Zhijia Zhao     
Zhijia Zhao

Ph.D. Candidate
College of William and Mary
"Enabling Parallel Execution and Dynamic Optimization – A Principled Approach”
Wednesday, February 4, 4:00 PM
Packard Lab room 466

Abstract:  Effectively translating computing hardware resource into computing efficiency is essential for lowering computing cost, maximizing scalability, and minimizing response delays. However, it is a daunting task for modern systems for their unprecedented level of concurrency and complexity. In this talk, I will introduce two software solutions that help significantly improve the computing efficiency for many commonly used applications. The first, Principled Speculation, adds rigor into program parallelization. The second, Probabilistic Calling Automata, enables predictability of large-scale program behaviors. Together, they demonstrate the large potential of the principled approach for advancing the state of the art of program analysis and optimizations. They represent a new direction to narrow the gap between modern computing hardware and the computing efficiency of applications.

Bio:  Zhijia Zhao is currently a Research Associate at North Carolina State University, working on fundamental research problems that could dramatically improve the computing efficiency. His overarching goal is to connect the demanding of applications to the innovation of hardware. He is also a PhD candidate at the College of William and Mary, with collaborations from Intel Labs, IBM Research and Mozilla Foundations.

© 2014-2016 Computer Science and Engineering, P.C. Rossin College of Engineering & Applied Science, Lehigh University, Bethlehem PA 18015.