Join us on June 21 for a webinar that will provide an overview of ALCF's exascale system, Aurora. The talk will focus on the Aurora exascale system architecture, including elements of the Intel CPU Max (codename “Sapphire Rapids” with HBM) and GPU Max (codename “Ponte Vecchio”) components, software stack available, and OneAPI.
OneAPI is a project with the goal of supporting development of applications that can simultaneously utilize all compute devices in a system regardless of vendor or architecture. In this webinar, the speakers will also discuss OneAPI vision, its technology and open source projects, its role and impact in the industry, its new independence from Intel, Intel's continued support of the standard, and its relationship with SYCL.
Olivier Franza is the Principal Investigator and chief architect of the Aurora supercomputer. He leads Intel’s Advanced Supercomputing System Architecture team in the Datacenter and AI (DCAI) group. With 25 years of professional experience, he has been responsible for technology pathfinding and design execution on several Itanium and Xeon products since joining Intel from Digital Equipment Corporation. He received a “diplôme d'ingénieur” degree from CenraleSupélec (France), a “doctorat en sciences” degree from Université Paris-Saclay (France), a Ph.D. degree from the University of Illinois at Urbana-Champaign (USA), as well as an MBA in Entrepreneurship from Babson College (USA).
James Reinders is an engineer at Intel, with parallel computing experience spanning four decades, focused on enabling parallel programming in a heterogeneous world. James is currently focused on the DPC++ project (SYCL for LLVM), and the oneAPI initiative (delivering APIs spanning compute devices of many types from many vendors). James is an author/co-author/editor of ten technical books related to parallel programming; his latest book is about SYCL (free download: https://www.apress.com/book/9781484255735). He has had the great fortune to help make key contributions to two of the world's fastest computers (#1 on Top500 list) as well as many other supercomputers, and software developer tools. James consistently enjoys writing, teaching, programming, and consulting in areas related to parallel computing (HPC and AI).
Xinmin Tian is an Intel Fellow and Chief Compiler Performance Architect at Intel Corporation. He serves as an Intel tech lead for Aurora Compiler projects and Intel's representative on the OpenMP Architecture Review Board (ARB). Xinmin focuses on LLVM-based OpenMP offloading, SYCL/DPC++ compiler optimizations, and tuning HPC/AI application performance. He holds 27 U.S. patents, has published over 60 technical papers, and co-authored two books in his field.
