Generating GPU Compiler Heuristics using Reinforcement Learning

2021-11-23 · Ian Colbert, Jake Daly, Norm Rubin

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%.

📄 PDF Abstract BibTeX arXiv:2111.12055

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningGPUreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Finding Missed Code Size Optimizations in Compilers using LLMs

2024-12-31 · Davide Italiano, Chris Cummins

Compilers are complex, and significant effort has been expended on testing them. Techniques such as random program generation and differential testing have proved highly effective and have uncovered thousands of bugs in …

Magellan: Autonomous Discovery of Novel Compiler Optimization Heuristics with AlphaEvolve

2026-01-28 · Hongzheng Chen, Alexander Novikov, Ngân Vũ, Hanna Alam 외 arxiv

Modern compilers rely on hand-crafted heuristics to guide optimization passes. These human-designed rules often struggle to adapt to the complexity of modern software and hardware and lead to high maintenance burden. To …

Learning Branch Probabilities in Compiler from Datacenter Workloads

2022-02-10 · Easwaran Raman, Xinliang David Li

Estimating the probability with which a conditional branch instruction is taken is an important analysis that enables many optimizations in modern compilers. When using Profile Guided Optimizations (PGO), compilers are a…

Deep Data Flow Analysis

2020-11-21 · Chris Cummins, Hugh Leather, Zacharias Fisches, Tal Ben-Nun 외

Compiler architects increasingly look to machine learning when building heuristics for compiler optimization. The promise of automatic heuristic design, freeing the compiler engineer from the complex interactions of prog…

BIG-bench Machine Learning Compiler Optimization

AutoPhase: Juggling HLS Phase Orderings in Random Forests with Deep Reinforcement Learning

2020-03-02 · Qijing Huang, Ameer Haj-Ali, William Moses, John Xiang 외

The performance of the code a compiler generates depends on the order in which it applies the optimization passes. Choosing a good order--often referred to as the phase-ordering problem, is an NP-hard problem. As a resul…

Deep Reinforcement Learning High-Level Synthesis reinforcement-learning Reinforcement Learning+1