High-Level Program Optimizations for Data Analytics

Abstract – Many modern applications, especially those in data analytics, often spend a large number of cycles on unnecessary computations such as examining hundreds of thousands of non-similar others documents in a dataset to find a document most similar to a query document. Such redundant computations have been hidden in the useful instructions of applications and are elusive for traditional compiler-based code optimizations.

This discussion examines new work that harnesses these hidden, but significant, optimization opportunities by raising the level of program optimizations from implementations to algorithms, and from instructions to formulas.

Bio – Yufei Ding is a Ph.D. candidate in the Computer Science Dept. at North Carolina State University. She received her B.S. and M.S. in Physics from University of Science and Technology of China and The College of William and Mary, respectively. She began her CS Ph.D. in 2012.

Her research interest is the intersection of compiler technology and big data analytics, with a focus on enabling high-level program optimizations for data analytics and other data-intensive applications.

Ding actively publishes in major CS and data analytics venues, such as ASPLOS, PLDI, VLDB, ICDE, and ICML. She received an NCSU Computer Science Outstanding Research Award in 2016.