In this video from the Argonne Training Program on Extreme-Scale Computing 2019, Howard Pritchard from LANL and Simon Hammond from Sandia present: NNSA Explorations: ARM for Supercomputing.
As part of the Vanguard program, the Arm-based Astra system is used by the National Nuclear Security Administration (NNSA) to run advanced modeling and simulation workloads for addressing areas such as national security, energy and science.
By introducing Arm processors with the HPE Apollo 70, a purpose-built HPC architecture, we are bringing powerful elements, like optimal memory performance and greater density, to supercomputers that existing technologies in the market cannot match,” said Mike Vildibill, vice president, Advanced Technologies Group, HPE. “Sandia National Laboratories has been an active partner in leveraging our Arm-based platform since its early design, and featuring it in the deployment of the world’s largest Arm-based supercomputer, is a strategic investment for the DOE and the industry as a whole as we race toward achieving exascale computing.”
The Argonne Training Program on Extreme-Scale Computing (ATPESC) provides intensive, two weeks of training on the key skills, approaches, and tools to design, implement, and execute computational science and engineering applications on current high-end computing systems and the leadership-class computing systems of the future. As a bridge to that future, this two-week program fills the gap that exists in the training computational scientists typically receive through formal education or other shorter courses. With around 70 participants accepted each year, admission to the ATPESC program is highly competitive. ATPESC is part of the Exascale Computing Project, a collaborative effort of the DOE Office of Science and the National Nuclear Security Administration.
Howard Pritchard is a Research Scientist at LANL and serves as the team lead for LANL’s HPC application readiness team. His areas of research include investigation of the performance of mission-critical applications on future systems, with a focus on architectures promising efficient computing at scale. Another area of his research is development of extensions to the MPI Standard as part of the Exascale Computing Project, as well as development and support of the Open MPI implementation of MPI. He is also active in the support and development of networking middleware software including OpenUCX , OFI libfabric, and OpenSHMEM.
Simon Hammond is a Principal Scientist in the Scalable Computer Architectures group at Sandia National Laboratories. He has worked in the group for eight years and served in multiple capacities as a technical leader for Sandia’s Application Performance Team and the lead of its Hardware Architecture Simulation group. In 2017, he joined the Exascale Computing Project (ECP) as a technical representative in the PathForward research program – to date, the largest computer hardware research project sponsored by the Department of Energy – and the lead of the ECP’s Hardware Evaluation team. Simon was the application and performance led for Sandia’s Astra platform, the world’s first petascale Arm-based supercomputer. In that capacity he led Sandia’s initial evaluation of Arm technologies including compiler toolchains, profilers, debuggers and scalable communication runtimes. Prior to joining Sandia, Simon studied for his PhD at the University of Warwick, England and was a visiting researcher at the United Kingdom’s Atomic Weapons Establishment (AWE).
In related news, the Arm HPC User Group takes place Nov. 18 at SC19 in Denver.
