Timezone: »

Community Infrastructure for Applying Reinforcement Learning to Compiler Optimizations
Chris Cummins · Bram Wasti · Brandon Cui · Olivier Teytaud · Benoit Steiner · Yuandong Tian · Hugh Leather

Mon Dec 13 02:22 PM -- 02:32 PM (PST) @

Interest in applying Reinforcement Learning (RL) techniques to compiler optimizations is increasing rapidly, but compiler research has a high entry barrier. Unlike in other domains, compiler and RL researchers do not have access to the infrastructure and datasets that enable fast iteration and development of ideas, and getting started requires a significant engineering investment.

We present CompilerGym, a community infrastructure for exposing compiler optimizations as RL environments, and initial results in applying RL to these environments. Our findings suggest two key challenges in RL for compilers is representation learning and transfer learning between program domains.

Author Information

Chris Cummins (Meta)

Chris Cummins is a Research Engineer at Facebook’s AI Research. His research focuses on fusing AI techniques with compilers and systems optimization. Before joining Facebook Chris was a postdoc at the University of Edinburgh where he received Ph.D. and MSc degrees. He completed his MEng degree at Aston University. He is the recipient of numerous best paper awards, the SISCA Best Scottish PhD Award, and the Institute of Engineering and Technology Prize.

Bram Wasti (Facebook)
Brandon Cui (Facebook AI Research)
Olivier Teytaud (Facebook)
Benoit Steiner (Facebook AI Research)
Yuandong Tian (Facebook AI Research)
Hugh Leather (Facebook AI Research)

More from the Same Authors