no code implementations • 24 Feb 2021 • Rahim Mammadli, Marija Selakovic, Felix Wolf, Michael Pradel
Applying the transformations that our model deems most favorable prior to compilation yields an average speedup of 1. 14x.
no code implementations • 20 Aug 2020 • Rahim Mammadli, Ali Jannesari, Felix Wolf
Provided with sub-sequences constituting LLVM's O3 sequence, our agent learns to outperform the O3 sequence on the set of source codes used for training and achieves competitive performance on the validation set, gaining up to 1. 32x speedup on previously-unseen programs.