Learning to superoptimize programs - Workshop Version [article]

Rudy Bunel, Alban Desmaison, M. Pawan Kumar, Philip H.S.Torr, Pushmeet Kohli
2016 arXiv   pre-print
Superoptimization requires the estimation of the best program for a given computational task. In order to deal with large programs, superoptimization techniques perform a stochastic search. This involves proposing a modification of the current program, which is accepted or rejected based on the improvement achieved. The state of the art method uses uniform proposal distributions, which fails to exploit the problem structure to the fullest. To alleviate this deficiency, we learn a proposal
more » ... bution over possible modifications using Reinforcement Learning. We provide convincing results on the superoptimization of "Hacker's Delight" programs.
arXiv:1612.01094v1 fatcat:rjlyc6cflreqhi3p5jlout6ihm