Back

Minisymposium Presentation

S4PST, Stewardship for Programming Systems

Monday, June 3, 2024
12:30
-
13:00
CEST
Climate, Weather and Earth Sciences
Climate, Weather and Earth Sciences
Climate, Weather and Earth Sciences
Chemistry and Materials
Chemistry and Materials
Chemistry and Materials
Computer Science and Applied Mathematics
Computer Science and Applied Mathematics
Computer Science and Applied Mathematics
Humanities and Social Sciences
Humanities and Social Sciences
Humanities and Social Sciences
Engineering
Engineering
Engineering
Life Sciences
Life Sciences
Life Sciences
Physics
Physics
Physics

Description

The 'Stewardship for Programming Systems and Tools' (S4PST) initiative represents one of the Software Stewardship Organizations (SSOs) selected by the US Department of Energy's (DOE) Advanced Scientific Computing Research (ASCR) Next Generation of Programming Systems and Tools (NGSST) project. S4PST is dedicated to sustaining and enhancing programming systems that support the evolution of next-generation high-performance computing (HPC) infrastructure, including GPUs and AI-accelerated hardware. Our mission extends to the seamless integration of these systems with emerging AI technologies to further scientific research. Through our collaboration with the collective SSOs in NGSST, we aim not only to steward but also to advance the foundational software developed during the DOE’s Exascale Computing Project (ECP). This project culminated in the deployment of the inaugural infrastructure (hardware, software, libraries, etc. ) exascale systems, significantly impacting scientific research. During our presentation, we will highlight the several programming system products in our portfolio and their plans to advance these programming systems for HPC. We are committed to fostering a collaborative environment that unites developers, end-users, vendors, and DOE supercomputing facilities. Our community-centric model strives to cultivate a proactive and responsive software ecosystem, tailored to meet the diverse computational demands inherent in the DOE’s scientific endeavors.

Authors