DOTA: detect and omit weak attentions for scalable transformer acceleration
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Transformer Neural Networks have demonstrated leading performance in many applications spanning over language understanding, image processing, and generative modeling. Despite the impressive performance, long-sequence Transformer processing is expensive due to quadratic computation complexity and memory consumption of self-attention. In this paper, we present DOTA, an algorithm-architecture co-design that effectively addresses the challenges of scalable Transformer inference. Based on the insight that not all connections in an attention graph are equally important, we propose to jointly optimize a lightweight Detector with the Transformer model to accurately detect and omit weak connections during runtime. Furthermore, we design a specialized system architecture for end-to-end Transformer acceleration using the proposed attention detection mechanism. Experiments on a wide range of benchmarks demonstrate the superior performance of DOTA over other solutions. In summary, DOTA achieves 152.6x and 4.5x performance speedup and orders of magnitude energy-efficiency improvements over GPU and customized hardware, respectively.
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
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
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · arXiv · doi:10.48550/arxiv.2005.12872 · Cited by 18,253
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×
“We first run BERT (large) [12] on question answering task (QA) using the Stanford Question Answering Dataset (SQuAD) [45] v1.”
MethodIn-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
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., & Kalenichenko, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00286 · Cited by 4,114
Zero-shot text-to-image generation
Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., & Sutskever, I. (2021) · arXiv · doi:10.48550/arxiv.2102.12092 · Cited by 2,417
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 1×
“Finally, hardware accelerators for DNNs are related to executing the non-attention components of Transformers [6, 8ś10, 13ś15, 24ś 26, 30, 47, 55].”
MethodGenerating Long Sequences with Sparse Transformers
Child, R., Gray, S., Radford, A., & Sutskever, I. (2019) · arXiv · doi:10.48550/arxiv.1904.10509 · Cited by 1,063
Efficient Content-Based Sparse Attention with Routing Transformers
Roy, A., Saffar, M., Vaswani, A., & Grangier, D. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00353 · Cited by 509 · cited 2×
“Prior work fails to deliver a satisfying solution for weak attention detection, as they either suffer from poor detection quality [18], or from hardware inefficiency [17, 22, 27, 48, 50].”
Background
Research works printed but not linked: 39
- 10.1145/375551.375608 · DOI · Paper page
- 10.1109/ISCA.2018.00061 · DOI · Paper page
- 10.1109/MC.2013.418 · DOI
- Mark Chen, Alec Radford, Rewon Child, Jeffrey Wu, Heewoo Jun, David Luan, and Ilya Sutskever. 2020. Generative Pretraining From Pixels. In Proceedings of the 37th International Conference on Machine Learning, Hal Daumé III and Aarti Singh (Eds.) (Proceedings of Machine Learning Research, Vol. 119). PMLR, 1691–1703. https://proceedings.mlr.press/v119/chen20s.html
- 10.1145/2541940.2541967 · DOI · Paper page
- 10.1109/MICRO.2014.58 · DOI · Paper page
- 10.1109/ISSCC.2016.7418007 · DOI · Paper page
- 10.18653/v1 · doi:10.18653/v1
- 10.1145/2749469.2750389 · DOI · Paper page
- 10.1145/3037697.3037702 · DOI · Paper page
- Suyog Gupta, Ankur Agrawal, Kailash Gopalakrishnan, and Pritish Narayanan. 2015. Deep learning with limited numerical precision. In International conference on machine learning. 1737–1746.
- 10.1109/HPCA47549.2020.00035 · DOI · Paper page
- 10.5555/3122009.3242044 · doi:10.5555/3122009.3242044 · Paper page
- 10.1109/DAC.2018.8465893 · doi:10.1109/dac.2018.8465893
- 10.1145/3307650.3322214 · DOI · Paper page
- Jianqiu Ji Jianmin Li Shuicheng Yan Bo Zhang and Qi Tian. 2012. Super-bit locality-sensitive hashing. In Advances in neural information processing systems. 108–116.
- 10.1109/LCA.2016.2597140 · DOI
- 10.1109/ISCA.2016.41 · DOI · Paper page
- Nikita Kitaev, Lukasz Kaiser, and Anselm Levskaya. 2020. Reformer: The Efficient Transformer. In International Conference on Learning Representations. https://openreview.net/forum?id=rkgNKkHtvB
- 10.1145/3205289.3205295 · DOI
- 10.1145/2694344.2694358 · DOI · Paper page
- 10.1109/MICRO50266.2020.00066 · DOI
- 10.1109/MM.2018.043191125 · DOI
- 10.5555/2002472.2002491 · doi:10.5555/2002472.2002491
- Stephen Merity Caiming Xiong James Bradbury and Richard Socher. 2016. Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843. · arXiv
- 10.1109/ISCA.2018.00063 · DOI · Paper page
- Junki Park, Hyunsung Yoon, Daehyun Ahn, Jungwook Choi, and Jae-Joon Kim. 2020. OPTIMUS: OPTImized matrix MUltiplication Structure for Transformer neural network accelerator. Proceedings of Machine Learning and Systems, 2 (2020), 363–378.
- Niki Parmar, Ashish Vaswani, Jakob Uszkoreit, Lukasz Kaiser, Noam Shazeer, Alexander Ku, and Dustin Tran. 2018. Image transformer. In International Conference on Machine Learning. 4055–4064.
- Jiezhong Qiu, Hao Ma, Omer Levy, Scott Wen tau Yih, Sinong Wang, and Jie Tang. 2020. Blockwise Self-Attention for Long Document Understanding. arxiv:1911.02972. · arXiv
- 10.1007/s10579-012-9211-2 · DOI · Paper page
- Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1, 8 (2019), 9.
- Colin Raffel Noam Shazeer Adam Roberts Katherine Lee Sharan Narang Michael Matena Yanqi Zhou Wei Li and Peter J Liu. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683. · arXiv
- 10.1109/TVLSI.2016.2586379 · DOI
- 10.1109/ISCA.2016.32 · DOI · Paper page
- 10.1109/ISCA.2018.00069 · DOI · Paper page
- Yi Tay, Dara Bahri, Liu Yang, Donald Metzler, and Da-Cheng Juan. 2020. Sparse sinkhorn attention. In International Conference on Machine Learning. 9438–9447. http://proceedings.mlr.press/v119/tay20a.html
- Yi Tay, Mostafa Dehghani, Samira Abnar, Yikang Shen, Dara Bahri, Philip Pham, Jinfeng Rao, Liu Yang, Sebastian Ruder, and Donald Metzler. 2021. Long Range Arena : A Benchmark for Efficient Transformers. In International Conference on Learning Representations. https://openreview.net/forum?id=qVyeW-grC2k
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 6000–6010.
- Manzil Zaheer, Guru Guruganesh, Kumar Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontañón, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, and Amr Ahmed. 2020. Big Bird: Transformers for Longer Sequences. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc’Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https://proceedings.neurips.cc/paper/2020/hash/c8512d142a2d849725f31a9a7a361ab9-Abstract.html
Cited by
A Survey of Techniques for Optimizing Transformer Inference
Chitty-Venkata, K. T., Mittal, S., Emani, M., Vishwanath, V., & Somani, A. K. (2023) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2023.102990 · Cited by 154
ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design
You, H., Sun, Z., Shi, H., Yu, Z., Zhao, Y., Zhang, Y., Li, C., Li, B., & Lin, Y. (2023) · 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca56546.2023.10071027 · Cited by 138
A Survey on Efficient Training of Transformers
Zhuang, B., Liu, J., Pan, Z., He, H., Weng, Y., & Shen, C. (2023) · Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/764 · Cited by 78
Adaptable butterfly accelerator for attention-based NNs via hardware and algorithm co-design
Fan, H., Chau, T., Venieris, S. I., Lee, R., Kouris, A., Luk, W., Lane, N. D., & Abdelfattah, M. S. (2022) · 2022 55th IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro56248.2022.00050 · Cited by 66
“A 3 [14] unstructured dynamic attention SpAtten [6] coarse-grained structured Sanger [15] load-balanced unstructured Energon [16] unstructured ELSA [17] unstructured DOTA [18] unstructured FTRANS [19] None static FFN EdgeBERT [20] None dynamic layer Our work fine-grained structured static attention & FFN”
BackgroundMethodInfluentialSOLE: Hardware-Software Co-design of Softmax and LayerNorm for Efficient Transformer Inference
Wang, W., Zhou, S., Sun, W., Sun, P., & Liu, Y. (2023) · 2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD) · doi:10.1109/iccad57390.2023.10323725 · Cited by 51
“Algorithms like quantization [13]–[15] are developed to diminish memory footprint and reduce computation overhead while many accelerators have also been proposed to expedite inference [16]–[19].”
Metadata
- Authors
- Qu, Z., Liu, L., Tu, F., Chen, Z., Ding, Y., & Xie, Y.
- Venue
- Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems
- Publisher
- ACM
- Published
- 2022-02-22
- Pages
- 14-26
- OpenAlex
- W4214686755
- Cited by
- 130
- References
- 14
- FWCI
- 23.23
- Type
- conference paper
- Language
- en
- Open access
- gold
- Funders
- NSF (2124039)
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: DOTA: detect and omit weak attentions for scalable transformer acceleration. https://app.cochat.ai/papers/10.1145/3503222.3507738
- The paper
- Qu, Z., Liu, L., Tu, F., Chen, Z., Ding, Y., & Xie, Y. (2022). DOTA: detect and omit weak attentions for scalable transformer acceleration. Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems. https://doi.org/10.1145/3503222.3507738
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.