Highly parallel GEMV with register blocking method on GPU architecture.

Jian Yin,Hui Yu,Weizhi Xu,Yuxuan Wang,Zhu Tian,Yingping Zhang,Bochuan Chen

Journal of Visual Communication and Image Representation（2014）

引用 4|浏览49

暂无评分

摘要

•We propose a register blocking method for GEMV on GPU.•The proposed method can improve the parallelism and reuse data on chip at the same time.•Different block sizes are tested to found the best block size on a GPU platform.

查看译文

关键词

GEMV,Register blocking,Data reuse,Memory bandwidth,GPU,Many-core,Parallelization,CUDA

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