GPUs and the Future of Parallel Computing
Stephen W. Keckler, William J. Dally, Brucek Khailany, Michael J. Garland, David Glasco · IEEE Micro · 2011
This article discusses the capabilities of state-of-the art GPU-based high-throughput computing systems and considers the challenges to scaling single-chip parallel-computing systems, highlighting high-impact areas that the computing research community can address. Nvidia Research is investigating an architecture for a heterogeneous high-performance computing system that seeks to address these challenges.