NSF POSE: Phase II: Nexus: Harnessing open High Performance Computing (HPC) through HPX

Award ID: 2347449

Nexus aims to democratize access to computational resources and promote innovation across various emerging sectors, such as artificial intelligence (AI) and biotechnology. At its core, the project seeks to address the growing need for an open, high-performance computing (HPC) ecosystem that is accessible, secure, and efficient. This project is poised to serve the HPC community by making cutting-edge computational tools available to a broader range of users, thereby accelerating scientific research and technological innovation. The broader impact of the project lies in its potential to drive advancements in fields such as data analytics and AI, making it a strategic asset for technological and economic development. Nexus revolves around developing the HPX asynchronous many-task (AMT) runtime system. HPX is a mature, standards-based, open source platform for high-performance computing (HPC), designed to provide flexibility and efficiency for applications that require high levels of parallelism and scalability. The project's goals include enhancing the accessibility of the library, improving its software ecosystem and community, and developing a sustainability plan. This involves enhancing documentation, developing online courses, and fostering collaboration within the HPC community. The technical focus of the project also includes leveraging the RISC-V (reduced instruction set computer) architecture and the LLVM/MLIR (Multi-Level Intermediate Representation) compiler to create a co-designed environment that improves system efficiency and reduces energy consumption. These efforts aim to make HPC resources more accessible and cost-effective, contributing to economic development and enabling innovation in the scientific research and technology sectors. This project is jointly funded by the Established Program to Stimulate Competitive Research (EPSCoR) and the Pathways to Enable Open-Source Ecosystems (POSE) Program which seeks to harness the power of open-source development for the creation of new technology solutions to problems of national and societal importance. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Program Director: Florence Rabanal