Research: Philippe's research lies at the intersection between Machine Learning and High-Performance Computing. He focuses on the design and implementation of new programming models for tensor computations, with an emphasis on the use of machine-learned compiler heuristics capable of accomodating a wide variety of hardware architecture and problem characteristics. He is also interested in the applications of his research to scientific computing, and spends part of his time working on large-scale volumetric segmentation for connectomics.
Bio: Philippe is a fifth-year PhD student in Computer Science. at Harvard University, and is co-advised by Professors David Cox and H.T. Kung. He received his Bachelor's degree in Information Technology from Telecom Sudparis, France and a Master's in Computer Science from National Chiao Tung University, Taiwan. He developed optimized BLAS kernels as an intern at NVIDIA, AMD and Intel, and was a 2017 NVIDIA Graduate Fellowship Finalist.