Pipeline gating: speculation control for energy reduction

DMCA

Pipeline gating: speculation control for energy reduction (1998)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Srilatha Manne

Venue:	In Proceedings of the 25th Annual International Symposium on Computer Architecture
Citations:	288 - 3 self

BibTeX

@INPROCEEDINGS{Manne98pipelinegating:,
    author = {Srilatha Manne},
    title = {Pipeline gating: speculation control for energy reduction},
    booktitle = {In Proceedings of the 25th Annual International Symposium on Computer Architecture},
    year = {1998},
    pages = {132--141}
}

OpenURL

Abstract

Branch prediction has enabled microprocessors to increase instruction level parallelism (ILP) by allowing programs to speculatively execute beyond control boundaries. Although speculative execution is essential for increasing the instructions per cycle (IPC), it does come at a cost. A large amount of unnecessary work results from wrong-path instructions entering the pipeline due to branch misprediction. Results generated with the SimpleScalar tool set using a 4-way issue pipeline and various branch predictors show an instruction overhead of 16 % to 105 % for every instruction committed. The instruction overhead will increase in the future as processors use more aggressive speculation and wider issue widths [9]. In this paper, we present an innovative method for power reduction which, unlike previous work that sacrificed flexibility or performance, reduces power in high-performance microprocessors without impacting performance. In particular, we introduce a hardware mechanism called pipeline gating to control rampant speculation in the pipeline. We present inexpensive mechanisms for determining when a branch is likely to mispredict, and for stopping wrong-path instructions from entering the pipeline. Results show up to a 38 % reduction in wrong-path instructions with a negligible performance loss ( ¢¡¤ £). Best of all, even in programs with a high branch prediction accuracy, performance does not noticeably degrade. Our analysis indicates that there is little risk in implementing this method in existing processors since it does not impact performance and can benefit energy reduction. 1

Keyphrases

energy reduction speculation control pipeline gating wrong-path instruction instruction overhead branch prediction 4-way issue pipeline control boundary speculative execution rampant speculation high branch prediction accuracy hardware mechanism power reduction present inexpensive mechanism simplescalar tool previous work aggressive speculation high-performance microprocessor unnecessary work result innovative method various branch predictor instruction level parallelism negligible performance loss issue width little risk large amount

DMCA