Enabling CUDA Memory Checker Feature
You can detect global memory addressing violations and misaligned global memory accesses by enabling the CUDA Memory Checker feature.
Enable this feature either in the UI or the CLI.
From the UI
In the UI, either:
*Select "Enable CUDA memory checking" in the Program Session dialog.
This dialog is available when you first launch a debugging session and also via the Process > Modify Arguments menu from within an existing session.
*From the Debug menu, choose “Enable CUDA memcheck”:
From the CLI
In the CLI, either:
*Pass the -cuda_memcheck option to the totalview command, for example:
totalview -cuda_memcheck
*Set the TV::cuda_memcheck CLI state variable to true. For example:
dset TV::cuda_memcheck true
Note that global memory violations and misaligned global memory accesses will be detected only while the CUDA thread is running. Detection will not happen when single-stepping the CUDA thread.