What does running NSight change about the environment?

When my CUDA code runs w/o NSight, I get the “Driver has stopped responding and was recovered” message and the program hangs. Obviously a memory boundary issue, which I am trying to track down.

When I run it with NSight and memory checking enabled, it finishes normally with no error messages.

This is really frustrating. So I wonder, what does NSight change that would allow memory violations w/o affecting the program exec?

And what kind of memory violations skate by w/o being detected by “CUDA Memory Checker”?

I had this problem with the previous version of NSight and hoped that 4.0 would fix it, but no joy.

It occurred to me that instead of a memory violation, I may be seeing the result of processing time exceeding a limit established by the display driver, even though I’m not using the CUDA card for display. Driver version is 335.23

Does NSight disable the processing timeout limit?

Is there a setting in the registry to disable the limit?

I’ve searched for a registry entry for that before and did not find it.

Hi robosmith,

You can modify the timeout in the Nsight monitor setting, you have to reboot.: