The Non-Predictability of Mispredicted Branches using Timing Information

TL;DR

This paper investigates whether incorporating microarchitectural timing information can improve branch prediction accuracy, finding limited overall gains but potential benefits for specific hard-to-predict branches, indicating avenues for future research.

Contribution

It introduces Speculative Branch Resolution (SBR), a novel approach that uses timing information to re-predict branches, and provides an analysis of its limited effectiveness and potential for targeted improvements.

Findings

Timing information did not improve overall prediction accuracy with a TAGE-Like predictor.

Two hard-to-predict branches showed prediction improvement with timing data.

Further research is needed to identify microarchitectural features that enhance branch prediction.

Abstract

Branch misprediction latency is one of the most important contributors to performance degradation and wasted energy consumption in a modern core. State-of-the-art predictors generally perform very well but occasionally suffer from high Misprediction Per Kilo Instruction due to hard-to-predict branches. In this work, we investigate if predicting branches using microarchitectural information, in addition to traditional branch history, can improve prediction accuracy. Our approach considers branch timing information (resolution cycle) both for older branches in the Reorder Buffer (ROB) and recently committed, and for younger branches relative to the branch we re-predict. We propose Speculative Branch Resolution (SBR) in which, N cycles after a branch allocates in the ROB, various timing information is collected and used to re-predict. Using the gem5 simulator we implement and perform a limit-study of SBR using a TAGE-Like predictor. Our experiments show that the post-alloc timing information we used was not able to yield performance gains over an unbounded TAGE-SC. However, we find two hard to predict branches where timing information did provide an advantage and thoroughly analysed one of them to understand why. This finding suggests that predictors may benefit from specific microarchitectural information to increase accuracy on specific hard to predict branches and that overriding predictions in the backend may yet yield performance benefits, but that further research is needed to determine such information vectors.