Employing both inter-branch and intra-branch correlation to improve the accuracy of branch prediction
نویسندگان
چکیده
Today’s superscalar processors use branch prediction to reduce the influence of control hazards. Conventional two-level branch predictors make predictions based on either intra-branch correlation or inter-branch correlation. In the paper, the authors proposed two new branch predictors, called PGXg and PGAg, which make predictions by employing both intra-branch correlation and inter-branch correction. It is shown that the proposed branch predictors can achieve a better cost-performance ratio than conventional two-level branch predictors, such as PAg and gshare. Keyword: superscalar processor, branch prediction, speculative execution, two-level branch predictor
منابع مشابه
Exploiting Intra-function Correlation with the Global History Stack
The demand for more computation power in high-end embedded systems has put embedded processors on parallel evolution track as the RISC processors. Caches and deeper pipelines are standard features on recent embedded microprocessors. As a result of this, some of the performance penalties associated with branch instructions in RISC processors are becoming more prevalent in these processors. As is...
متن کاملThe Cascaded Predictor: Economic and Adaptive Branch Target Prediction
Two-level predictors improve branch prediction accuracy by allowing predictor tables to hold multiple predictions per branch. Unfortunately, the accuracy of such predictors is impaired by two detrimental effects. Capacity misses increase since each branch may occupies entries proportional to the number of different path histories leading up to the branch. The working set of a given program ther...
متن کاملThe Significance of Affectors and Affectees Correlations for Branch Prediction
This work investigates the potential of direction-correlations to improve branch prediction. There are two types of direction-correlation: affectors and affectees. This work considers for the first time their implications at a basic level. These correlations are determined based on dataflow graph information and are used to select the subset of global branch history bits used for prediction. If...
متن کاملBranch Prediction: a Criticism and a Novel Scheme
The main aim of this work is to propose a new Two Level Adaptive Branch Prediction scheme, based on a new additional correlation information. We prove that branch's history is insufficient for a good branch correlation and as a consequence, for high prediction accuracy. Also, we investigate comparatively, through a trace driven simulation method, a classical branch prediction scheme called GAp,...
متن کاملDynamic per-branch history length adjustment to improve branch prediction accuracy
Branch misprediction limits processor performance signiWcantly, as the pipeline deepens and the instruction issued per cycle increases. Since the introduction of the two-level adaptive branch predictor, branch history has been a major input vector in branch prediction, together with the address of a branch instruction. Until now, the length of branch history has been statically Wxed for all bra...
متن کامل