History length adjustable gshare predictor for high-performance embedded processor

Authors:
Jong Wook Kwak;Seong Tae Jhang;Chu Shik Jhon
Affiliations:
Department of Electrical Engineering and Computer Science, Seoul National University, Seoul, Korea;Department of Computer Science, The University of Suwon, Suwon, Gyeonggi-do, Korea;Department of Electrical Engineering and Computer Science, Seoul National University, Seoul, Korea
Venue:
ICCSA'06 Proceedings of the 2006 international conference on Computational Science and Its Applications - Volume Part IV
Year:
2006

Citing 5
Cited 0

Two-level adaptive training branch prediction

MICRO 24 Proceedings of the 24th annual international symposium on Microarchitecture
Dynamic history-length fitting: a third level of adaptivity for branch prediction

Proceedings of the 25th annual international symposium on Computer architecture
Variable length path branch prediction

Proceedings of the eighth international conference on Architectural support for programming languages and operating systems
ARM System-on-Chip Architecture

ARM System-on-Chip Architecture
Elastic History Buffer: A Low-Cost Method to Improve Branch Prediction Accuracy

ICCD '97 Proceedings of the 1997 International Conference on Computer Design (ICCD '97)

Quantified Score

Hi-index	0.00

Visualization

Abstract

As modern microprocessros and embedded processors employ deeper pipelines and issue multiple instructions per cycle, accurate branch predictors become an essential part of processor architectures. In this paper, we introduce a history length adjustable gshare predictor for the high-performance embedded processors and show its low-level implementation. Compared to the previous gshare predictor, history length adjustable gshare predictor selectively utilizes the branch history, resulting in substantial improvement in branch prediction accuracy.