The effect of speculatively updating branch history on branch prediction accuracy, revisited

Authors:
Eric Hao;Po-Yung Chang;Yale N. Patt
Affiliations:
Department of Electrical Engineering and Computer Science, The University of Michigan, Ann Arbor, MI;Department of Electrical Engineering and Computer Science, The University of Michigan, Ann Arbor, MI;Department of Electrical Engineering and Computer Science, The University of Michigan, Ann Arbor, MI
Venue:
MICRO 27 Proceedings of the 27th annual international symposium on Microarchitecture
Year:
1994

Citing 7
Cited 19

Reducing the cost of branches

ISCA '86 Proceedings of the 13th annual international symposium on Computer architecture
Checkpoint repair for out-of-order execution machines

ISCA '87 Proceedings of the 14th annual international symposium on Computer architecture
Two-level adaptive training branch prediction

MICRO 24 Proceedings of the 24th annual international symposium on Microarchitecture
Alternative implementations of two-level adaptive branch prediction

ISCA '92 Proceedings of the 19th annual international symposium on Computer architecture
Improving the accuracy of dynamic branch prediction using branch correlation

ASPLOS V Proceedings of the fifth international conference on Architectural support for programming languages and operating systems
A comprehensive instruction fetch mechanism for a processor supporting speculative execution

MICRO 25 Proceedings of the 25th annual international symposium on Microarchitecture
The impact of unresolved branches on branch prediction scheme performance

ISCA '94 Proceedings of the 21st annual international symposium on Computer architecture

The influence of branch prediction table interference on branch prediction scheme performance

PACT '95 Proceedings of the IFIP WG10.3 working conference on Parallel architectures and compilation techniques
Implementation and analysis of path history in dynamic branch prediction schemes

ICS '97 Proceedings of the 11th international conference on Supercomputing
Branch Prediction, Instruction-Window Size, and Cache Size: Performance Trade-Offs and Simulation Techniques

IEEE Transactions on Computers
Offline program re-mapping to improve branch prediction efficiency in embedded systems

ASP-DAC '00 Proceedings of the 2000 Asia and South Pacific Design Automation Conference
A time-stamping algorithm for efficient performance estimation of superscalar processors

Proceedings of the 2001 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Design tradeoffs for the Alpha EV8 conditional branch predictor

ISCA '02 Proceedings of the 29th annual international symposium on Computer architecture
Two cache lines prediction for a wide-issue micro-architecture

ACSAC '01 Proceedings of the 6th Australasian conference on Computer systems architecture
Skipper: a microarchitecture for exploiting control-flow independence

Proceedings of the 34th annual ACM/IEEE international symposium on Microarchitecture
Selective Branch Inversion: Confidence Estimation for Branch Predictors

International Journal of Parallel Programming
Putting Data Value Predictors to Work in Fine-Grain Parallel Processors

HiPC '01 Proceedings of the 8th International Conference on High Performance Computing
Exploiting data-width locality to increase superscalar execution bandwidth

Proceedings of the 35th annual ACM/IEEE international symposium on Microarchitecture
Detecting global stride locality in value streams

Proceedings of the 30th annual international symposium on Computer architecture
Prophet/Critic Hybrid Branch Prediction

Proceedings of the 31st annual international symposium on Computer architecture
Control Flow Modeling in Statistical Simulation for Accurate and Efficient Processor Design Studies

Proceedings of the 31st annual international symposium on Computer architecture
Architectural contesting: exposing and exploiting temperamental behavior

ACM SIGARCH Computer Architecture News - Special issue on the 2006 reconfigurable and adaptive architecture workshop
Impact analysis of performance faults in modern microprocessors

ICCD'09 Proceedings of the 2009 IEEE international conference on Computer design
Recovery logics for speculative update global and local branch history

ISCIS'06 Proceedings of the 21st international conference on Computer and Information Sciences
The Performance Vulnerability of Architectural and Non-architectural Arrays to Permanent Faults

MICRO-45 Proceedings of the 2012 45th Annual IEEE/ACM International Symposium on Microarchitecture
On the Impact of Performance Faults in Modern Microprocessors

Journal of Electronic Testing: Theory and Applications

Quantified Score

Hi-index	0.01

Visualization

Abstract

Recent research has suggested that the branch history register need not contain the outcomes of the most recent branches in order for the Two-Level Adaptive Branch Predictor to work well. From this result, it is tempting to conclude that the branch history register need not be speculatively updated. This paper revisits this work and explains when the most recent branch outcomes can be omitted without significantly affecting performance. It also explains why this result does not imply that speculative update is not important. This paper shows that because the number of unresolved branches present in the machine varies during program execution, branch predictors without speculative update perform significantly worse than branch predictors with speculative update.