The International Conference for High Performance Computing, Networking, Storage, and Analysis
The International Conference for High Performance Computing, Networking, Storage, and Analysis
Authors: Nicholas Malaya (Advanced Micro Devices (AMD) Inc); Bronson Messer (Oak Ridge National Laboratory (ORNL)); Joseph Glenski (Hewlett Packard Enterprise (HPE)); Antigoni Georgiadou, Justin Lietz, and Kalyana Gottiparthi (Oak Ridge National Laboratory (ORNL)); Marc Day (National Renewable Energy Laboratory (NREL)); Jackie Chen (Sandia National Laboratories); Jon Rood and Lucas Esclapez (National Renewable Energy Laboratory (NREL)); James White III (Hewlett Packard Enterprise (HPE)); Gustav R. Jansen (Oak Ridge National Laboratory (ORNL)); Nicholas Curtis (AMD Research); Stephen Nichols (Oak Ridge National Laboratory (ORNL)); Jakub Kurzak, Noel Chalmers, Chip Freitag, Paul Bauman, and Alessandro Fanfarillo (AMD Research); Reuben D. Budiardja and Thomas Papatheodore (Oak Ridge National Laboratory (ORNL)); Nicholas Frontiere (Argonne National Laboratory (ANL)); Damon McDougall (AMD Research); Matthew Norman, Sarat Sreepathi, Philip Roth, and Dmytro Bykov (Oak Ridge National Laboratory (ORNL)); Noah Wolfe and Paul Mullowney (AMD Research); Markus Eisenbach (Oak Ridge National Laboratory (ORNL)); Marc T. Henry de Frahan (National Renewable Energy Laboratory (NREL)); and Wayne Joubert (Oak Ridge National Laboratory (ORNL))
Abstract: The advent of exascale computing invites an assessment of existing best practices for developing application readiness on the world’s largest supercomputers. This work details observations from the last four years in preparing scientific applications to run on the Oak Ridge Leadership Computing Facility's (OLCF) Frontier system. This paper addresses a range of topics in software including programmability, tuning, and portability considerations that are key to moving applications from existing systems to future installations. A set of representative workloads provides case studies for general system and software testing. We evaluate the use of early access systems for development across several generations of hardware. Finally, we discuss how best practices were identified and disseminated to the community through a wide range of activities including user-guides and trainings. We conclude with recommendations for ensuring application readiness on future leadership computing systems.
Back to Technical Papers Archive Listing