I'm currently a software engineer at Google Brain, working on TensorFlow.
My research areas are High Performance Computing and Parallel Computing. I completed my Ph.D. in Computer Science at UC Berkeley, advised by Professor Kathy Yelick. My dissertation focused on avoiding communication in parallel, distributed N-body algorithms and matrix computations on supercomputers to achieve highly-scalable and energy-efficient implementations. Prior to my Ph.D., I enjoyed optimizing scientific applications on hardware accelerators such as GPU, Intel Xeon Phi, and Cell Broadband Engine.
During my time at Berkeley, I was part of the Berkeley Benchmarking and Optimization Group (BeBOP). I have been and am still affiliated with the Dynamic Exascale Global Address Space Programming Environments (DEGAS) project at the Lawrence Berkeley National Laboratory.
I was a Fulbrighter from Thailand. My first name is pronounced 'pen-pon' instead of 'pen-porn'.