Closed msiglreith closed 5 years ago
Hi @msiglreith
The current performance counter architecture of AMD GPUs does not allow performance counter monitoring of individual wavefronts. RGP uses a different performance monitoring mechanism inside AMD GPUs that is not the same as normal performance counters. GPA is, I believe, designed specifically for gathering performance counters.
@jlgreathouse thanks for the response! I assume there isn't public information (API) regarding the performance monitoring used by RGP, is it?
Unfortunately, no, not at this time.
Hi, first of all thanks for publishing this library!
Looking trough the API I'm wondering if there is the possibility to sample workloads on a smaller granularity? If I understand it correctlt, it's currently only possible to get samples per draw/dispatch call for example but not possible to get information about the individual wavefronts in a similiar fashion and granularity as the Radeon GPU profiler (wavefront occupancy)?
Cheers