OpenMP Offload Capabilities in the oneAPI HPC Toolkit
OpenMP provides portable, performant, and productive parallel programming interfaces for applications on a wide range of platforms and is one of the programming models offered in the oneAPI HPC Toolkit. This talk presents the key capabilities of the C/C++/Fortran compilers in oneAPI, especially those to exploit the Intel Xe GPUs to be in Aurora, the ALCF's forthcoming exascale system. Use cases of HPC applications from the Aurora Early Science Program will be discussed.
About the Speaker
Jeongnim Kim is a Principal Engineer in HPC organization of Cloud Enterprise Solution Group, where she focuses on Intel SW infrastructure advancement, HPC ecosystem development, and HPC-driven science discovery. She is an expert in computational physics, applied mathematics, and computer science, and has been developing parallel algorithms and HPC applications on generations of supercomputers. Her work has demonstrated the capability and advantage of Intel platforms for the advanced materials research and broad HPC areas. She is the architect of QMCPACK, a US-DOE flagship exascale application and an acceptance application for the Aurora exascale system.
About the Series
The Aurora Early Adopter webinar series is designed to help researchers and developers ramp up their efforts to optimize applications for the ALCF’s forthcoming exascale system. The interactive webinars will cover programming models, exascale technologies, and other tools available for testing and development work in preparation for Aurora. This webinar series is free and open to the public.