Yale University
abhishek at cs.yale.edu
-
NVIDIA-
NVIDIA-
NVIDIA-
NVIDIAI am an Associate Professor of CS at Yale, a member of its Computer Systems Lab and Wu Tsai Institute for cognition, as well as a Fellow at Grace Hopper College.
My research and teaching interests focus on computer architectures, systems software, and their efficient layering for both classical systems as well as those used for and inspired by the brain sciences.
My group has spent over a decade uncovering the challenges imposed on the virtual memory abstraction by advances in memory subsystems and the advent of hardware accelerators. We have laid the foundation for translation contiguity and memory transistency, proposed TLB coalescing, shared TLBs, better MMU caches, faster GPU address translation, efficient translation coherence, optimizations for large pages, rack-scale distributed shared memory, and more. These results and the body of work that they have enabled other groups to pursue are summarized in my textbook. Our results have influenced virtual memory implementation on real-world systems. Coalesced TLBs have been implemented in AMD's chips, our large page migration optimizations are now in Linux, and our work on generating translation contiguity is under active development in the Linux community.
We are also building computer systems to help treat neurological disorders, enable direct brain-computer interfacing, accelerate scientific discovery of the brain, and are also using techniques from the cognitive sciences to build better computer systems. In our HALO project, we are building low power and flexible chips for brain-computer interfaces. In our Distill project, we have built a compiler for large-scale computational modeling of cognitive control in the human brain.
My group's research has been recognized with four IEEE Micro Top Picks awards, two IEEE Micro Top Picks honorable mentions, an NSF CAREER award, the Chancellor's Award for Faculty Excellence in Research at Rutgers, where I was previously on the faculty, a visiting CV Starr Fellowship at Princeton's Neuroscience Institute, where I spent my post-tenure sabbatical, and more. My teaching and mentoring have been recognized with the Yale SEAS Ackerman Award.
Appendix L in "Computer Architecture: A Quantitative Approach" by Hennessy and Patterson