Porting Applications to HIP

AMD will present “Porting Applications to HIP” on Monday, August 28, 2023. This event is part of the HIP Training Series and will be presented by Maria del Carmen Ruiz Varela of AMD.

Porting applications from CUDA to HIP can transform an application to be portable across both Nvidia and AMD GPU hardware. With the tools from AMD, the process of “hipifying” code in many cases is automated with just a small amount of manual work required. This talk will review the AMD porting tools and how to use them. Portability for other GPU programming languages will also be briefly discussed. A demonstration of porting the DOE mini-app, Pennant, will show some both the ease of the porting process and some of the complexity that might be encountered. The hands-on exercises will be to port the same mini-app, but this time do it with a portable makefile or cmake build system that will work on both AMD and Nvidia GPU systems.

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)