Identifying and exploiting sparse branch correlations for optimizing branch prediction

Abstract summary

This work investigates how a small set of past branch outcomes can explain useful correlations for processor branch prediction. It uses sparse modeling to identify these relationships and proposes a compact prediction mechanism that stores the resulting models. Experiments examine prediction accuracy and the hardware cost of using sparse correlations.

Abstract on arXiv

arXiv PDF

Cite this work

@misc{identifyingandexploitingsparsebranchcorrelationsforoptimizingbranchprediction,
  title = {Identifying and exploiting sparse branch correlations for optimizing branch prediction},
  author = {Anastasios Zouzias and Kleovoulos Kalaitzidis and Konstantin Berestizshevsky and Renzo Andri and Leeor Peled and Zhe Wang},
  year = {2022},
  note = {arXiv},
  url = {https://arxiv.org/abs/2207.14033}
}

Download