Ningxin Zheng, Microsoft Research; Bin Lin, Microsoft Research and Tsinghua University; Quanlu Zhang, Lingxiao Ma, Yuqing Yang, Fan Yang, Yang Wang, Mao Yang, and Lidong Zhou, Microsoft Research
Sparsity is becoming arguably the most critical dimension to explore for efficiency and scalability, as deep learning models grow significantly larger and more complex. After all, the biological neural networks, where deep learning draws inspirations, are naturally sparse and highly efficient.
We advocate an end-to-end approach to model sparsity via a new abstraction called Tensor-with-Sparsity-Attribute (TeSA), which augments the default Tensor abstraction that is fundamentally designed for dense models. TeSA enables the sparsity attributes and patterns (e.g., for pruning and quantization) to be specified, propagated forward and backward across the entire deep learning model, and used to create highly efficient, specialized operators, taking into account the execution efficiency of different sparsity patterns on different (sparsity-aware) hardware. The resulting SparTA framework can accommodate various sparsity patterns and optimization techniques, delivering 1.7x~8.4x average speedup on inference latency compared to seven state-of-the-art (sparse) solutions with smaller memory footprints. As an end-to-end model sparsity framework, SparTA facilitates sparsity algorithms to explore better sparse models.
OSDI '22 Open Access Sponsored by NetApp
Open Access Media
USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.
![](https://www.usenix.org/sites/all/modules/usenix/usenix_files/images/usenix-locked.png)
author = {Ningxin Zheng and Bin Lin and Quanlu Zhang and Lingxiao Ma and Yuqing Yang and Fan Yang and Yang Wang and Mao Yang and Lidong Zhou},
title = {{SparTA}: {Deep-Learning} Model Sparsity via {Tensor-with-Sparsity-Attribute}},
booktitle = {16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)},
year = {2022},
isbn = {978-1-939133-28-1},
address = {Carlsbad, CA},
pages = {213--232},
url = {https://www.usenix.org/conference/osdi22/presentation/zheng-ningxin},
publisher = {USENIX Association},
month = jul
}
![](https://www.usenix.org/sites/default/files/usenix_artifact_evaluation_available_125_update.png)
![](https://www.usenix.org/sites/default/files/usenix_artifact_evaluation_functional_125.png)
![](https://www.usenix.org/sites/default/files/usenix_artifact_evaluation_reproduced_125.png)