Adaptive VP decay: making value predictors leakage-efficient designs for high performance processors

ABSTRACT

Energy-efficient microprocessor designs are one of the major concerns in both high performance and embedded processor domains. Furthermore, as process technology advances toward deep submicron, static power dissipation becomes a new challenge to address, especially for large on-chip array structures such as caches or prediction tables. Value prediction emerged in the recent past as a very effective way of increasing processor performance by overcoming data dependences. The more accurate the value predictor is the more performance is obtained, at the expense of becoming a source of power consumption and a thermal hot spot, and therefore increasing its leakage. Recent techniques, aimed at reducing the leakage power of array structures such as caches, either switch off (non-state preserving) or reduce the voltage level (state-preserving) of unused array portions.In this paper we propose the design of leakage-efficient value predictors by applying adaptive decay techniques in order to disable unused entries in the prediction tables. As value predictors are implemented as non-tagged structures an adaptive decay scheme has no way to precisely determine the induced miss-ratio due to prematurely decaying an entry. This paper explores adaptive decay strategies suited for the particularities of value predictors (Stride, DFCM and FCM) studying the tradeoffs for these prediction structures, that exhibit different pattern access behaviour than caches, in order to reduce their leakage energy efficiently compromising neither VP accuracy nor the speedup provided. Results show average leakage energy reductions of 52%, 70% and 80% for the Stride, DFCM and FCM value predictors of 20 KB respectively.

REFERENCES

• 1: J. Adam Butts , Gurindar S. Sohi, A static power model for architects, Proceedings of the 33rd annual ACM/IEEE international symposium on Microarchitecture, p.191-201, December 2000, Monterey, California, United States [doi>10.1145/360128.360148]
• 2: Brad Calder , Glenn Reinman , Dean M. Tullsen, Selective value prediction, Proceedings of the 26th annual international symposium on Computer architecture, p.64-74, May 01-04, 1999, Atlanta, Georgia, United States
• 3: J.M. Cebrián, J.L. Aragón and J.M. García. "Leakage Energy Reduction in Value Predictors through Static Decay". In Proc. of the Int. Workshop on High-Performance, Power-Aware Computing HP-PAC'07 (in conjunction with IPDPS'07), March 2007.
• 4: Krisztián Flautner , Nam Sung Kim , Steve Martin , David Blaauw , Trevor Mudge, Drowsy caches: simple techniques for reducing leakage power, Proceedings of the 29th annual international symposium on Computer architecture, May 25-29, 2002, Anchorage, Alaska
• 5: Michael J. Flynn , Patrick Hung, Microprocessor Design Issues: Thoughts on the Road Ahead, IEEE Micro, v.25 n.3, p.16-31, May 2005 [doi>10.1109/MM.2005.56]
• 6: F. Gabbay and A. Mendelson. "Speculative execution based on value prediction". Technical Report 1080, Technion -- Israel Institute of Technology, 1997.
• 7: Bart Goeman , Hans Vandierendonck , Koen de Bosschere, Differential FCM: Increasing Value Prediction Accuracy by Improving Table Usage Efficiency, Proceedings of the 7th International Symposium on High-Performance Computer Architecture, p.207, January 20-24, 2001
• 8: Applying Decay Strategies to Branch Predictors for Leakage Energy Savings, Proceedings of the 2002 IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD'02), p.442, September 16-18, 2002
• 9: Yingmin Li , Dharmesh Parikh , Yan Zhang , Karthik Sankaranarayanan , Mircea Stan , Kevin Skadron, State-Preserving vs. Non-State-Preserving Leakage Control in Caches, Proceedings of the conference on Design, automation and test in Europe, p.10022, February 16-20, 2004
• 10: Mikko H. Lipasti , Christopher B. Wilkerson , John Paul Shen, Value locality and load value prediction, Proceedings of the seventh international conference on Architectural support for programming languages and operating systems, p.138-147, October 01-04, 1996, Cambridge, Massachusetts, United States
• 11: Philo Juang , Kevin Skadron , Margaret Martonosi , Zhigang Hu , Douglas W. Clark , Philip W. Diodato , Stefanos Kaxiras, Implementing branch-predictor decay using quasi-static memory cells, ACM Transactions on Architecture and Code Optimization (TACO), v.1 n.2, p.180-219, June 2004 [doi>10.1145/1011528.1011531]
• 12: S. Kaxiras, Z. Hu and M. Martonosi. "Cache Decay: Exploiting Generational Behavior to Reduce Cache Leakage Power". In
• 13: A. Kesharvarzi. "Intrinsic iddq: Origins, reduction, and applications in deep sub-micron low-power CMOS IC's". In Proc. of the IEEE International Test Conference, 1997.
• 14: Nam Sung Kim , Todd Austin , David Blaauw , Trevor Mudge , Krisztián Flautner , Jie S. Hu , Mary Jane Irwin , Mahmut Kandemir , Vijaykrishnan Narayanan, Leakage Current: Moore's Law Meets Static Power, Computer, v.36 n.12, p.68-75, December 2003 [doi>10.1109/MC.2003.1250885]
• 15: Nevin Kirman , Meyrem Kirman , Mainak Chaudhuri , Jose F. Martinez, Checkpointed Early Load Retirement, Proceedings of the 11th International Symposium on High-Performance Computer Architecture, p.16-27, February 12-16, 2005 [doi>10.1109/HPCA.2005.9]
• 16: Michael Powell , Se-Hyun Yang , Babak Falsafi , Kaushik Roy , T. N. Vijaykumar, Gated-Vdd: a circuit technique to reduce leakage in deep-submicron cache memories, Proceedings of the 2000 international symposium on Low power electronics and design, p.90-95, July 25-27, 2000, Rapallo, Italy [doi>10.1145/344166.344526]
• 17: Yiannakis Sazeides , James E. Smith, The predictability of data values, Proceedings of the 30th annual ACM/IEEE international symposium on Microarchitecture, p.248-258, December 01-03, 1997, Research Triangle Park, North Carolina, United States
• 18: Se-Hyun Yang , Babak Falsafi , Michael D. Powell , Kaushik Roy , T. N. Vijaykumar, An Integrated Circuit/Architecture Approach to Reducing Leakage in Deep-Submicron High-Performance I-Caches, Proceedings of the 7th International Symposium on High-Performance Computer Architecture, p.147, January 20-24, 2001
• 19: Y. Zhang, D. Paritkh, K. Sankaranarayanan, K.Skadron and M. Stan. "HotLeakage: a temperature-aware model of subthreshold and gate leakage for architects". Technical Report, Dept. Comp. Science, U. Virginia, 2003.
• 20: Huiyang Zhou , Mark C. Toburen , Eric Rotenberg , Thomas M. Conte, Adaptive Mode Control: A Static-Power-Efficient Cache Design, Proceedings of the 2001 International Conference on Parallel Architectures and Compilation Techniques, p.61, September 08-12, 2001

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.1 PROCESSOR ARCHITECTURES
      C.1.1 Single Data Stream Architectures
          Subjects: RISC/CISC, VLIW architectures

General Terms:
Design, Measurement, Performance

Keywords:
cache decay, energy efficient architectures, leakage, value prediction