GPU Profiling (Performance Profile: Omniperf)

AMD will present “GPU Profiling (Performance Timelines: Rocprof and Omnitrace)” on Monday, October 16, 2023. This event is part of the HIP Training Series and will be presented by Ian Bogle and Cole Ramos of AMD.

Collecting and presenting data on the performance of kernels can help identify key optimizations. AMD’s rocprof profiler collects the basic hardware counter data to enable this profiling. Omniperf adds to this hardware counter data many derived metrics and presents it in a form that application developers can use to tune their kernels and applications for top performance. The kernel profiling data can help determine which kernels to address by showing which kernels take the most time. Performance can be visualized on a roofline plot and compared against the peak possible performance for the hardware. Hands-on exercises will generate performance profiles, implement optimizations and then generate a performance report that shows the differences between the optimized and unoptimized performance profiles.

Participation in the hands-on portion of each session will be limited to participants who already have access to OLCF’s Frontier or NERSC’s Perlmutter.

The Q&A for all the sessions will be in this Google doc

If you have any questions, please contact Subil Abraham (abrahams@ornl.gov)