Graphics Processing Units (GPUs) are becoming an inevitable part of every computing system because of their ability to provide orders of magnitude faster and more energy-efficient execution. They have become the default choice for accelerating innovations in various fields such as high-performance computing (HPC), artificial intelligence, deep learning, and virtual/augmented reality. As GPUs can provide very high throughput and memory bandwidth on a competitive power budget, they are being deployed into almost all kinds of computing systems, including many machines on Top500 and Green500 lists.
The goal of this lecture series is to discuss basic and advanced concepts related to GPUs. The lecture series will begin with providing an overview of GPU programming models (e.g., CUDA and OpenCL) and traditional GPU computing architecture. Next, it will cover various concepts related to micro-architecture and architecture of a typical GPU. Finally, we will discuss a subset of top-tier architecture conference papers to understand the important research challenges (along with a few approaches) towards fully leveraging the computational power of GPUs.
Adwait Jog is an Assistant Professor of Computer Science at the College of William and Mary (W&M). He earned his Ph.D. from the Pennsylvania State University, University Park in 2015 and Bachelor of Technology (B.Tech) from the National Institute of Technology (NIT) Rourkela, India in 2009. His research interests lie in the broad area of computer architecture with a high-level goal of architecting next-generation computers. Specifically, he is interested in designing capable, energy-efficient, reliable, and secure general-purpose Graphics Processing Units (GPUs) and other accelerators, which have become an integral part of almost every computing system. Results of his research have appeared in the top IEEE/ACM computer architecture conferences: ISCA, MICRO, HPCA, ASPLOS, and PACT. He is the recipient of the NSF CAREER Award (2018), NSF CRII award (2017), and Penn State Outstanding Graduate Research Assistant Award (2014).