NASP/cuda-samples
85
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2026-10-25 22:28:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

Bug 5196362, 5184356, 5212196, 5214258 and 5214259: Update sameples for CUDA13.0 API changes

Browse Source
This commit is contained in:
shawnz
2025-04-10 18:27:18 +08:00
parent 278f4adbd2
commit 02fdb070ad
27 changed files with 181 additions and 116 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
Samples/0_Introduction/simpleHyperQ/simpleHyperQ.cu
View File

@@ -127,6 +127,10 @@ int main(int argc, char **argv)
checkCudaErrors(cudaGetDevice(&cuda_device));
checkCudaErrors(cudaGetDeviceProperties(&deviceProp, cuda_device));
// Get device clock rate
int clockRate;
checkCudaErrors(cudaDeviceGetAttribute(&clockRate, cudaDevAttrClockRate, cuda_device));
// HyperQ is available in devices of Compute Capability 3.5 and higher
if (deviceProp.major < 3 || (deviceProp.major == 3 && deviceProp.minor < 5)) {
if (deviceProp.concurrentKernels == 0) {
@@ -170,9 +174,9 @@ int main(int argc, char **argv)
#if defined(__arm__) || defined(__aarch64__)
// the kernel takes more time than the channel reset time on arm archs, so to
// prevent hangs reduce time_clocks.
clock_t time_clocks = (clock_t)(kernel_time * (deviceProp.clockRate / 100));
clock_t time_clocks = (clock_t)(kernel_time * (clockRate / 100));
#else
clock_t time_clocks = (clock_t)(kernel_time * deviceProp.clockRate);
clock_t time_clocks = (clock_t)(kernel_time * clockRate);
#endif
clock_t total_clocks = 0;