25902

Generating GPU Compiler Heuristics using Reinforcement Learning

Ian Colbert, Jake Daly, Norm Rubin
Advanced Micro Devices, Inc.
arXiv:2111.12055 [cs.LG], (23 Nov 2021)

@misc{colbert2021generating,

   title={Generating GPU Compiler Heuristics using Reinforcement Learning},

   author={Ian Colbert and Jake Daly and Norm Rubin},

   year={2021},

   eprint={2111.12055},

   archivePrefix={arXiv},

   primaryClass={cs.LG}

}

Download Download (PDF)   View View   Source Source   

323

views

GPU compilers are complex software programs with many optimizations specific to target hardware. These optimizations are often controlled by heuristics hand-designed by compiler experts using time- and resource-intensive processes. In this paper, we developed a GPU compiler autotuning framework that uses off-policy deep reinforcement learning to generate heuristics that improve the frame rates of graphics applications. Furthermore, we demonstrate the resilience of these learned heuristics to frequent compiler updates by analyzing their stability across a year of code check-ins without retraining. We show that our machine learning-based compiler autotuning framework matches or surpasses the frame rates for 98% of graphics benchmarks with an average uplift of 1.6% up to 15.8%.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2022 hgpu.org

All rights belong to the respective authors

Contact us: