JolokiaC++: Optimizing Irregular Accesses for GPGPU.

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)

Cited 0|Views10
No score
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.
Translated text
Key words
GPU, GPGPU, Irregular Accesses, Parallel Constructs
AI Read Science
Must-Reading Tree
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined