Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 272

The DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.

Scalpel: Customizing DNN Pruning to the Underlying Hardware Parallelism

Yu, Jiecao, Lukefahr, Andrew, Palframan, David, Dasika, Ganesh, Das, Reetuparna, Mahlke, Scott·2017·Proceedings of the 44th Annual International Symposium on Computer Architecture

Abstract

As the size of Deep Neural Networks (DNNs) continues to grow to increase accuracy and solve more complex problems, their energy footprint also scales. Weight pruning reduces DNN model size and the computation by removing redundant weights. However, we implemented weight pruning for several popular networks on a variety of hardware platforms and observed surprising results. For many networks, the network sparsity caused by weight pruning will actually hurt the overall performance despite large reductions in the model size and required multiply-accumulate operations. Also, encoding the sparse format of pruned networks incurs additional storage space overhead. To overcome these challenges, we propose Scalpel that customizes DNN pruning to the underlying hardware by matching the pruned network structure to the data-parallel hardware organization. Scalpel consists of two techniques: SIMD-aware weight pruning and node pruning. For low-parallelism hardware (e.g., microcontroller), SIMD-aware weight pruning maintains weights in aligned fixed-size groups to fully utilize the SIMD units. For high-parallelism hardware (e.g., GPU), node pruning removes redundant nodes, not redundant weights, thereby reducing computation without sacrificing the dense matrix format. For hardware with moderate parallelism (e.g., desktop CPU), SIMD-aware weight pruning and node pruning are synergistically applied together. Across the microcontroller, CPU and GPU, Scalpel achieves mean speedups of 3.54x, 2.61x, and 1.25x while reducing the model sizes by 88%, 82%, and 53%. In comparison, traditional weight pruning achieves mean speedups of 1.90x, 1.06x, 0.41x across the three platforms.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3079856.3080215

Cites

46 of 46 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 46 references

Research works printed but not linked: 6

  1. Yiwen Guo, Anbang Yao, and Yurong Chen. 2016. Dynamic Network Surgery for Efficient DNNs. arXiv preprint arXiv:1608.04493 (2016). · arXiv
  2. 10.5555/2969239.2969366 · doi:10.5555/2969239.2969366
  3. 10.5555/2969830.2969903 · doi:10.5555/2969830.2969903
  4. Min Lin, Qiang Chen, and Shuicheng Yan. 2013. Network in network. arXiv preprint arXiv:1312.4400 (2013). · arXiv
  5. 10.5555/2627435.2670313 · doi:10.5555/2627435.2670313
  6. 10.1109/ICASSP.2013.6639137 · doi:10.1109/icassp.2013.6639137

Cited by

See all 272

Metadata

Authors
Yu, J., Lukefahr, A., Palframan, D., Dasika, G., Das, R., & Mahlke, S.
Venue
Proceedings of the 44th Annual International Symposium on Computer Architecture
Publisher
ACM
Published
2017-06-24
Pages
548-560
ISSN
1063-6897 (ISSN-L)
OpenAlex
W2657126969
Cited by
272
References
46
FWCI
14.72
Type
conference paper
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Scalpel: Customizing DNN Pruning to the Underlying Hardware Parallelism. https://app.cochat.ai/papers/10.1145/3079856.3080215
The paper
Yu, J., Lukefahr, A., Palframan, D., Dasika, G., Das, R., & Mahlke, S. (2017). Scalpel: Customizing DNN Pruning to the Underlying Hardware Parallelism. Proceedings of the 44th Annual International Symposium on Computer Architecture. https://doi.org/10.1145/3079856.3080215

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.