Early Successes in Porting HPC Workloads to Intel® GPUs

Argonne National Laboratory began deploying to the Aurora Exascale supercomputer, which is powered by Intel® Data Center GPU Max Series (formerly code named Ponte Vecchio) and 4th generation Intel® Xeon® Scalable processors (formerly code named Sapphire Rapids). Get an overview of the Aurora system hardware and software, and the progress for preparing complex HPC applications to run on it.

A diverse portfolio of applications is being developed to perform novel leading-edge science on Aurora, including over 40 applications from the Exascale Computing project and the Aurora Early Science project. The progress in developing, porting, and optimizing these applications for Aurora are presented.

Speaker

JaeHyuk Kwack is a member of the Performance Engineering Team at the Argonne Leadership Computing Facility. He is responsible for performance tools and ensuring the readiness of several major scientific applications for performant use on future exascale systems for the US Department of Energy.