JolokiaC++: Optimizing Irregular Accesses for GPGPU.

Vibha Patel,Sanjeev Aggarwal,Amey Karkare

2015 IEEE 17th International Conference on High Performance Computing and Communications, 2015 IEEE 7th International Symposium on Cyberspace Safety and Security, and 2015 IEEE 12th International Conference on Embedded Software and Systems（2015）

引用 0|浏览12

暂无评分

摘要

We present JolokiaC++ a compiler framework to ease coding of irregular data applications on GPUs. The effectiveness of the compiler and runtime systems of JolokiaC++ is tested using three kernels IRREG, MOLDYN and NBF, executed on NVIDIA GPUs. We developed extensions for the generic parallel constructs that allow portable and efficient programming of codes with irregular accesses on the GPU. We present experimental results from compiling the kernels for execution on Fermi GTX 480, Tesla C1060 and Tesla K20c GPUs.

查看译文

关键词

GPU, GPGPU, Irregular Accesses, Parallel Constructs

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要