You can detect global memory addressing violations and misaligned global memory accesses by enabling the CUDA MemoryChecker feature.
To enable the feature, use one of the following:
• Select "Enable CUDA memory checking" from the Startup Parameters dialog box in TotalView, as shown in Figure 275.
Figure 275 – Enabling CUDA memory checking from TotalView Startup Parameters
• Pass the -cuda_memcheck option to the totalview command.
• 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.
