Energy Efficient Register Renaming
Modern microprocessor designs implement register renaming using register alias tables (RATs), which maintain the mapping between architectural and physical registers. Because of the non-trivial power that is dissipated in a disproportionately small area, the power density in the RAT is significantly higher than in some other datapath components. In this paper, we propose mechanisms to reduce the RAT power and the power density by exploiting the fundamental observation that most of the generated register values are used by the instructions in close proximity to the instruction producing a value. Our first technique disables the RAT lookup for a source register if that register is a destination of an earlier instruction dispatched in the same cycle. The second technique eliminates some of the remaining RAT read accesses even if the source register value is produced by an instruction dispatched in an earlier cycle. This is done by buffering a small number of recent register address translations in a set of external latches and satisfying some RAT lookup requests from these latches. The net result of applying both techniques is a 30% reduction in the RAT energy with no performance penalty, little additional complexity and no cycle time degradation.
KeywordsPerformance Penalty Destination Register Register Address Superscalar Processor Reorder Buffer
Unable to display preview. Download preview PDF.
- 1.Burger, D., Austin, T.M.: The SimpleScalar tool set: Version 2.0., Tech. Report, Dept. of CS, Univ. of Wisconsin–Madison, and documentation for all Simplescalar releases (June 1997)Google Scholar
- 2.Cruz, J.–L., Gonzalez, A., Valero, M., et al.: Multiple–Banked Register File Architecture. In: Proceedings 27th International Symposium on Computer Architecture, pp. 316–325 (2000)Google Scholar
- 3.Ergin, O., et al.: A Circuit–Level Implementation of Fast, Energy–Efficient CMOS Comparators for High–Performance Microprocessors. In: Proceedings of ICCD (2002)Google Scholar
- 4.Folegnani, D., Gonzalez, A.: Energy–Effective Issue Logic. In: Proceedings of International Symposium on Computer Architecture (July 2001)Google Scholar
- 5.Ghose, K., Kamble, M.: Reducing Power in Superscalar Processor Caches Using Subbanking, Multiple Line Buffers and Bit–Line Segmentation. In: Proceedings of International Symposium on Low Power Electronics and Design (ISLPED 1999), August 1999, pp. 70–75 (1999)Google Scholar
- 6.Liu, T., Lu, S.: Performance Improvement with Circuit Level Speculation. In: Proceedings of the 33rd International Symposium on Microarchitecture (2000)Google Scholar
- 8.Manne, S., Klauser, A., Grunwald, D.: Pipeline Gating: Speculation Control for Energy Reduction. In: Proceedings of the 25th International Symposium on Computer Architecture (ISCA), pp. 132–141 (1998)Google Scholar
- 9.Moshovos, A.: Power–Aware Register Renaming. Technical Report, University of Toronto (August 2002)Google Scholar
- 10.Ponomarev, D., Kucuk, G., Ghose, K.: AccuPower: an Accurate Power Estimation Tool for Superscalar Microprocessors. In: Proceedings of 5th Design, Automation and Test in Europe Conference (DATE-2002) (March 2002)Google Scholar
- 11.Pollack, F.: New Microarchitecture Challenges in the Coming Generations of CMOS Process Technologies. In: 32nd International Symposium on Microarchitecture (November 1999) (keynote presentation)Google Scholar