Grace Dinh

I received my PhD from UC Berkeley in December 2023, advised by James Demmel. I am affiliated with the SLICE, BeBOP, and Theory groups.

I’m broadly interested in 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

As of 2024, I am currently searching for postdoctoral positions.

If you’d like to collaborate or just say hi, please feel to contact me!