Issue No. 03 - May/June (2009 vol. 11)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MCSE.2009.48
Wen-Mei Hwu , University of Illinois
Christopher Rodrigues , University of Illinois
Shane Ryoo , ZeroSoft
John Stratton , University of Illinois
Graphics processing units (GPUs) can provide excellent speedups on some, but not all, general-purpose workloads. Using a set of computational GPU kernels as examples, the authors show how to adapt kernels to utilize the architectural features of a GeForce 8800 GPU and what finally limits the achievable performance.
CUDA, GPGPU, computer architecture, software optimization, benchmarks, compute unified device architecture, general-purpose computing on GPU
S. Ryoo, C. Rodrigues, J. Stratton and W. Hwu, "Compute Unified Device Architecture Application Suitability," in Computing in Science & Engineering, vol. 11, no. , pp. 16-26, 2009.