Towards Energy-Efficient Computing in Graphics Processing Units

When: CANCELLED Friday, September 20, 2019

(Cancelled due to inclement weather)

Speaker: Dr. Xin Fu, University of Houston

Host: Dr. Larry Shi

With its strong computing power to achieve high teraflops peak performance, graphics processing units (GPUs) have been widely applied for complex computations such as machine learning, graphics, cryptography, and so on. However, the GPU is facing severe power and energy challenges. Energy-efficient computing becomes essential for GPUs to resist the grand “power wall” and meanwhile, boosting the GPU execution performance. In this talk, I discuss our recent work on exploring energy-efficient computing for three types of popular applications that are adopted in GPUs: 1) Long-Short Term Memory Networks (LSTMs) – one type of recurrent neural network that is mainly used for natural language processing, I will present our memory friendly LSTMs design on mobile GPUs; 2) 3D rendering, I will present the integration of new memory technology (i.e., processing-in-memory) into GPUs to energy-efficiently support 3D rendering; and 3) Virtual Reality (VR), I will discuss our object-oriented VR rendering framework for future multi-GPU systems.

Bio:

Dr. Xin Fu received the Ph.D. degree in Computer Engineering from the University of Florida, Gainesville, in 2009. She was a NSF Computing Innovation Fellow with the Computer Science Department, the University of Illinois at Urbana-Champaign, Urbana, from 2009 to 2010. From 2010 to 2014 she was an Assistant Professor at the Department of Electrical Engineering and Computer Science, the University of Kansas, Lawrence. Currently, she is an Associate Professor at the Electrical and Computer Engineering Department, the University of Houston, Houston. Her research interests include computer architecture, energy-efficient computing, mobile computing, near-data computing, graphics processing units, and neural-network acceleration. Dr. Fu is a recipient of 2014 NSF Faculty Early CAREER Award, 2012 Kansas NSF EPSCoR First Award, and 2009 NSF Computing Innovation Fellow.