What Will the Grace Hopper-Powered Jupiter Supercomputer Bring for Sparse Linear Algebra?

Submitted by webmaster on

TitleWhat Will the Grace Hopper-Powered Jupiter Supercomputer Bring for Sparse Linear Algebra?
Publication TypeConference Paper
Year of Publication2026
AuthorsTsai, Y-H., M. Bode, and H. Anzt
Conference NameSCA/HPCAsia 2026: Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region
Date Published2026-01
PublisherACM
Conference LocationOsaka, Japan
ISBN Number9798400720673
KeywordsComputing methodologies, Distributed computing methodologies, Parallel computing methodologies
Abstract

The first exascale supercomputer in Europe, JUPITER, is currently being built using the NVIDIA Grace Hopper superchips as main building blocks. JUPITER is designed to provide computing power for both data-driven (AI) workloads and numerics-based simulation workloads. For both workload types, and particularly for PDE-based simulations, high-performance sparse linear algebra operations are crucial. In this paper, we analyze the performance levels that sparse linear algebra operations can achieve on the JUPITER supercomputer and identify algorithmic modifications that can improve performance by acknowledging the Grace Hopper architecture.
URLhttps://dl.acm.org/doi/proceedings/10.1145/3773656
DOI10.1145/377365610.1145/3773656.3773691
External Publication Flag: