Skip to content

Fixes #57

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
psychocoderHPC merged 1 commit into from
Mar 6, 2026
Merged

Fixes #57

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions cuda_memtest.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -575,12 +575,12 @@ main(int argc, char** argv)
exit(ERR_BAD_STATE);
}

active_update_temperature = 0;

for(i=0;i < num_gpus;i++){
pthread_join(pid[i], NULL);
}

active_update_temperature = 0;

printf("main thread: Program exits\n");

return 0;
Expand Down
13 changes: 12 additions & 1 deletion misc.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,13 +8,24 @@ void update_temperature(void)
unsigned int deviceCount;
NVML_CHECK(nvmlDeviceGetCount( &deviceCount ));

for( unsigned int devIdx = 0; devIdx < deviceCount; ++devIdx )
unsigned int monitoredCount = (deviceCount > MAX_GPU_NUM) ? MAX_GPU_NUM : deviceCount;
if (deviceCount > MAX_GPU_NUM) {
fprintf(stderr, "WARNING: Found %u GPUs, but MAX_GPU_NUM is %u. Clamping to maximum supported.\n", deviceCount, MAX_GPU_NUM);
}

for( unsigned int devIdx = 0; devIdx < monitoredCount; ++devIdx )
{
nvmlDevice_t devHandle;
NVML_CHECK(nvmlDeviceGetHandleByIndex( devIdx, &devHandle ));

unsigned int devTemperature;
#if (NVML_API_VERSION >= 13)
nvmlTemperature_t temperature = {nvmlTemperature_v1, NVML_TEMPERATURE_GPU};
NVML_CHECK(nvmlDeviceGetTemperatureV( devHandle, &temperature ));
devTemperature = temperature.temperature;
#else
NVML_CHECK(nvmlDeviceGetTemperature( devHandle, NVML_TEMPERATURE_GPU, &devTemperature ));
#endif
gpu_temp[devIdx] = devTemperature;

DEBUG_PRINTF("temperature updated: (gpu %d) %d \n", devIdx, devTemperature);
Expand Down