Matriz operations Using GPU
The rapid development of personal computers leads to that various applications in computer graphics are migrating from workstations to PCs. With the advancement of Graphics Processing Unit (GPU) and the creation of its feature of programmability, researchers begin to transfer some of the processing stages in the graphics output pipeline or some graphics algorithms from CPU to GPU. Except from those applications in graphics itself, GPU finds its applications in general purpose computations in other fields, and it comes up as a hot topic for research in recent years. Our work shows that matrix computations can be performed efficiently on the commodity GPU, which we regard as a powerful vector coprocessor to the CPU.In this paper, a detail introduction and analysis will be given to the technique and the latest development of GPU for matrix computations. We include results demonstrating proof of concept, correctness, speedup, and simple applications. Based on our results and current trends, we believe that efficient use of graphics hardware will become increasingly important to high-performance computing on commodity hardware.
Matriz operation GPU
Qihui Wang Zhouxiang Shou
Hangzhou Normal University, Hangzhou, Zhejiang, 310012, P.R.China
国际会议
The Third International Workshop on Applied Matriz Theory(第三届国际矩阵分析与应用会议)
杭州
英文
166-168
2009-07-09（万方平台首次上网日期，不代表论文的发表时间）