期刊文献+

关于CPU+GPU异构计算的研究与分析 被引量:5

On the CPU + GPU Heterogeneous Computing Research and Analysis
下载PDF
导出
摘要 在PC技术领域,CPU和GPU始终是相辅相成,在二者已经发展到出现新的瓶颈时,"结合"也许是明智的解决方案,而关于整合CPU和GPU的方案就一直被人们所津津乐道。本文研究了CPU+GPU的异构化计算算法的优势和未来应用的可能性,特别是随着通用计算程序接口(OpenCL)的发布,CPU+GPU的异构化计算这种看起来像是CPU和GPU混合体的出现,相信这将使计算机处理器又将迈上一个新台阶,这种异构化成就的是更加高性能,更加高性价比的处理器,而这必将掀起GPU和CPU革命的高潮。 In the PC technology, CPU and GPU is always complement each other, in the two have developed to the emergence of new bottlenecks, the"integration"is probably the sensible solution, but on the integration of the program on the CPU and the GPU has been talked about by people. This paper studies the CPU + GPU, heterogeneous computing algorithms advantages and the possibility of future applications, especially with the general-purpose computer program interface (OpenCL) release, CPU + GPU, heterogeneous computing that looks like a CPU and the emergence of a mixture of GPU I believe this will allow a computer processor in turn to a new level, the achievements of this isomerlzation is more highperformance,A more cost-effective processor, which will surely mark the climax of the revolutionary GPU and CPU.
作者 许桢
出处 《科技信息》 2010年第17期I0097-I0097,I0014,共2页 Science & Technology Information
关键词 中央处理器(CPU) 图形处理器(GPU) 整合 异构计算 Central Processing Unit (CPU) (GPU) Integration Heterogeneous computing
  • 相关文献

参考文献4

二级参考文献60

  • 1陈国良,并行算法.设计与分析,1994年
  • 2朱洪,算法设计和分析,1989年,132页
  • 3Kumar V,Int J Parallel Programming,1987年,16卷,6期,501页
  • 4Clark James H.The geometry engine:A VLSI geometry system for graphics[A].In:Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH,Boston,1982.127~133
  • 5Fuchs Herry,Poulton John.Pixel-planes:A VLSI-Oriented design for a raster graphics engine[J].VLSI Design,1981,2(3):20~28
  • 6Eyles John,Austin John,Fuchs Henry,et al.Pixel-plane 4:A summary,advances in computer graphics hardware II[A].Eurographic Seminars Tutorials and Perspectives in Computer Graphics,New York:Springer-Verlag,1988.183~208
  • 7Fuchs Herry,Israel Laura,Poulton John,et al.Pixel-planes 5:A heterogeneous multiprocessor graphics system using processor-enhanced memories[A].In:Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH,Boston,1989.79~88
  • 8http://www.nvidia.com/object/gpu.html[OL]
  • 9http://developer.nvidia.com/[OL]
  • 10http://www.ati.com/developer/[OL]

共引文献231

同被引文献41

  • 1陶涛,郭红卫,何海涛.镜面反射面形光学三维测量技术综述[J].光学仪器,2005,27(2):90-95. 被引量:22
  • 2李加文,陈宗雨,李从心.基于函数逼近的三角函数加减速方法[J].机床与液压,2006,34(3):66-67. 被引量:16
  • 3蒋尊兴,郭红卫,陈明仪.自适应空间载波相移算法[J].光学仪器,2006,28(6):54-58. 被引量:1
  • 4张舒,褚艳丽,赵开勇,等.GPU性能运算之CUDA[M].北京:中国水利出版社.2009.
  • 5Harish P, Narayanan P J. Accelerating large graph algorithms on the GPU using CUDA [J]. High Performance Computing- HiPC, 2007:197-208.
  • 6Nvidia: Cuda 3.0.Technical report, Nvidia Corp. (2010) Available at[EB/OL], http://developer.nvidia.com/objeet/cuda_3_ 0_ downloads.html.
  • 7Venkataraman G,Sahni S,Mukhopad H S. A blocked all-pairs shortest-paths algorithm[M]. J. Exp. Algorithmics ,2003.
  • 8胡天亮,张洪波,刘日良.基于STEP-NC的数控车削系统的加工工艺参数优化[J].工艺与检测,2011(8):128-131.
  • 9BELLIS S J, MARNANE W P. A CORDIC arctangent FPGA implementation for ahigh-speed 3D-camerasystems[J]. Lecture Notes in Computer Science, 2000,1896 : 485- 494.
  • 10TAKEDA M,MUTOH K. Fourier transform profilometry for the automatic measurement of 3-D object shapes[J]. Appl Opt, 1983, 22(24) :3977-3982.

引证文献5

二级引证文献19

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部