arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1206.3215physics.comp-phcs.MS
收藏

傅立叶伪谱算法基准套件的FORTRAN和C GPU扩展的性能

Performance of FORTRAN and C GPU Extensions for a Benchmark Suite of Fourier Pseudospectral Algorithms

B. Cloutier, B. K. Muite, P. Rigge

摘要:

报告了PGI OpenACC、FORTRAN CUDA和Nvidia CUDA伪谱方法在单个GPU上的比较以及GCC FORTRAN在单个和多个CPU内核上的比较。GPU实现使用CuFFT,CPU实现使用FFTW。移植预先存在的FORTRAN代码以利用GPU是高效的,并且易于使用OpenACC和CUDA FORTRAN实现。提供了示例程序。

英文摘要:

A comparison of PGI OpenACC, FORTRAN CUDA, and Nvidia CUDA pseudospectral methods on a single GPU and GCC FORTRAN on single and multiple CPU cores is reported. The GPU implementations use CuFFT and the CPU implementations use FFTW. Porting pre-existing FORTRAN codes to utilize a GPUs is efficient and easy to implement with OpenACC and CUDA FORTRAN. Example programs are provided.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑