Jeff is a Ph.D. candidate at Stanford University in Electrical Engineering advised by Mark Horowitz. His research interests are in building hardware accelerators from software languages. Halide to Hardware is a project to use a data-parallel functional program formerly developed for CPU programs to produce hardware. Through the AHA hardware toolflow, these image processing and deep learning algorithms are mapped to a CGRA. Previously, Jeff received a B.S. in Electrical and Computer Engineering from Cornell University in 2015.

All Publications

  • Interstellar: Using Halide's Scheduling Language to Analyze DNN Accelerators Yang, X., Gao, M., Liu, Q., Setter, J., Pu, J., Nayak, A., Bell, S., Cao, K., Ha, H., Raina, P., Kozyrakis, C., Horowitz, M., ACM ASSOC COMPUTING MACHINERY. 2020: 369–83
  • Programming Heterogeneous Systems from an Image Processing DSL ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION Pu, J., Bell, S., Yang, X., Setter, J., Richardson, S., Ragan-Kelley, J., Horowitz, M. 2017; 14 (3)

    View details for DOI 10.1145/3107953

    View details for Web of Science ID 000423744000006