Overcoming Communication Latency Barriers in Massively Parallel Scientific Computation

Ron Dror, J. P. Grossman,Kenneth Mackenzie,Brian Towles,Edmond Chow,John Salmon,Cliff Young,Joseph Bank,Brannon Batson,David Shaw,Jeffrey S. Kuskin,Richard H. Larson,Mark A. Moraes,David E. Shaw

IEEE Micro（2011）

引用 8|浏览0

暂无评分

摘要

Anton, a massively parallel special-purpose machine that accelerates molecular dynamics simulations by orders of magnitude, uses a combination of specialized hardware mechanisms and restructured software algorithms to reduce and hide communication latency. Anton delivers end-to-end internode latency significantly lower than any other large-scale parallel machine, and its critical-path communication time for molecular dynamics simulations is less than 3 percent that of the next-fastest platform.

查看译文

关键词

software algorithm,end-to-end internode latency,molecular dynamics simulation,large-scale parallel machine,critical-path communication time,communication latency,next-fastest platform,parallel special-purpose machine,parallel scientific computation,overcoming communication latency barriers,specialized hardware mechanism,computational modeling,hardware,system on a chip,application software,parallel systems,synchronization,anton

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