Xipeng Shen joins CS from University of Rochester where he did research in compiler technology.
Xipeng Shen attended the University of Rochester from 2001 to 2006 receiving a Master of Science degree and a Ph.D. degree in Computer Science in 2003 and 2006 respectively. His research lies in the area of Programming Systems and Compiler Technology. He focuses on modeling and predicting large-scale dynamic behavior patterns to improve performance, control memory size, and support coarse-grain parallelization through offline program transformation and online program adaptation. His work has contributed effective techniques for understanding and exploiting program locality, behavior phases, and high-level parallelism, which have been published on major conferences (PLDI, ASPLOS, ICS, ICPP, ISMM etc.) and academic journals (ACM TOPLAS, IEEE TOC, Pattern Recognition.) His lightweight locality model has been implemented in TPO, the core optimization component of IBM C/C++ and Fortran compilers. Before joining the University of Rochester, he received his Master of Science in Pattern Recognition and Intelligent Systems from the Institute of Automation at the Chinese Academy of Sciences in 2001. He attended the North China University of Technology from 1994 to 1998 receiving a Bachelor of Engineering in Industry Automation in 1998.