Improving the accuracy of history-based branch prediction
- 1 April 1997
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 46 (4) , 469-472
- https://doi.org/10.1109/12.588060
Abstract
In this paper, we present mechanisms that improve the accuracy and performance of history-based branch prediction. By studying the characteristics of the decision structures present in high-level languages, two mechanisms are proposed that reduce the number of wrong predictions made by a branch target buffer (BTB). Execution-driven modeling is used to evaluate the improvement in branch prediction accuracy, as well as the reduction in overall program execution.Keywords
This publication has 7 references indexed in Scilit:
- A Comparison Of Dynamic Branch Predictors That Use Two Levels Of Branch HistoryPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Fast and accurate instruction fetch and branch predictionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A study of branch prediction strategiesPublished by Association for Computing Machinery (ACM) ,1998
- Branch target buffer design and optimizationIEEE Transactions on Computers, 1993
- Improving the accuracy of dynamic branch prediction using branch correlationPublished by Association for Computing Machinery (ACM) ,1992
- Two-level adaptive training branch predictionPublished by Association for Computing Machinery (ACM) ,1991
- Reducing the branch penalty in pipelined processorsComputer, 1988