Toward a Cohesive AI and Simulation Software Ecosystem for Scientific Innovation

TL;DR

This paper advocates for a unified AI and simulation software ecosystem to enhance scientific discovery, emphasizing compatibility, ease of deployment, and community collaboration on high-performance computing systems.

Contribution

It proposes a cohesive software stack integrating AI and ModSim tools, addressing compatibility and deployment challenges for scientific innovation.

Findings

Highlights the need for standardized, portable software environments.

Recommends community-driven stewardship and collaboration with DOE.

Supports initiatives like E4S and Spack for ecosystem development.

Abstract

In this paper, we discuss the need for an integrated software stack that unites artificial intelligence (AI) and modeling and simulation (ModSim) tools to advance scientific discovery. The authors advocate for a unified AI/ModSim software ecosystem that ensures compatibility across a wide range of software on diverse high-performance computing systems, promoting ease of deployment, version management, and binary distribution. Key challenges highlighted include balancing the distinct needs of AI and ModSim, especially in terms of software build practices, dependency management, and compatibility. The document underscores the importance of continuous integration, community-driven stewardship, and collaboration with the Department of Energy (DOE) to develop a portable and cohesive scientific software ecosystem. Recommendations focus on supporting standardized environments through initiatives like the Extreme-scale Scientific Software Stack (E4S) and Spack to foster interdisciplinary innovation and facilitate new scientific advancements.