I am an ADIA Lab research fellow for the Complexity and Linear Algebra program at the Simons Institute for the Theory of Computing and postdoc at Cornell University’s Computer Systems Lab, advised by Zhiru Zhang. Previously, I received my PhD from UC Berkeley, where I was advised by James Demmel, and affiliated with the SLICE, BeBOP, and Theory groups.
I’m broadly interested in high-performance tensor computations and making it easier to build high-performance domain-specific software and hardware. More specifically, I work on:
algorithms for achieving maximum performance on models of computation that reflect modern hardware realities, and lower bounds to prove that these algorithms are optimal (or to help improve them if they’re not)
tools to apply these algorithms on real hardware in practice (compiler optimizations, accelerator mappers)
design-space exploration techniques to generate efficient hardware designs
If you’d like to collaborate or just say hi, please feel to contact me!