NeurIPS 2020poster38 citations
AdaTune: Adaptive Tensor Program Compilation Made Efficient
Menghao Li, Minjia Zhang, Chi Wang, Mingqin Li
Abstract
Deep learning models are computationally intense, and implementations often have to be highly optimized by experts or hardware vendors to be usable in practice. The DL compiler, together with Learning to Compile have proven to be a powerful technique for optimizing tensor programs. However, a limitation of this approach is that it still suffers from unbearably long overall optimization time.
BibTeX
@inproceedings{NEURIPS2020_a9b7ba70,
author = {Li, Menghao and Zhang, Minjia and Wang, Chi and Li, Mingqin},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {14807--14819},
publisher = {Curran Associates, Inc.},
title = {AdaTune: Adaptive Tensor Program Compilation Made Efficient},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/a9b7ba70783b617e9998dc4dd82eb3c5-Paper.pdf},
volume = {33},
year = {2020}
}