Table of Contents
Customizing Communication and Computation
Abstract
The virtuous cycle of Moore’s Law has reached an impasse. Due to
technology limitations, the incommensurate scaling of energy relative
to transistor density threatens to undermine the scalability of future
computing devices. In this talk, I will first describe several
opportunities for addressing this challenge through efficient
customization of communication and computation. In the remainder of
the talk, I will present several ongoing efforts that span the
development of flexible, programmable accelerators to the design of
custom interconnects in the data center and future computing devices.
Bio
Eric Chung is currently a post-doc researcher at Microsoft
Research Silicon Valley and received his Ph.D. from Carnegie Mellon in
2011. Eric’s research interests lie in the exploration, prototyping,
and programmability of future, energy-efficient computer
architectures. At CMU, Eric led the CoRAM project, an effort to
re-think the architecture of FPGAs for computing. He was also the
project lead for ProtoFlex, which developed large-scale, full-system
multiprocessor emulators using FPGAs.
Back to the seminar page