Asgari Receives DOE Early Career Research Award

Aug 15, 2023

Bahar Asgari, an assistant professor of computer science with an appointment in the University of Maryland Institute for Advanced Computer Studies, has received a Department of Energy Early Career Research Award to advance new methods that can efficiently scale scientific computing.

The five-year, $875,000 grant comes from the DOE Office of Science’s Early Career Research Program, which bolsters the nation’s scientific workforce by supporting exceptional researchers at the outset of their careers, when many scientists do their most formative work.

Asgari was one of only 93 researchers nationwide selected to receive an award in this year’s round of funding.

“When I got the news, I was thrilled to be the first from our department to receive it,” she says. “The award's competitiveness makes it even more significant. Beyond that, I'm eager to delve into my research. I'm confident it will significantly transform our computational methods.”

Asgari’s proposal for the DOE funding, “Developing Techniques to Enable Intelligent Dynamic Reconfigurable Computing for Sparse Scientific Problems,” offers an innovative approach to allow diverse workloads to reach their peak performance without sacrificing performance for common cases.

To achieve this goal, her research will develop techniques for intelligent dynamic reconfigurability, unifying hardware and software in a holistic manner, adapting them together to run a program or multiple programs efficiently.

Ultimately, she says, her goal is to make efficient high-performance computing open access, for scientists focused on physics and medical sciences, to various engineering domains, to high school students.

“We want to democratize scientific computing for everyone,” Asgari says. "Right now, intricate computations, especially in areas like scientific computing or machine learning, depend on costly systems and can be time-consuming. We saw this during the COVID research phase, where the lengthy computational processes slowed the development of vaccines. Our goal is to expedite these critical computations.”

—This news brief was adapted from a story published by the Department of Computer Science.