Preprint · 2021 · Open access

SparseDNN: Fast Sparse Deep Learning Inference on CPUs

Ziheng Wang

arXiv (Cornell University) · Published 20 January 2021 · DOI 10.48550/arxiv.2101.07948

Open PDFView at the publisherCite this paper

In brief

“SparseDNN: Fast Sparse Deep Learning Inference on CPUs” is a 2021 preprint by Ziheng Wang, published in arXiv (Cornell University). OpenAlex counts 29 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
29
Most cited in
2025 (8)
References
40
Authors
1

Abstract

The last few years have seen gigantic leaps in algorithms and systems to support efficient deep learning inference. Pruning and quantization algorithms can now consistently compress neural networks by an order of magnitude. For a compressed neural network, a multitude of inference frameworks have been designed to maximize the performance of the target hardware. While we find mature support for quantized neural networks in production frameworks such as OpenVINO and MNN, support for pruned sparse neural networks is still lacking. To tackle this challenge, we present SparseDNN, a sparse deep learning inference engine targeting CPUs. We present both kernel-level optimizations with a sparse code generator to accelerate sparse operators and novel network-level optimizations catering to sparse networks. We show that our sparse code generator can achieve significant speedups over state-of-the-art sparse and dense libraries. On end-to-end benchmarks such as Huggingface pruneBERT, SparseDNN achieves up to 5x throughput improvement over dense inference with state-of-the-art OpenVINO. Open source library at: https://github.com/marsupialtail/sparsednn.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Wang, Z. (2021). SparseDNN: Fast Sparse Deep Learning Inference on CPUs. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2101.07948

MLA 9

Wang, Ziheng. “SparseDNN: Fast Sparse Deep Learning Inference on CPUs.” arXiv (Cornell University), 2021. https://doi.org/10.48550/arxiv.2101.07948.

Chicago

Wang, Ziheng. 2021. “SparseDNN: Fast Sparse Deep Learning Inference on CPUs.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2101.07948.

Harvard

Wang, Z. (2021) ‘SparseDNN: Fast Sparse Deep Learning Inference on CPUs’, arXiv (Cornell University). doi:10.48550/arxiv.2101.07948.

IEEE

Z. Wang, “SparseDNN: Fast Sparse Deep Learning Inference on CPUs,” arXiv (Cornell University), 2021, doi: 10.48550/arxiv.2101.07948.

BibTeX

@misc{wang2021sparsednn,
  title     = {{SparseDNN: Fast Sparse Deep Learning Inference on CPUs}},
  author    = {Wang, Ziheng},
  howpublished = {arXiv (Cornell University)},
  year      = {2021},
  doi       = {10.48550/arxiv.2101.07948},
  url       = {https://doi.org/10.48550/arxiv.2101.07948}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202122
202244
202355
202477
202588
202633

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • CPU-only inference
  • sparse operators
  • network-level optimization
  • neural network compression

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Wang, Z. (2021). SparseDNN: Fast Sparse Deep Learning Inference on CPUs. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2101.07948

How many times has this paper been cited?

29 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Ziheng Wang.

What is the DOI of this paper?

10.48550/arxiv.2101.07948, permanently at https://doi.org/10.48550/arxiv.2101.07948. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.