期刊文献+

多核处理器P2020的访存实时性分析与优化 被引量:4

Analysis and Optimization of Memory Latency Based on Multi- core Processor P2020
下载PDF
导出
摘要 多核处理器以其高集成度、高性能功耗比的特点,获得了军事、电信、网络等领域的关注,但多个处理核心对共享资源的抢占带来的实时性问题阻碍了多核处理器在上述领域的应用。面向实时性的代表指标——访存时间,以P2020为研究对象,分析了其实时性的影响因素,采用可变步长的模型,对各种影响因素进行了定量的测试与分析,为多核处理器访存实时性的优化提供了参考。 Multi- core processor has the characteristics of high integrated and high performance with low power,which attract several areas' attention such as military,telecommunications,network and so on. But there is a serious problem of real- time caused by the cores accessing the shared resources simultaneously,which counteracts the applications of multi-core processor in such areas. Faces the representative indicator of real-time,which is memory access time. With P2020 processor as the research prototype and analyses its effect factors of real- time. Adopts a measurement model based on variable strides to quantificationally test and analyze the effect factors. Provides references for optimizing the performance of memory access time.
作者 段宇博 王乐
出处 《航空计算技术》 2015年第3期108-112,共5页 Aeronautical Computing Technique
基金 中航工业技术创新基金项目资助(2013D63125R)
关键词 多核 实时性 访存延迟 测试 multi- processor real- time memory access latency test
  • 相关文献

参考文献7

  • 1Conductor, Inc. Freescale Semiconductor Corp. Multi-Core Microprocessors in Embedded Applications [M]. America:Freescale Semiconductor,2009.
  • 2陈芳园,张冬松,王志英.多核实时线程间干扰分析及WCET估值[J].电子学报,2012,40(7):1372-1378. 被引量:9
  • 3Conductor, Inc. Freescale Semiconductor Corp. QorlQTM P2020 Communications Processor Product Brief [M]. America:Frees-cale Semiconductor,2009.
  • 4Conductor, Inc. Freescale Semiconductor Corp. P2020 QorIQ Integrated Processor Reference Manual [M]. America:Free-scale Semiconductor,2009.
  • 5Mericas A E, Mirablella R D. Method for Measuring Memory Latency in a Hierarchical Memory System, US, 7051177B2[P]. 2006.
  • 6Bergstorm L. Measuring NUMA Effects with the STREAM Benchmark [R]. Chicago, USA:University of Chicago,2011.
  • 7吴俊杰,杨学军.面向非一致Cache的任意步长预提升技术[J].计算机科学与探索,2010,4(7):577-588. 被引量:4

二级参考文献43

  • 1吴佳骏,冯晓兵,张兆庆.非线性规律访存操作的数据预取技术[J].计算机研究与发展,2007,44(2):355-360. 被引量:1
  • 2郇丹丹,李祖松,胡伟武,刘志勇.结合访存失效队列状态的预取策略[J].计算机学报,2007,30(7):1104-1114. 被引量:3
  • 3Gendler A,Mendelson A,Birk Y.A PAB-based multiprefetcher mechanism[J].Int J Parallel Program,2006,34(2):171-188.
  • 4Magnusson P S.Simics:A full system simulation platform[J].Computer,2002,35(2):50-58.
  • 5Muralimanohar N,Balasubramonian R,Jouppi N.Optimizing NUCA organizations and wiring alternatives for large caches with CACTI 6.0[C] //Proceedings of the 40th Annual IEEE/ACM International Symposium on Microarchitecture.Washington,DC,USA:IEEE Computer Society,2007:3-14.
  • 6Bailey D H.The NAS parallel benchmark results[C] //Proceedings of the 1992 ACM/IEEE Conference on Supercomputing.Now York,USA:ACM,1992:386-393.
  • 7Henning J L.SPEC CPU 2000:Measuring CPU performance in the new millennium[J].Computer,2000,33(7):28-35.
  • 8Kim C,Burger D,Keckler S W.An adaptive,non-uniform cache structure for wire-delay dominated on-chip caches[C] //Proceedings of the 10th International Conference on Architectural Support for Programming Languages and Operating Systems.New York,USA:ACM,2002:211-222.
  • 9Chishti Z,Powell M D,Vijaykumar T N.Distance associativity for high-performance energy-efficient non-uni-form cache architectures[C] //Proceedings of the 36th Annual IEEE/ACM International Symposium on Microarchitecture.Washington,DC,USA:IEEE Computer Society,2003.
  • 10Beckmann B M,Wood D A.Managing wire delay in large chip-multiprocessor caches[C] //Proceedings of the 37th Annual IEEE/ACM International Symposium on Microarchitecture.Washington,DC,USA:IEEE Computer Society,2004:319-330.

共引文献11

同被引文献11

引证文献4

二级引证文献4

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