PolyGym: Polyhedral Optimizations as an Environment for Reinforcement Learning

The polyhedral model allows a structured way of defining semantics-preserving transformations to improve the performance of a large class of loops. Finding profitable points in this space is a hard problem which is usually approached by heuristics that generalize from domain-expert knowledge. Existi...

Full description

Bibliographic Details

Published in:	2021 30th International Conference on Parallel Architectures and Compilation Techniques (PACT) pp. 17 - 29
Main Authors:	Brauckmann, Alexander, Goens, Andres, Castrillon, Jeronimo
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.09.2021
Subjects:	Benchmark testing loop scheduling machine learning Machine learning algorithms Markov processes PolyGym polyhedral optimization Reinforcement learning Schedules Shape Time measurement
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!