image: Tabitha Samuel
Credit: University of Tennessee
Faculty members from the Min H. Kao Department of Electrical Engineering and Computer Science at University of Tennessee are involved in two collaborative National Science Foundation grants that aim to address health disparities research and enhance the performance and productivity of AI science.
Tabitha Samuel, the interim director and operations group leader for UT’s National Institute for Computational Sciences (NICS), is the principal investigator for UT on both projects.
AI Advancement in Health Research
The first grant ($82,824) is a statewide collaboration among Tennessee Tech University, UT, Meharry Medical College, and Vanderbilt University that is part of the NSF’s National Artificial Intelligence Research Resource (NAIRR) Pilot.
The project, Mid-South Conferences on Cyberinfrastructure Advances to Enable Interdisciplinary AI Research in Health, will train participants how to use high-performance computing, cloud-based AI applications, and open data tools in medical research and healthcare delivery.
According to the 2023 America’s Health Rankings report, Tennessee ranks 44th among the 50 states in national health outcomes. This project will advance the use of modern, AI/ML-enabled computer technology in medical research and healthcare delivery while fostering sustained collaboration among medical professionals, engineers, scientists, and students who participate. Adhering to UT’s land-grant mission, the researchers will share content and outcomes with the NSF NAIRR program and broadly with the public at no charge.
The project consists of three workshops to be held in Knoxville, Nashville, and Memphis every six months over an 18-month period.
The co-PIs on this grant from UT are Vasileios Maroulas, director of the AI Tennessee Initiative; Courtney Cronley, a professor in the College of Social Work; Hector Santos-Villalobos, EECS assistant professor; and Fatima Zahra, an assistant professor of evaluation, statistics, and research methodology in the Department of Educational Leadership and Policy Studies.
“We focused on bringing AI training for health disparities research in Tennessee and the Mid-South area because we are aware of the magnitude of research being done around health disparities unique to the region,” Samuel said. “We hope that this AI training, coupled with exposure to the expanse of NAIRR resources, will empower Tennessee researchers with a distinct advantage in addressing and mitigating health disparities through innovative and impactful research.”
Boosting AI Speed and Efficiency
The second grant ($800,000) is a collaboration among Tennessee Tech, UT, Illinois Institute of Technology, and Stony Brook University. This NSF Cyber Infrastructure for Sustained Scientific Innovation grant aims to improve how massively parallel computers run large-scale artificial intelligence (AI) applications by enhancing the Message Passing Interface (MPI), a widely used standard for coordinating work across many high-performance-computing nodes in parallel programs.
Currently, the enabling data-transfer software used in AI for communication between computers enhanced by Graphical Processing Units (GPUs) are often proprietary and/or limited in scope; they cannot be expanded or enhanced by an open community. That situation restricts innovation, making it harder for scientists to collaborate and enhance their science output on limited computer resources, while also creating dependency on a few vendors.
By contrast, this project, Enhancing Performance and Productivity of AI Science through Next-generation High Performance Communication Abstractions, builds on and advances Open MPI, a major open-source implementation of MPI with a long history of broad impact, to make it more efficient, flexible, and better suited for modern AI tasks.
“In this age of AI, how do we instrument and improve MPI to perform better for AI codes?” Samuel said. “The hardware is at the stage where AI can do fairly well on HPC hardware. But the next question is, how do AI codes perform across multiple nodes and scaling? That’s where this project comes in.”