计算机科学 ›› 2015, Vol. 42 ›› Issue (1): 71-74.doi: 10.11896/j.issn.1002-137X.2015.01.016
• 2013年全国理论计算机科学学术年会 • 上一篇 下一篇
张海博,安虹,贺松涛,孙涛,王涛,彭毅,程亦超
ZHANG Hai-bo, AN Hong, HE Song-tao, SUN Tao, WANG Tao, PENG Yi and CHENG Yi-chao
摘要: 对称多处理器的飞速发展和近年来提出的动态异构处理器(DHMP)为性能优化提供了新的机遇。一个机遇是找出程序每个阶段的性能瓶颈,提出了静态程序阶段分析方法,即通过分析结构参数和计算相似度矩阵来找出程序每个阶段的资源瓶颈;另一个机遇是给出动态异构处理器重构的时间节点,提出了DPDA和HTPD两种动态阶段检测算法,检测出阶段的变化能够为动态可重构处理器提供重构的时间节点。DPDA算法效果很好且软硬件实现代价小,而HTPD算法是目前为止第一个使用统计学方法进行动态检测阶段的算法。实验表明,与BBV相比,DPDA和HTPD能避免BBV离线、动态算法需添加额外硬件、结果与编译器相关等限制,并且阶段划分的稳定性和正确率与BBV相当。DPDA和HTPD算法由于本身不依赖额外硬件,因此都能直接在主流处理器和动态异构处理器(DHMP)中使用。
[1] Intel Corporation.Intel 64 and IA-32 Architectures SoftwareDeveloper’s Manualys.http://www.intel.com/content/www.us/en/processors/architectures-software-developer-manuals.html [2] Kalla R,Sinharoy B,Starke W J,et al.Power7:IBM’s Next-Generation Server Processor[J].IEEE Micro,2010,30(2):7-15 [3] Ipek E,Kirman M,Kirman N,et al.Core fusion:accommodating software diversity in chip multiprocessors[C]∥Proceedings of the 34th annual international symposium onComputer architecture.Dean Tullsen ed.San Diego,California,USA:ACM,2007:186-197 [4] Kim C,Sethumadhavan S,Govindan M S,et al.ComposableLightweight Processors[C]∥Proceedings of the 40th Annual IEEE/ACM International Symposium on Microarchitecture.IEEE Computer Society,2007:381-394 [5] Watanabe Y,Davis J D,Wood D A.WiDGET:Wisconsin decoupled grid execution tiles[C]∥Proceedings of the 37th Annual International Symposium on Computer Architecture.André SeznecedSaint-Malo,France,ACM,2010:2-13 [6] Sherwood T,Sair S,Calder B.Phase tracking and prediction[C]∥Proceedings of the 30th Annual International Symposium on Computer Architecture.New York,NY,USA,ACM,2003:336-349 [7] Sherwood T,Perelman E,Calder B.Basic block distributionanalysis to find periodic behavior and simulation[C]∥Procee-dings 2001 International Conference on Parallel Architectures and Compilation Techniques.Barcelona,Catalunya,Spain,IEEE Computer Society,2001:3-14 [8] Sherwood T,Perelman E,Hamerly G,et al.Automatically chara-cterizing large scale program behavior[C]∥Proceedings of the 10th International Conference on Architectural Support for Programming Languages and Operating Systems.New York,NY,USA,ACM,2002:45-57 [9] Dhodapkar A S,Smith J E.Comparing Program Phase DetectionTechniques[C]∥Proceedings of the 36th Annual IEEE/ACM International Symposium on Microarchitecture.IEEE Computer Society,Washington DC,USA,2003:217-228 [10] Lau J,Schoenmackers S,Calder B.Transition Phase Classification and Prediction[C]∥Proceedings of the 11th International Symposium on High-Performance Computer Architecture.IEEE Computer Society,Washington DC,USA,2005:278-289 |
No related articles found! |
|