GPU Profiling (Performance Timelines: Rocprof and Omnitrace)

AMD will present “GPU Profiling (Performance Timelines: Rocprof and Omnitrace)” on Monday, October 2, 2023. This event is part of the HIP Training Series and will be presented by Suyash Tandon of AMD.

Application developers have found that viewing performance data as a timeline of events and communications can yield important insights. We’ll look at how to use the AMD rocprof and Omnitrace tools to present performance timelines and the kind of data that can be collected and shown. Rocprof enables the collection of hardware counter data to display on the timeline. Omnitrace adds to the GPU hardware data many other data sources on the GPU and the CPU. Timeline analysis will help to understand the performance of streams on the GPU. And it becomes critical to understanding and tune the tight cooperation between GPU and CPU in many applications. Hands-on exercises will run the analysis tools and generate timelines to analyze.

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)