摘要
针对图形处理器（GPU）架构下的软件可移植性、可编程性差的问题，为了便于在GPU上开发并行程序，通过自动映射与静态编译相结合，提出了一种新的基于制导语句控制的编译优化方法，实现了一个源到源的自动转化工具GPU-S2S，它能够将插入了制导语句的串行C程序转化为统一计算架构（CUDA）程序。实验结果表明，经GPU-S2S转化生成的代码和英伟达（NVIDIA）提供的基准测试代码具有相当的性能；与原串行程序在CPU上执行相比，转换后的并行程序在GPU上能够获取显著的性能提升。
To address the problem of poor software portability and programmability of a graphic processing unit （ GPU）, and to facilitate the development of parallel programs on GPU, this study proposed a novel directive based compiler guided approach, and then the GPU-S2S, a prototypic tool for automatic source-to-source translation, was implemented through combining automatic mapping with static compilation configuration, which is capable of translating a C sequential program with directives into a compute unified device architecture （CUDA） program. The experimental results show that CUDA codes generated by the GPU-S2S can achieve comparable performance to that of CUDA benchmarks provided by NVIDIA CUDA SDK, and have significant performance improvements compared to its original C sequential codes.
出处
《高技术通讯》
CAS
CSCD
北大核心
2012年第4期388-394,共7页
Chinese High Technology Letters
基金
863计划（2009AA012108,2009AA01A135,2006AA01A109）和中央高校基本科研业务费专项资金（08142007）资助项目.
关键词
图形处理器(GPU)
制导语句控制
源到源转化
graphic processing unit （GPU）, compiler directive, source to source translation
