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
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.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 3×
“We compare the performance and the model size of five DNNs: LeNet-300-100 [32], LeNet-5 [32], ConvNet [28], Network-in-Network (NIN) [34] and AlexNet [29].”
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
(2014) · Cited by 33,419
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
A unified architecture for natural language processing: deep neural networks with multitask learning
Collobert, R., & Weston, J. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390177 · Cited by 5,058
(1989) · Cited by 3,214
MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
Chen, T., Li, M., Li, Y., Lin, M., Wang, N., Wang, M., Xiao, T., Xu, B., Zhang, C., & Zhang, Z. (2015) · arXiv · doi:10.48550/arxiv.1512.01274 · Cited by 1,819
ISAAC: a convolutional neural network accelerator with in-situ analog arithmetic in crossbars
Shafiee, A., Nag, A., Muralimanohar, N., Balasubramonian, R., Strachan, J. P., Hu, M., Williams, R. S., & Srikumar, V. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001139 · Cited by 1,536
DaDianNao: A Machine-Learning Supercomputer
Chen, Y., Luo, T., Liu, S., Zhang, S., He, L., Wang, J., Li, L., Chen, T., Xu, Z., Sun, N., et al. (2014) · 2014 47th Annual IEEE/ACM International Symposium on Microarchitecture · doi:10.1109/micro.2014.58 · Cited by 1,492
Deep Learning with Limited Numerical Precision
Gupta, S., Agrawal, A., Gopalakrishnan, K., & Narayanan, P. (2015) · arXiv · doi:10.48550/arxiv.1502.02551 · Cited by 1,364 · cited 1×
“[17] demonstrates that DNN can be trained with the 16bit fixed-point representation using stochastic rounding.”
Do Deep Nets Really Need to be Deep?
Ba, J. L., & Caruana, R. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1312.6184 · Cited by 1,335
DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning
Chen, T., Du, Z., Sun, N., Wang, J., Wu, C., Chen, Y., & Temam, O. (2014) · Proceedings of the 19th international conference on Architectural support for programming languages and operating systems · doi:10.1145/2541940.2541967 · Cited by 1,297
Chi, P., Li, S., Xu, C., Zhang, T., Zhao, J., Liu, Y., Wang, Y., & Xie, Y. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001140 · Cited by 1,231
Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks
Chen, Y.-H., Emer, J., & Sze, V. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001177 · Cited by 1,182
GradientBased Learning Applied to Document Recognition
(2009) · Intelligent Signal Processing · doi:10.1109/9780470544976.ch9 · Cited by 1,135
EIE: Efficient Inference Engine on Compressed Deep Neural Network
Han, S., Liu, X., Mao, H., Pu, J., Pedram, A., Horowitz, M. A., & Dally, W. J. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.30 · Cited by 1,077
cuDNN: Efficient Primitives for Deep Learning
Chetlur, S., Woolley, C., Vandermersch, P., Cohen, J., Tran, J. J., Catanzaro, B., & Shelhamer, E. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1410.0759 · Cited by 943
ShiDianNao: shifting vision processing closer to the sensor
Du, Z., Fasthuber, R., Chen, T., Ienne, P., Li, L., Luo, T., Feng, X., Chen, Y., & Temam, O. (2015) · Proceedings of the 42nd Annual International Symposium on Computer Architecture · doi:10.1145/2749469.2750389 · Cited by 933
Fast Algorithms for Convolutional Neural Networks
Lavin, A., & Gray, S. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.435 · Cited by 915
ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars
Shafiee, A., Nag, A., Muralimanohar, N., Balasubramonian, R., Strachan, J. P., Hu, M., Williams, R. S., & Srikumar, V. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.12 · Cited by 775
(2011) · Cited by 713
Cnvlutin: ineffectual-neuron-free deep neural network computing
Albericio, J., Judd, P., Hetherington, T., Aamodt, T., Jerger, N. E., & Moshovos, A. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001138 · Cited by 614
Optimal Brain Surgeon and general network pruning
Hassibi, B., Stork, D. G., & Wolff, G. J. (2002) · IEEE International Conference on Neural Networks · doi:10.1109/icnn.1993.298572 · Cited by 597
Chi, P., Li, S., Xu, C., Zhang, T., Zhao, J., Liu, Y., Wang, Y., & Xie, Y. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.13 · Cited by 573
Small-footprint keyword spotting using deep neural networks
Chen, G., Parada, C., & Heigold, G. (2014) · 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2014.6854370 · Cited by 545
BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1Preprint
Courbariaux, M., & Bengio, Y. (2016) · arXiv (Cornell University) · Cited by 484
Predicting Parameters in Deep Learning
Shakibi, B. (2014) · University of British Columbia · doi:10.14288/1.0165555 · Cited by 462
Minerva: enabling low-power, highly-accurate deep neural network accelerators
Reagen, B., Whatmough, P., Adolf, R., Rama, S., Lee, H., Lee, S. K., Hernández-Lobato, J. M., Wei, G.-Y., & Brooks, D. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001165 · Cited by 446
Do Deep Nets Really Need to be DeepPreprint
Ba, L. J., & Caruana, R. (2013) · arXiv (Cornell University) · Cited by 282
DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning
Chen, T., Du, Z., Sun, N., Wang, J., Wu, C., Chen, Y., & Temam, O. (2014) · ACM SIGPLAN Notices · doi:10.1145/2644865.2541967 · Cited by 281
Fast Convolutional Nets With fbfft: A GPU Performance Evaluation
Vasilache, N., Johnson, J., Mathieu, M., Chintala, S., Piantino, S., & LeCun, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.7580 · Cited by 246 · cited 1×
“[43] accelerate DNN by faster convolutional computation into FFT computation, which suffers from extra memory cost.”
Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators
Reagen, B., Whatmough, P., Adolf, R., Rama, S., Lee, H., Lee, S. K., Hernandez-Lobato, J. M., Wei, G.-Y., & Brooks, D. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.32 · Cited by 246
Cnvlutin: Ineffectual-Neuron-Free Deep Neural Network Computing
Albericio, J., Judd, P., Hetherington, T., Aamodt, T., Jerger, N. E., & Moshovos, A. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.11 · Cited by 226
RedEye: analog ConvNet image sensor architecture for continuous mobile vision
LiKamWa, R., Hou, Y., Gao, J., Polansky, M., & Zhong, L. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001164 · Cited by 189
Accelerating pointer chasing in 3D-stacked memory: Challenges, mechanisms, evaluation
Hsieh, K., Khan, S., Vijaykumar, N., Chang, K. K., Boroumand, A., Ghose, S., & Mutlu, O. (2016) · 2016 IEEE 34th International Conference on Computer Design (ICCD) · doi:10.1109/iccd.2016.7753257 · Cited by 175
Reshaping deep neural network for fast decoding by node-pruning
He, T., Fan, Y., Qian, Y., Tan, T., & Yu, K. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6853595 · Cited by 121
RedEye: Analog ConvNet Image Sensor Architecture for Continuous Mobile Vision
LiKamWa, R., Hou, Y., Gao, Y., Polansky, M. G., & Zhong, L. (2016) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca.2016.31 · Cited by 104
Stripes: Bit-Serial Deep Neural Network Computing
Judd, P., Albericio, J., & Moshovos, A. (2016) · IEEE Computer Architecture Letters · doi:10.1109/lca.2016.2597140 · Cited by 66
Deep compression and EIE: Efficient inference engine on compressed deep neural network
Han, S., Liu, X., Mao, H., Pu, J., Pedram, A., Horowitz, M., & Dally, B. (2016) · IEEE Hot Chips Symposium · doi:10.1109/hotchips.2016.7936226 · Cited by 46
A Deep Neural Network Compression Pipeline: Pruning, Quantization, Huffman EncodingPreprint
Han, S., Mao, H., & Dally, W. J. (2015) · arXiv (Cornell University) · Cited by 37
Neural networks with differentiable structurePreprint
Miconi, T. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.06216 · Cited by 18
Research works printed but not linked: 6
- Yiwen Guo, Anbang Yao, and Yurong Chen. 2016. Dynamic Network Surgery for Efficient DNNs. arXiv preprint arXiv:1608.04493 (2016). · arXiv
- 10.5555/2969239.2969366 · doi:10.5555/2969239.2969366
- 10.5555/2969830.2969903 · doi:10.5555/2969830.2969903
- Min Lin, Qiang Chen, and Shuicheng Yan. 2013. Network in network. arXiv preprint arXiv:1312.4400 (2013). · arXiv
- 10.5555/2627435.2670313 · doi:10.5555/2627435.2670313
- 10.1109/ICASSP.2013.6639137 · doi:10.1109/icassp.2013.6639137
Cited by
Efficient Processing of Deep Neural Networks: A Tutorial and Survey
Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2017) · Proceedings of the IEEE · doi:10.1109/jproc.2017.2761740 · Cited by 4,215
“, SIMD) found in existing general purpose hardware, which results in more efficient processing [149]; (2) it amortizes the overhead cost required to signal the location of the non-zero weights across a group of weights, which improves compression and thus reduces storage cost.”
Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey
Deng, B. L., Li, G., Han, S., Shi, L., & Xie, Y. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2020.2976475 · Cited by 996
“For example, the block-wise weight sparsity is leveraged to optimize the running performance on general-purpose processors [13], [220], [234], and a more aggressive diagonal weight matrix is utilized in the accelerator design [282].”
InfluentialFine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
Liu, K., Dolan-Gavitt, B., & Garg, S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-00470-5_13 · Cited by 1,055
Pruning and quantization for deep neural network acceleration: A survey
Liang, T., Glossner, J., Wang, L., Shi, S., & Zhang, X. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.045 · Cited by 943
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
Yang, T.-J., Howard, A., Chen, B., Zhang, X., Go, A., Sandler, M., Sze, V., & Adam, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01249-6_18 · Cited by 572
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
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.