Abhishek Bhattacharjee

Associate Professor of Computer Science

Yale University


abhishek at cs.yale.edu

I am an Associate Professor of Computer Science at Yale University. I am a member of the Computer Systems Lab, the Interdepartmental Neuroscience Program, and the Yale Wu Tsai Institute for cognition. I am also a Fellow of Grace Hopper College.

I am interested in computer architectures, systems software, and their efficient layering in computer systems. Effective layering through the right abstractions gives software developers a stable programming model, even while the underlying architecture is augmented via innovations in general-purpose execution, domain-specific acceleration, and new memory technologies. I am especially interested in hardware-software co-design for the computational brain sciences and neuroengineering.

My group has spent over a decade uncovering the challenges imposed on the virtual memory abstraction by larger and more heterogeneous memories as well as domain-specific hardware acceleration. We have laid the foundation for translation contiguity and memory transistency, and proposed TLB coalescing, shared TLBs, better MMU caches, faster GPU address translation, intermediate address spaces, 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 on virtual memory. Our results have also 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 even larger pages is under active development in the Linux community.

More recently, we have also built computer systems to help treat neurological disorders, enable tighter connectivity between computers and the brain, and offer a path towards more human-like AI. In our HALO project, we are building low power and flexible chips for brain-computer interfaces. In our Distill project, we have built a domain-specific compiler for large-scale computational modeling of cognitive control in the human brain.

From 2010 to 2018, I was an Associate Professor of Computer Science at Rutgers University. In 2016, I was a visiting CV Starr Fellow at Princeton University's Neuroscience Institute. I received my PhD from Princeton University and my undergraduate degree from McGill University.

teaching & research

    Selected Articles

  • PDF
    Distill: Domain-Specific Compilation for Cognitive Models, CGO '22
    Compiler tools for large-scale computational modeling of cognitive control in the human brain
  • PDF
    MIND: In-Network Memory Management for Disaggregated Data Centers, SOSP '21
    Pushing virtual memory functionality into programmable network switches for memory disaggregation
  • PDF
    Rebooting Virtual Memory with Midgard, ISCA '21
    A study of the benefits of injecting the virtual memory area abstraction into hardware
  • PDF
    KLOCs: Kernel-Level Object Contexts for Heterogeneous Memory Systems, ASPLOS '21
    Check out our experimental kernel here
  • PDF
    Fast Local Page-Tables for Virtualized NUMA Servers with vMitosis, ASPLOS '21
    Check out our experimental kernel here
  • PDF
    Hardware-Software Co-Design for Brain-Computer Interfaces, ISCA '20
    IEEE Micro's Top Picks in Computer Architecture
    Check out a layout diagram of our HALO chips as well as their close-up and batch snaps
  • PDF
    Translation Ranger: Operating System Support for Contiguity-Aware TLBs, ISCA '19
    Check out our kernel here
    Check out the status of our Linux patchset
  • PDF
    Nimble Page Management for Tiered Memory Systems, ASPLOS '19
    Native transparent hugepage migration has been integrated into the Linux kernel
    Our experimental kernel is available here
  • PDF
    Generic System Calls for GPUs, ISCA '18
    Honorable mention, IEEE Micro's Top Picks in Computer Architecture
    Released under the Radeon Open Compute project for ultrascale computing
  • PDF
    Translation-Triggered Prefetching, ASPLOS '17
    IEEE Micro's Top Picks in Computer Architecture
    Best paper award nominee
  • PDF
    COATCheck: Verifying Memory Ordering at the Hardware-OS Interface, ASPLOS '16
    IEEE Micro's Top Picks in Computer Architecture
    Our COATCheck tool is available here
  • PDF
    Architectural Support for Address Translation on GPUs, ASPLOS '14
    IEEE Micro's Top Picks in Computer Architecture
  • PDF
    CoLT: Coalesced Large-Reach TLBs, MICRO '12
    Integrated in AMD chips, beginning with the Zen architecture
    • Technical Monographs

  • PDF
    Architectural and Operating System Support for Virtual Memory
    Synthesis lecture monograph on introductory and more advanced virtual memory concepts
  • PDF
    Advanced Concepts on Address Translation

    Appendix L in "Computer Architecture: A Quantitative Approach" by Hennessy and Patterson

    • Currently Teaching

  • Link
    CPSC 323: Introduction to Systems Programming and Computer Organization
    Spring '20, Spring '21, Spring '22