GPU Porting of an HPC Application Using Intel® oneAPI

oneAPI is a cross-industry, open, standards-based unified programming model that delivers a common developer experience across accelerator architectures for faster application performance, more productivity, and greater innovation. Intel® oneAPI Toolkits include implementations of the oneAPI specification along with complementary tools to develop and deploy applications and solutions across Intel® CPU and XPU architectures.

This training shall demonstrate the use of Intel® oneAPI tools in the context of an HPC application. Starting off from a traditional CPU enabled HPC application, we shall showcase strategies to select prospective code regions for offload to GPUs, make necessary code changes and deploy it in a heterogeneous XPU environment. Some optimizations to increase performance will also be demonstrated. This presentation will end with a demo on a Linux based machine.