{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:25:21Z","timestamp":1755926721023,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031213946"},{"type":"electronic","value":"9783031213953"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-21395-3_4","type":"book-chapter","created":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T14:34:17Z","timestamp":1670250857000},"page":"42-53","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SADD: A Novel Systolic Array Accelerator with Dynamic Dataflow for Sparse GEMM in Deep Learning"],"prefix":"10.1007","author":[{"given":"Bo","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Libo","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,1]]},"reference":[{"issue":"1","key":"4_CR1","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s10462-018-09679-z","volume":"52","author":"G Nguyen","year":"2019","unstructured":"Nguyen, G., et al.: Machine learning and deep learning frameworks and libraries for large-scale data mining: a survey. Artif. Intell. Rev. 52(1), 77\u2013124 (2019). https:\/\/doi.org\/10.1007\/s10462-018-09679-z","journal-title":"Artif. Intell. Rev."},{"key":"4_CR2","unstructured":"Yang, S., Wang, Y., Chu, X.: A survey of deep learning techniques for neural machine translation. arXiv preprint arXiv:2002.07526 (2020)"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Acun, B., Murphy, M., Wang, X., Nie, J., Wu, C., Hazelwoodet, K.: Understanding training efficiency of deep learning recommendation models at scale. In: IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 802\u2013814. IEEE (2021)","DOI":"10.1109\/HPCA51647.2021.00072"},{"key":"4_CR4","unstructured":"AI and Compute. https:\/\/openai.com\/blog\/ai-and-compute\/ Accessed 01 May 2022"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Qin, E., et al.: Sigma: a sparse and irregular gemm accelerator with flexible interconnects for dnn training. In: HPCA 2020, pp. 28\u201370. IEEE (2020)","DOI":"10.1109\/HPCA47549.2020.00015"},{"issue":"3","key":"4_CR6","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/MM.2018.032271057","volume":"38","author":"N Jouppi","year":"2018","unstructured":"Jouppi, N., Young, C., Patil, N., Patterson, D.: Motivation for and evaluation of the first tensor processing unit. IEEE Micro 38(3), 10\u201319 (2018)","journal-title":"IEEE Micro"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Samajdar, A., Zhu, Y., Whatmough, P., Mattina, M., Krishna, T.: A systematic methodology for characterizing scalability of DNN accelerators using SCALE-sim. In: Proceedings of the IEEE In-ternational Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 58\u201368. IEEE (2020)","DOI":"10.1109\/ISPASS48437.2020.00016"},{"key":"4_CR8","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097\u20131105 (2012)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"4_CR9","first-page":"1135","volume":"28","author":"S Han","year":"2015","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. Adv. Neural Inf. Process. Syst. 28, 1135\u20131143 (2015)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"4_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3007787.3001138","volume":"44","author":"J Albericio","year":"2016","unstructured":"Albericio, J., Judd, P., Hetherington, T., Aamodt, T., Jerger, N.E., Moshovos, A.: Cnvlutin: ineffectual-neuron-free deep neural network computing. ACM SIGARCH Comput. Archit. News 44(3), 1\u201313 (2016)","journal-title":"ACM SIGARCH Comput. Archit. News"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Yazdanbakhsh, A., Samadi, K., Kim, N.S., Esmaeilzadeh, H.: GANAX: a unified MIMD-SIMD acceleration for generative adversarial networks. In: 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA), pp. 650\u2013661. IEEE (2018)","DOI":"10.1109\/ISCA.2018.00060"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Liu, X., Chen, Y., Hao, C., Dhar, A., Chen, D.: WinoCNN: kernel sharing Winograd systolic array for efficient convolutional neural network acceleration on FPGAs. In: 2021 IEEE 32nd International Conference on Application-specific Systems, Architectures and Processors (ASAP), pp. 258\u2013265. IEEE (2021)","DOI":"10.1109\/ASAP52443.2021.00045"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Wang, J., Guo, L., Cong, J.: AutoSA: a polyhedral compiler for high-performance systolic arrays on FPGA. In: The 2021 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 93\u2013104. ACM (2021)","DOI":"10.1145\/3431920.3439292"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Xu, R., Ma, S., Wang, Y., Guo, Y.: CMSA: configurable multi-directional systolic array for convolutional neural networks. In: 2020 IEEE 38th International Conference on Computer Design (ICCD), pp. 494\u2013497. IEEE (2020)","DOI":"10.1109\/ICCD50377.2020.00089"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"He, X., et al.: Sparse-TPU: adapting systolic arrays for sparse matrices. In: Proceedings of the 34th ACM International Conference on Supercomputing, pp. 1\u201312. ACM (2020)","DOI":"10.1145\/3392717.3392751"},{"issue":"6","key":"4_CR16","first-page":"1440","volume":"71","author":"J Yang","year":"2021","unstructured":"Yang, J., Fu, W., Cheng, X., Ye, X., Dai, P., Zhao, W.: S2 engine: a novel systolic architecture for sparse convolutional neural networks. IEEE Trans. Comput. 71(6), 1440\u20131452 (2021)","journal-title":"IEEE Trans. Comput."}],"container-title":["Lecture Notes in Computer Science","Network and Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21395-3_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T14:52:34Z","timestamp":1670251954000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21395-3_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031213946","9783031213953"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21395-3_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Network and Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jinan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"npc2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/npc2022.jlu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"89","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"8","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"26% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}