Issue No.03 - May/June (2009 vol.11)
Christopher Rodrigues , University of Illinois
Shane Ryoo , ZeroSoft
Wen-Mei Hwu , University of Illinois
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MCSE.2009.48
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
Christopher Rodrigues, Shane Ryoo, Wen-Mei Hwu, "Compute Unified Device Architecture Application Suitability", Computing in Science & Engineering, vol.11, no. 3, pp. 16-26, May/June 2009, doi:10.1109/MCSE.2009.48