Parallel computing experiences with CUDA

Garland, M (Garland, Michael); Le Grand, S (Le Grand, Scott); Nickolls, J (Nickolls, John); Anderson, J (Anderson, Joshua); Hardwick, J (Hardwick, Jim); Morton, S (Morton, Scott); Phillips, E (Phillips, Everett); Zhang, Y (Zhang, Yao); Volkov, V (Volkov, Vasily)

IEEE MICRO, 28 (4): 13-27 JUL-AUG 2008

The CUDA programming model provides a straightforward means of describing inherently parallel computations, and NVIDIA's Tesla GPU architecture delivers high computational throughput on massively parallel problems. This article surveys experiences gained in applying CUDA to a diverse set of problems and the parallel speedups over sequential codes running on traditional CPU architectures attained by executing key computations on the GPU.

Return to Publications page