期刊文献+

CC-NUMA系统中一种块传输通讯机制的设计与实现 被引量:1

Design and Implementation of a Block Transfer Communication Mechanism in CC-NUMA Systems
下载PDF
导出
摘要 本文描述了一种CC-NUMA结点控制器内实现的通信机制,通信请求通过描述符进行提交,利用CC-NUMA硬件实现的Cache一致性协议,实现高性能的一致性数据传输。基于这种通信机制,实现了高速通信软件接口,使用用户级通信技术,将硬件的通讯功能抽象出来给应用层使用,在测试中获得了较好的性能。 An intra-node communication mechanism implemented in the CC-NUMA node controller is proposed in this paper. All communication requests are submitted to the controller in a descriptor format, the hardware performs coherent block data transfer in the whole system. A user-level communication interface is implemented based on this communication mechanism,and the applications can utilize it and get high performance.
出处 《计算机工程与科学》 CSCD 2008年第1期138-141,共4页 Computer Engineering & Science
关键词 CC-NUMA 描述符 一致性块传输 通信接口 CC-NUMA descriptor coherent block data transfer communication interface
  • 相关文献

参考文献10

  • 1PangZhengbin DouQiang LiuGuangming etal.A Hybrid Directory-Based Cache Coherence Protocol Design.高技术通讯,2004,14:88-90.
  • 2InfiniBand Architecture Specification Volume 1. ReleaSe 1.0a[M]. InfiniBand Trade Association, 2000.
  • 3Boden N J, Cohen D, Felderman R E, et al. Myrinet: A Gigabit-per-Second Local Area Network [J]. IEEE Micro, 1995, 15(1):29-36.
  • 4Bhoedjang R A F,Ruhl T,Bal H E. LFC:A Communication Substrate for Myrinet[C]//Proe of the 4th Annual Conf of the Advanced School for Computing and Imaging, 1998.
  • 5Cameron D , Regnier G. The Virtual Interface Architecture [M].Intel Press, 2002.
  • 6Buonadonna P,Geweke A,Culler D. An Implementation and Analysis of the Virtual Interface Architecture[C]//Proc of Supercomputing' 98,1998.
  • 7Gillett R. Memory Channel Network for PCI[J]. IEEE Micro, 1996,16(1): 12-18.
  • 8Kuskin J,Ofelt D, Heinrich M,et al. The FLASH Multiprocessor[C]//Proc of 21st Int 'l Syrup on Computer Architecture, 1994: 302-313.
  • 9Heinlein J, Gharaehorloo K, Bosch R P, et al. Coherent Block Data Transfer in the FLASH Multiprocessor[C]//Proc of the Int 'l1 Parallel Processing Symp, 1997 : 485-496.
  • 10Laudon J, Lenoski D. The SGI Origin : A CC-NUMA Highly Scalable Scrver[C]//Proc of the 24rd Int'l Syrnp on Computer Architecture, 1997: 241-251.

同被引文献6

  • 1弋瑞录,胡飞,奚水清,侯雪梅.基于LSF集群系统的分布式并行计算[J].测控技术,2006,25(7):53-55. 被引量:8
  • 2苗瑞生,居贤铭,吴甲生.导弹空气动力学[M].国防工业出版社,2006.
  • 3J Mark Bull, Chris Johnson. Data Distribution, Migration and Replication on acc - NUMA Architecute[ M]. University of Edin- burgh, Scotland, UK, 2009.
  • 4卢宇彤,朱敏,沈志宇.大规模并行计算资源管理体系结构的研究[C].第七届全国并行计算学术交流会(成都),2003.
  • 5史小卿.ANSYSAUTODYN6.0非线性显式动力学软件[M].杭州:浙江教育出版社,2010.
  • 6李裕春,时党勇,赵远.ANSYS10.O/LS-DYNA基础理论与工程实践[M].北京:中国水利水电出版社,2006.

引证文献1

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