I am using a tool named HPCToolkit to measure the performance of all loops in the program. It looks like it only shows whats causing the performance bottlenecks and not the profiling information for the entire source. Is my understanding correct?
I am using a tool named HPCToolkit to measure the performance of all loops in the program. It looks like it only shows whats causing the performance bottlenecks and not the profiling information for the entire source. Is my understanding correct?