Litcius/Paper detail

GTuner

Qi Sun, Xinyun Zhang, Hao Geng, Yuxuan Zhao, Yang Bai, Haisheng Zheng, Bei Yu

2022Proceedings of the 59th ACM/IEEE Design Automation Conference10 citationsDOI

Abstract

It is an open problem to compile DNN models on GPU and improve the performance. A novel framework, GTuner, is proposed to jointly learn from the structures of computational graphs and the statistical features of codes to find the optimal code implementations. A Graph ATtention network (GAT) is designed as the performance estimator in GTuner. In GAT, graph neural layers are used to propagate the information in the graph and a multi-head self-attention module is designed to learn the complicated relationships between the features. Under the guidance of GAT, the GPU codes are generated through auto-tuning. Experimental results demonstrate that our method outperforms the previous arts remarkably.

Topics & Concepts

Computer scienceCompilerImplementationEstimatorGraphArtificial neural networkTheoretical computer scienceParallel computingComputer engineeringArtificial intelligenceProgramming languageStatisticsMathematicsAdvanced Graph Neural NetworksGraph Theory and AlgorithmsAdvanced Neural Network Applications