English

Simulating Execution Time of Tensor Programs using Graph Neural Networks

Machine Learning 2019-11-28 v3 Machine Learning

Abstract

Optimizing the execution time of tensor program, e.g., a convolution, involves finding its optimal configuration. Searching the configuration space exhaustively is typically infeasible in practice. In line with recent research using TVM, we propose to learn a surrogate model to overcome this issue. The model is trained on an acyclic graph called an abstract syntax tree, and utilizes a graph convolutional network to exploit structure in the graph. We claim that a learnable graph-based data processing is a strong competitor to heuristic-based feature extraction. We present a new dataset of graphs corresponding to configurations and their execution time for various tensor programs. We provide baselines for a runtime prediction task.

Keywords

Cite

@article{arxiv.1904.11876,
  title  = {Simulating Execution Time of Tensor Programs using Graph Neural Networks},
  author = {Jakub M. Tomczak and Romain Lepert and Auke Wiggers},
  journal= {arXiv preprint arXiv:1904.11876},
  year   = {2019}
}

Comments

All authors contributed equally. Accepted as a workshop paper at Representation Learning on Graphs and Manifolds @ ICLR 2019. Fixed values in Table 1

R2 v1 2026-06-23T08:50:33.764Z