Broadening the Field of Heterogeneous Computing: From Protein Discovery to Hardware Design

Speaker

Lisa Wu Will
Assistant Professor of Computer Science and ECE at Duke University.

Title

"Broadening the Field of Heterogeneous Computing: From Protein Discovery to Hardware Design "

Abstract

The explosion of data produced and consumed, coupled with ever-demanding performance and power efficiency in this post-Moore's Law era of computing, necessitates revolutionary hardware design and usage. In this talk, I will highlight three recent projects that demonstrate how we leverage hardware acceleration to push the boundaries of emerging applications across domains, as well as how we make hardware-accelerated system development more intuitive and accessible, akin to software development. The first project accelerates protein-protein interaction using accelerated NLP models, the second project uses deep-learning-based models to predict synthesis results of arbitrary hardware designs in seconds, and the third project is an accelerator composer that provides a programming abstraction for developing and deploying device-agnostic hardware accelerators, including optimal placement/routing on multi-die FPGAs.

About Speaker

Lisa Wu Wills is an Assistant Professor of Computer Science and ECE at Duke University. Prior to Duke, she was a postdoctoral researcher at UC Berkeley and a research scientist at Intel Labs. Her research interests include computer architecture and microarchitecture, hardware acceleration, hardware-software co-design, and emerging applications in big data, healthcare, and artificial intelligence. Wills has a PhD in computer science from Columbia University. Her research is recognized via various awards such as an NSF CAREER Award, a Google ML&Systems junior faculty award, a VMware Early Career Faculty Grant, IEEE Micro Top Picks (x3) and Honorable Mentions (x2), and best paper awards from MICRO and ISPASS.