CNNs applied to global history improve prediction accuracy for hard-to-predict branches in SPEC 2017, with hardware-adapted inference and reusability across inputs.
Experiments with SPEC CPU 2017: Similarity, Balance, Phase Behavior and Simpoints
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Improving Branch Prediction By Modeling Global History with Convolutional Neural Networks
CNNs applied to global history improve prediction accuracy for hard-to-predict branches in SPEC 2017, with hardware-adapted inference and reusability across inputs.