WHU-CVRS

Presentations

Title: Overcoming GPU Hardware Limitations through Software Innovations
Reporter: Dr. Prof. Xipeng Shen, Computer Science Department at North Carolina State University
Time:  9:30AM-11:00AM, 13 Dec. 2016
Address3-202, Building No. 5, School of Remote Sensing and Information Engineering, Wuhan University
 
Abstract
For their tremendous computing power, Graphic Processing Units (GPUs) have received broad adoptions for a large variety of applications. The massively parallel hardware design makes it superior for efficient data-parallel computations. However, the design features some inherent hardware limitations that have been preventing GPUs to effectively support other types of computations, which include irregular computations, pipelined workloads, applications with dynamic parallelism, and multiprogramming computations that require flexible preemptions. In this talk, Dr. Shen will present a set of system software innovations that his group have produced in the last ten years' research, and show how these techniques effectively overcome the hardware limitations, significantly enhancing both performance and productivity for a wide range of applications on GPU.
Dr. Shen will also introduce the graduate program at NCSU, and answer any application questions.
 
Biography:
Xipeng Shen is an Associate Professor in the Computer Science Department at North Carolina State University. He is a receipt of U.S. DOE Early Career Research Award, U.S. NSF CAREER Award, and Google Faculty Research Award. He is an ACM Distinguished Speaker, and an IBM Center for Advanced Studies (CAS) Faculty Fellow.  His research lies in the broad field of compiler and programming systems, with an emphasis on enabling data-intensive high performance computing and intelligent computing through innovations in both compilers and runtime systems.
 
Prior to joining NC State in 2014, Shen was the Adina Allen Term Distinguished Associate Professor at The College of William and Mary. He was a Visiting Scientist at MIT and Microsoft Research, and had served as a consultant to Intel Labs and Cisco. He received his Ph.D. in Computer Science from University of Rochester in 2006, M.S. from Chinese of Academy of Sciences in 2001, and B.S. from the North China University of Technology in 1998.

Presented by Dr. Prof. Xipeng Shen