Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights
Open accessThe DOI matches its Crossref record; 60 of the 60 references it cites were found in a registry or an index.
Abstract
Machine learning (ML) models are widely used in many important domains. For efficiently processing these computational- and memory-intensive applications, tensors of these overparameterized models are compressed by leveraging sparsity, size reduction, and quantization of tensors. Unstructured sparsity and tensors with varying dimensions yield irregular computation, communication, and memory access patterns; processing them on hardware accelerators in a conventional manner does not inherently leverage acceleration opportunities. This article provides a comprehensive survey on the efficient execution of sparse and irregular tensor computations of ML models on hardware accelerators. In particular, it discusses enhancement modules in the architecture design and the software support, categorizes different hardware designs and acceleration techniques, analyzes them in terms of hardware and execution costs, analyzes achievable accelerations for recent DNNs, and highlights further opportunities in terms of hardware/software/model codesign optimizations (inter/intramodule). The takeaways from this article include the following: understanding the key challenges in accelerating sparse, irregular shaped, and quantized tensors; understanding enhancements in accelerator systems for supporting their efficient computations; analyzing tradeoffs in opting for a specific design choice for encoding, storing, extracting, communicating, computing, and load-balancing the nonzeros; understanding how structured sparsity can improve storage efficiency and balance computations; understanding how to compile and map models with sparse tensors on the accelerators; and understanding recent design trends for efficient accelerations and further opportunities.
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
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
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · arXiv · doi:10.48550/arxiv.1802.02611 · Cited by 20,063 · cited 2×
“Models for semantic segmentation and language translation often use encoder-decoder structures with convolutions and/or recurrent layers [12], [13], [27].”
BackgroundMethodEncoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_49 · Cited by 20,054
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072 · cited 5×
“models [6], a single dataflow may not be effective in all scenarios [63], [88], leading to significant acceleration loss due to poor PE-array utilization or ineffective interleaving of PE computations with data communication latency.”
BackgroundMethodInfluentialA survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2017) · arXiv · doi:10.48550/arxiv.1707.01083 · Cited by 9,982
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00716 · Cited by 9,982
Learning Spatiotemporal Features with 3D Convolutional Networks
Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.510 · Cited by 9,593
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
Rethinking Atrous Convolution for Semantic Image Segmentation
Chen, L.-C., Papandreou, G., Schroff, F., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1706.05587 · Cited by 7,517
Graph neural networks: A review of methods and applications
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020) · AI Open · doi:10.1016/j.aiopen.2021.01.001 · Cited by 6,880
Graph Neural Networks: A Review of Methods and Applications
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2018) · arXiv · doi:10.48550/arxiv.1812.08434 · Cited by 6,880
Recent advances in convolutional neural networks
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J., et al. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.10.013 · Cited by 6,576
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208 · cited 1×
“E.g., for BERT-base-uncased [8] (92% sparse weights [71]) on SQuAD [138], they achieved about 7.7 × –8.9 × speedup out of 12.2 × speedup for processing at peak.”
MethodInfluentialSqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016) · arXiv · doi:10.48550/arxiv.1602.07360 · Cited by 6,201
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016) · arXiv · doi:10.48550/arxiv.1609.08144 · Cited by 5,319
Deep visual-semantic alignments for generating image descriptions
Karpathy, A., & Fei-Fei, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298932 · Cited by 4,902
Han, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
In-Datacenter Performance Analysis of a Tensor Processing Unit
Jouppi, N. P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., et al. (2017) · Proceedings of the 44th Annual International Symposium on Computer Architecture · doi:10.1145/3079856.3080246 · Cited by 4,537 · cited 10×
“Then, the bottom PE-row provides the reduced partial outputs to accumulator buffers (CompAct [111], TPU [22]).”
BackgroundInfluentialEfficient 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 · cited 7×
“Surveys [28], [64]–[66] provide additional details about various layers used by different deep neural networks (DNNs) [67].”
BackgroundInfluentialLearning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1406.1078 · Cited by 3,317
Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks
Chen, Y.-H., Krishna, T., Emer, J. S., & Sze, V. (2017) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2016.2616357 · Cited by 3,247
End to End Learning for Self-Driving Cars
Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L. D., Monfort, M., Muller, U., Zhang, J., et al. (2016) · arXiv · doi:10.48550/arxiv.1604.07316 · Cited by 3,198
Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks
Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., & Cong, J. (2015) · Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/2684746.2689060 · Cited by 2,158 · cited 3×
“models [35], [36], [80], [143].”
MethodNeural Architecture Search: A Survey
Elsken, T., Metzen, J. H., & Hutter, F. (2018) · arXiv · doi:10.48550/arxiv.1808.05377 · Cited by 1,763
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., & Zou, Y. (2016) · arXiv · doi:10.48550/arxiv.1606.06160 · Cited by 1,690
Learning IoT in Edge: Deep Learning for the Internet of Things with Edge Computing
Li, H., Ota, K., & Dong, M. (2018) · IEEE Network · doi:10.1109/mnet.2018.1700202 · Cited by 1,566 · cited 1×
“n [1]–[6] and detection [7]–[13]), media processing [14]–[22] and generation [23], [24], recommendation systems [25], [26], largescale scientific computing [27], embedded systems [28], edge processing [29], and even for optimizing system executions [30], [31] and designing the hardware [32] and software systems [33]. T…”
BackgroundThe Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Frankle, J., & Carbin, M. (2018) · arXiv · doi:10.48550/arxiv.1803.03635 · Cited by 1,529
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
He, Y., Lin, J., Liu, Z., Wang, H., Li, L.-J., & Han, S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_48 · Cited by 1,400
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
TVM: an automated end-to-end optimizing compiler for deep learning
(2018) · arXiv (Cornell University) · doi:10.5555/3291168.3291211 · Cited by 1,170
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
Lin, Y., Han, S., Mao, H., Wang, Y., & Dally, W. J. (2017) · arXiv · doi:10.48550/arxiv.1712.01887 · Cited by 1,134
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
Cheng, Y., Wang, D., Zhou, P., & Zhang, T. (2018) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2765695 · Cited by 817 · cited 1×
“Compact models: Cheng et al. [265] surveyed techniques for parameter pruning and low-rank factorization.”
MethodTo prune, or not to prune: exploring the efficacy of pruning for model compression
Zhu, M., & Gupta, S. (2017) · arXiv · doi:10.48550/arxiv.1710.01878 · Cited by 805
Quantizing deep convolutional networks for efficient inference: A whitepaper
Krishnamoorthi, R. (2018) · arXiv · doi:10.48550/arxiv.1806.08342 · Cited by 753
Designing Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning
Yang, T.-J., Chen, Y.-H., & Sze, V. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.643 · Cited by 732
Fixed Point Quantization of Deep Convolutional Networks
Lin, D. D., Talathi, S. S., & Annapureddy, V. S. (2015) · arXiv · doi:10.48550/arxiv.1511.06393 · Cited by 684 · cited 4×
“79], [93] or use quantization-aware training [48]. Thus, quantization techniques typically do not degrade inference accuracy [18], [97] or can even trade-off the accuracy with aggressive quantization [50], [94], [138]–[141]. Quantization provides significant storage benefits and enables lower accesses to off-chip memory…”
BackgroundInfluentialAlwani, M., Chen, H., Ferdman, M., & Milder, P. (2016) · 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro.2016.7783725 · Cited by 662 · cited 3×
“3) Fused-layer execution: Fused-layer CNNs [173] lever-aged cross-layer reuse by processing a small tile of activations such that outputs for few layers can be computed alongside while retaining the corresponding data in the on-chip memory.”
BackgroundESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA
Han, S., Kang, J., Mao, H., Hu, Y., Li, X., Li, Y., Xie, D., Luo, H., Yao, S., Wang, Y., et al. (2017) · Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/3020078.3021745 · Cited by 591 · cited 8×
“Primitive Operation Matrix-Vector Multiply [45], [57], [61]–[63], [97], [101], [147], [148], [151], [152], [156], [165], [168] Matrix-Matrix Multiply [62], [107], [144], [151], [152], [163], [167] Convolution [34], [57], [62], [63], [95]–[97], [101], [109], [132], [145]–[151], [153], [155], [157]–[160], [162], [165] R…”
MethodInfluentialTensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions
Vasilache, N., Zinenko, O., Theodoridis, T., Goyal, P., DeVito, Z., Moses, W. S., Verdoolaege, S., Adams, A., & Cohen, A. (2018) · arXiv · doi:10.48550/arxiv.1802.04730 · Cited by 548
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
The State of Sparsity in Deep Neural Networks
Gale, T., Elsen, E., & Hooker, S. (2019) · arXiv · doi:10.48550/arxiv.1902.09574 · Cited by 440
SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
Wang, H., Zhang, Z., & Han, S. (2021) · 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca51647.2021.00018 · Cited by 427
UNPU: An Energy-Efficient Deep Neural Network Accelerator With Fully Variable Weight Bit Precision
Lee, J., Kim, C., Kang, S., Shin, D., Kim, S., & Yoo, H.-J. (2019) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2018.2865489 · Cited by 335
CLIP-Q: Deep Network Compression Learning by In-parallel Pruning-Quantization
Tung, F., & Mori, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00821 · Cited by 220
Benchmarking TinyML Systems: Challenges and Direction
Banbury, C. R., Reddi, V. J., Lam, M., Fu, W., Fazel, A., Holleman, J., Huang, X., Hurtado, R., Kanter, D., Lokhmotov, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2003.04821 · Cited by 216
SBNet: Sparse Blocks Network for Fast Inference
Ren, M., Pokrovsky, A., Yang, B., & Urtasun, R. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00908 · Cited by 198
A Study of BFLOAT16 for Deep Learning Training
Kalamkar, D., Mudigere, D., Mellempudi, N., Das, D., Banerjee, K., Avancha, S., Vooturi, D. T., Jammalamadaka, N., Huang, J., Yuen, H., et al. (2019) · arXiv · doi:10.48550/arxiv.1905.12322 · Cited by 169
Self-citationAccelerating Deep Convolutional Networks using low-precision and sparsity
Venkatesh, G., Nurvitadhi, E., & Marr, D. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952679 · Cited by 123
Compiling KB-sized machine learning models to tiny IoT devices
Gopinath, S., Ghanathe, N., Seshadri, V., & Sharma, R. (2019) · Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation · doi:10.1145/3314221.3314597 · Cited by 92
Software-Hardware Codesign for Efficient Neural Network Acceleration
Guo, K., Han, S., Yao, S., Wang, Y., Xie, Y., & Yang, H. (2017) · IEEE Micro · doi:10.1109/mm.2017.39 · Cited by 78 · cited 1×
“COO [152], [153] COO-1D [101], [109], [147], [148], [158], [161], [165], [167] RLC [34], [95]–[97], [132], [145], [188] Bitmap [57], [62], [110], [132], [144], [146], [149]–[151], [153]–[155], [157] CSR [45] CSC [45], [61], [63], [102], [156], [160], [189] CSF [152]”
An Instruction Set Architecture for Machine Learning
Chen, Y., Lan, H., Du, Z., Liu, S., Tao, J., Han, D., Luo, T., Guo, Q., Li, L., Xie, Y., et al. (2018) · ACM Transactions on Computer Systems · doi:10.1145/3331469 · Cited by 14 · cited 2×
“Chen et al. [237] proposed a programming framework consisting of assembly language, an assembler, and run-time support for executing ML models with their Cambricon ISA.”
BackgroundMethod
Cited by
Hoefler, T., Alistarh, D., Ben-Nun, T., Dryden, N., & Peste, A. (2021) · ETH Zurich · doi:10.3929/ethz-b-000519202 · Cited by 423
Efficient Acceleration of Deep Learning Inference on Resource-Constrained Edge Devices: A Review
Shuvo, M. M. H., Islam, S. K., Cheng, J., & Morshed, B. I. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2022.3226481 · Cited by 436
“Handling sparse and irregular tensors resulted in different DL models, and techniques in hardware are summarized in [15].”
MethodComputing Graph Neural Networks: A Survey from Algorithms to Accelerators
Abadal, S., Jain, A., Guirado, R., López-Alonso, J., & Alarcón, E. (2022) · ACM Computing Surveys · doi:10.1145/3477141 · Cited by 285
Machine Learning for Microcontroller-Class Hardware: A Review
Saha, S. S., Sandha, S. S., & Srivastava, M. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3210773 · Cited by 253
From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks
Geng, X., Wang, Z., Chen, C., Xu, Q., Xu, K., Jin, C., Gupta, M., Yang, X., Chen, Z., Sabry Aly, M. M., et al. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3394494 · Cited by 26
Metadata
- Authors
- Dave, S., Baghdadi, R., Nowatzki, T., Avancha, S., Shrivastava, A., & Li, B.
- Venue
- Proceedings of the IEEE
- Published
- 2021-10
- Volume
- 109
- Issue
- 10
- Pages
- 1706-1752
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W3040646053
- Cited by
- 111
- References
- 60
- FWCI
- 12.03
- Type
- journal article
- Language
- en
- Open access
- green
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.