期刊文献+

基于线程感知寄存器重命名的SMT处理器资源分配 被引量:3

Regulating SMT Resource Allocation via Thread-Sensitive Register Renaming
下载PDF
导出
摘要 SMT处理器的资源分配一般是通过调控各线程的取指过程间接实现的,这种间接调控有时会导致资源滥用和饥饿,从而严重浪费资源并降低整体性能.以往的改进措施往往实现代价较大,且不能消除资源分配的"不均衡性",因此效果不太理想.文中提出一种新的SMT处理器资源调控机制——线程感知寄存器重命名TSRR(Thread-Sensitive Register Renaming),消除了资源分配的"不均衡性",其优点如下:(1)资源分配自动适应线程运行状态的变化,实现"按需分配";(2)通过调控重命名寄存器文件(RRF)的分配来间接控制其它资源分配,实现代价较低;(3)兼顾资源分配的效率和公平,既防止了资源滥用和饥饿,又充分发掘各线程的性能潜力.此外,TSRR还可以间接降低RRF的尺寸要求和取指逻辑的复杂度. SMT processors generally regulate the resource allocation indirectly by controlling the Instruction-Fetch (I-Fetch) process, which may lead to resource misuse and even starvation, incurring resource underutilization and performance depression. Various improving techniques have been proposed; however their effects are discounted due to either being too expensive to imple- ment, or failing in eliminating the imbalance of resource allocation. This paper proposes a novel scheme, Thread-Sensitive Register Renaming (TSRR), which serves as a resource gating, remarkably eliminating the imbalance of resource allocation and improving the overall performance. TSRR features that: (1) it tracks the performance variations and dynamically tunes the resource amount available to each thread, realizing allocation-on-demand, (2) it is cost-effective because it tunes up all resources just by regulating the allocation of the rename-register-file (RRF), and (3) concerning both effectiveness and fairness, TSRR prevents both resource misuse and starvation, whereas fully exploits the performance potential of each thread. Meanwhile, TSRR can lessen the RRF size demands and I-Fetch hardware complexities.
出处 《计算机学报》 EI CSCD 北大核心 2008年第5期845-857,共13页 Chinese Journal of Computers
基金 “十五”预研基金(41316.1.2) 国家自然科学基金(60503015) 教育部博士点基金项目(20020213017)资助
关键词 同时多线程 资源分配 寄存器重命名 处理器 高性能 SMT resource allocation register renaming processor high-performance
  • 相关文献

参考文献17

  • 1Tullsen D M, Eggers S J, Levy H M. Simultaneous multithreading: Maximizing on-chip parallelism Proceedings of the 22nd Annual International Symposium on Computer Architecture. Santa Margherita Ligure, Italy, 1995:392-403.
  • 2Tullsen D M, Eggers S J, Emert J Set al. Exploiting choice: Instruction Fetch and issue on an implementable simultaneous multithreading processor Proceedings of the 23rd Annual International Symposium on Computer Architecture. Philadelphia, USA, 1996:191-202.
  • 3Tullsen D M, Brown J A. Handling long-latency loads in a simultaneous muhithreading proeessor Proeeedings of the 34th Annual International Symposium on Microarehitecture. Austin, USA, 2001: 318-327.
  • 4Robatmili B, Yazdani N, Sardashti Set al. Thread-sensitive instruction issue for SMT processors. IEEE Computer Architecture Letters, 2004, 3(1): 5.
  • 5Raasch S E, Reinhardt S K. The impact of resource partitioning on SMT processors Proceedings of the 12th International Conference on Parallel Architectures and Compilation Techniques. New Orleans, USA, 2003:15-25.
  • 6Cazorla F J, Fernandez E, Ramirez Aet al. Improving memory latency aware fetch policies for SMT processors Proceedings of the 5th International Symposium on High Performance Computing. Orlando, USA, 2003:70-85.
  • 7Cazorla F J, Ramirez A, Valero M et al. DCache warn: An I-Fetch policy to increase SMT efficiency Proceedings of the 18th International Parallel and Distributed Processing Symposium. Santa Fe, USA, 2004:1037-1046.
  • 8El-Moursy A, Albonesi D H. Front-end policies for improved issue efficiency in SMT processors Proceedings of the 9th International Symposium on High-Performance Computer Architecture. Anaheim, USA, 2003:31-40.
  • 9Falcon A, Ramirez A, Valero M. A low-complexity, highperformance fetch unit for simultaneous multithreading processors Proceedings of the 10th International Symposium on High Performance Computer Architecture. Madrid, Spain, 2004:244-253.
  • 10Luo K, Gummaraju J, Franklin M. Balancing throughput and fairness in SMT processors Proceedings of the International Symposium on Performance Analysis of Systems and Software. Tucson, USA, 2001:164-171.

二级参考文献23

  • 1Sima D..The design space of register renaming techniques.IEEE Micro,2000,20(5):70~83
  • 2Lipasti M.H.,Mestan B.R.,Gunadi E..Physical register inlining.In:Proceedings of the 31st International Symposium on Computer Architecture,Munich,2004,325~335
  • 3Balasubramonian R.,Dwarkadas S.,Albonesi D.H..Reducing the complexity of the register file in dynamic superscalar processors.In:Proceedings of the 34th IEEE/ACM International Symposium on Microarchitecture,Austin,2001,237~248
  • 4Postiff M.,Greene D.,Raasch S.et al.Integrating superscalar processor components to implement register caching.In:Proceedings of the International Conference on Supercomputing,Serento,2001,348~357
  • 5González A.,González J.,Valero M..Virtual-physical registers.In:Proceedings of the 4th International Symposium on High-Performance Computer Architecture,Los Alamitos,1998,175~184
  • 6Yang H.,Cui G.,Yang X.Z..Eliminating inter-thread interference in register file for SMT processors.In:Proceedings of the 6th International Conference on Parallel and Distributed Computing,Applications and Technologies.Dalian,2005,40~45
  • 7Cruz J.L.,González A.,Valero M.,Topham N.P..Multiple-banked register file architectures.In:Proceedings of the 27th International Symposium on Computer Architecture,Vancouver,2000,316~325
  • 8Martin M.M.,Roth A.,Fischer C.N..Exploiting dead value information.In:Proceedings of the 30th IEEE/ACM International Symposium on Microarchitecture,Triangle Park,1997,125~135
  • 9Lo J.L.,Parekh S.S.,Eggers S.J.et al.Software-directed Register deallocation for simultaneous multithreaded processors.IEEE Transactions on Parallel and Distributed Systems,1999,10(9):922~933
  • 10Martinez J.F.,Renau J.,Huang M.C.Et al.Cherry:Checkpointed early resource recycling in out-of-order microprocessors.In:Proceedings of the 35th IEEE/ACM International Symposium on Microarchitecture,Istanbul,2002,3~14

共引文献1

同被引文献80

  • 1何立强,刘志勇.一种具有QoS特性的同时多线程处理器取指策略[J].计算机研究与发展,2006,43(11):1980-1984. 被引量:4
  • 2杨华,崔刚,刘宏伟,杨孝宗.基于间隔译码的处理器瞬时故障检测[J].宇航学报,2006,27(6):1328-1334. 被引量:2
  • 3张盛兵,王晶.同时多线程结构的线程预构[J].西北工业大学学报,2007,25(2):159-163. 被引量:2
  • 4Allan A,Edenfetd D,Joyner Jr W H,etal. 2001 Technology Roadmap for Semiconductors[J]. IEEE Corn puter ,2002,35(1) :42-53.
  • 5Weaver C, Emer J, Mukherjee S,et al. Techniques to Reduce the Soft Error Rate of a High-Performance Microprocessor[C]//ISCA 2004. New York: IEEE Press, 2004 : 264-275.
  • 6Ronen R,Mendelson A, Lai K,et al. Coming Challenges in Microarchitecture and Architecture [J]. Proceedings of the IEEE ,2001,89(3) :325-340.
  • 7杨华 崔刚 刘宏伟 等.容错处理器体系结构概述[J].哈尔滨工业大学学报,2006,38:586-590.
  • 8Rotenberg E. AR-SMT: A Microarchitectural Approach to Fault Tolerance in Microprocessors [C]// FTCS 29. New York : IEEE Press, 1999 : 84-91.
  • 9Reinhardt S K,Mukherjee S S. Transient Fault Detection Via Simultaneous Multithreading [C]//ISCA 2000. New York:IEEE Press,2000:25-36.
  • 10Vijaykumar T N, Pomeranz K, Cheng K. Transient Fault Recovery Using Simultaneous Multithreading[C]//ISCA 2002. New York: IEEE Press, 2002: 87-98.

引证文献3

二级引证文献3

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