-by: yuzhai <yuzhai@nvidia.com>
This commit is contained in:
Yujia Zhai
2025-04-03 02:10:16 -04:00
committed by GitHub
co-authored by yuzhai
parent 6f4921858b
commit 79fc51f4b8
72 changed files with 19875 additions and 459 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/unit/common/filter_architecture.cpp
+4 -2
View File
@@ -28,7 +28,6 @@
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
**************************************************************************************************/
#include <cuda_runtime_api.h>
#include "cutlass_unit_test.h"
@@ -59,7 +58,10 @@ std::ostream &operator<<(std::ostream &out, cudaDeviceProp const &deviceProperti
int deviceMajorMinor = deviceProperties.major * 10 + deviceProperties.minor;
if (deviceMajorMinor) {
int32_t clock_MHz = deviceProperties.clockRate / 1000;
int32_t clock_MHz;
int32_t clock_KHz;
cudaDeviceGetAttribute(&clock_KHz, cudaDevAttrClockRate, 0);
clock_MHz = clock_KHz / 1000;
out << "GPU(compute_"
<< deviceMajorMinor << ", "
<< deviceProperties.multiProcessorCount << " SMs @ " << clock_MHz << " MHz)";