TY - JOUR
T1 - GPU computing
AU - Owens, John D.
AU - Houston, Mike
AU - Luebke, David
AU - Green, Simon
AU - Stone, John E.
AU - Phillips, James C.
N1 - Manuscript received May 11, 2007; revised October 21, 2007 and January 2008. The work of J. Owens was supported by the U.S. Department of Energy under Early Career Principal Investigator Award DE-FG02-04ER25609, the National Science Foundation under Award 0541448, the SciDAC Institute for Ultrascale Visualization, and Los Alamos National Laboratory. The work of M. Houston was supported by the Intel Foundation Ph.D. Fellowship Program, the U.S. Department of Energy, AMD, and ATI. J. D. Owens is with the Department of Electrical and Computer Engineering, University of California, Davis, CA 95616 USA (e-mail: [email protected]). M. Houston is with the Department of Computer Science, Stanford University, Stanford, CA 94305 USA (e-mail: [email protected]). D. Luebke and S. Green are with NVIDIA Corporation, Santa Clara, CA 95050 USA (e-mail: [email protected]; [email protected]). J. E. Stone and J. C. Phillips are with the Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL 61801 USA (e-mail: [email protected]; [email protected]).
PY - 2008/5
Y1 - 2008/5
N2 - The graphics processing unit (GPU) has become an integral part of today's mainstream computing systems. Over the past six years, there has been a marked increase in the performance and capabilities of GPUs. The modern GPU is not only a powerful graphics engine but also a highly parallel programmable processor featuring peak arithmetic and memory bandwidth that substantially outpaces its CPU counterpart. The GPU's rapid increase in both programmability and capability has spawned a research community that has successfully mapped a broad range of computationally demanding, complex problems to the GPU. This effort in general-purpose computing on the GPU, also known as GPU computing, has positioned the GPU as a compelling alternative to traditional microprocessors in high-performance computer systems of the future. We describe the background, hardware, and programming model for GPU computing, summarize the state of the art in tools and techniques, and present four GPU computing successes in game physics and computational biophysics that deliver order-of-magnitude performance gains over optimized CPU applications.
AB - The graphics processing unit (GPU) has become an integral part of today's mainstream computing systems. Over the past six years, there has been a marked increase in the performance and capabilities of GPUs. The modern GPU is not only a powerful graphics engine but also a highly parallel programmable processor featuring peak arithmetic and memory bandwidth that substantially outpaces its CPU counterpart. The GPU's rapid increase in both programmability and capability has spawned a research community that has successfully mapped a broad range of computationally demanding, complex problems to the GPU. This effort in general-purpose computing on the GPU, also known as GPU computing, has positioned the GPU as a compelling alternative to traditional microprocessors in high-performance computer systems of the future. We describe the background, hardware, and programming model for GPU computing, summarize the state of the art in tools and techniques, and present four GPU computing successes in game physics and computational biophysics that deliver order-of-magnitude performance gains over optimized CPU applications.
KW - GPU computing
KW - General-purpose computing on the graphics processing unit (GPGPU)
KW - Parallel computing
UR - http://www.scopus.com/inward/record.url?scp=49049088756&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=49049088756&partnerID=8YFLogxK
U2 - 10.1109/JPROC.2008.917757
DO - 10.1109/JPROC.2008.917757
M3 - Article
AN - SCOPUS:49049088756
SN - 0018-9219
VL - 96
SP - 879
EP - 899
JO - Proceedings of the IEEE
JF - Proceedings of the IEEE
IS - 5
M1 - 4490127
ER -