{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:30:19Z","timestamp":1742913019218,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031226762"},{"type":"electronic","value":"9783031226779"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-22677-9_28","type":"book-chapter","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T09:04:32Z","timestamp":1673341472000},"page":"529-547","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SparG: A Sparse GEMM Accelerator for Deep Learning Applications"],"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":"Yuan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,11]]},"reference":[{"issue":"1","key":"28_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":"28_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":"28_CR3","doi-asserted-by":"crossref","unstructured":"Acun, B., Murphy, M., Wang, X., et al.: Understanding training efficiency of deep learning recommendation models at scale. In: HPCA2021, pp. 802\u2013814. IEEE (2021)","DOI":"10.1109\/HPCA51647.2021.00072"},{"issue":"2","key":"28_CR4","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1109\/TNNLS.2020.2979670","volume":"32","author":"DW Otter","year":"2020","unstructured":"Otter, D.W., Medina, J.R., Kalita, J.K.: A survey of the usages of deep learning for natural language processing. IEEE Trans. Neural Netw. Learn. Syst. 32(2), 604\u2013624 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"28_CR5","unstructured":"AI and Compute, https:\/\/openai.com\/blog\/ai-and-compute\/, last accessed 2022\/04\/01"},{"key":"28_CR6","unstructured":"Jouppi, N.P., et al.: In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, pp 1\u201312. (2017)"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Qin, E., Samajdar, A., Kwon, H., et al.: Sigma: a sparse and irregular gemm accelerator with flexible interconnects for dnn training. In: HPCA2020, pp. 28\u201370. IEEE (2020)","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"28_CR8","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","volume":"77","author":"J Gu","year":"2018","unstructured":"Gu, J., Wang, Z., Kuen, J., et al.: Recent advances in convolutional neural networks. Pattern Recogn. 77, 354\u2013377 (2018)","journal-title":"Pattern Recogn."},{"key":"28_CR9","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., et al.: Imagenet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 25, 1097\u20131105 (2012)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"11","key":"28_CR10","doi-asserted-by":"publisher","first-page":"1663","DOI":"10.1109\/TC.2019.2924215","volume":"68","author":"J Li","year":"2019","unstructured":"Li, J., Jiang, S., Gong, S., Wu, J., et al.: Squeezeflow: a sparse CNN accelerator exploiting concise convolution rules. IEEE Trans. Comput. 68(11), 1663\u20131677 (2019)","journal-title":"IEEE Trans. Comput."},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Cao, S., Ma, L., Xiao, W., Zhang, C., et al.: Seernet: predicting convolutional neural network feature-map sparsity through low-bit quantization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11216\u201311225 (2019)","DOI":"10.1109\/CVPR.2019.01147"},{"issue":"1","key":"28_CR12","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"28_CR13","first-page":"1135","volume":"28","author":"S Han","year":"2015","unstructured":"Han, S., Pool, J., Tran, J., et al.: 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":"28_CR14","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., et al.: Cnvlutin: Ineffectual-neuron-free deep neural network computing. ACM SIGARCH Comput. Arch. News 44(3), 1\u201313 (2016)","journal-title":"ACM SIGARCH Comput. Arch. News"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Gupta, U., Reagen, B., Pentecost, L., Donato, M., et al.: Masr: a modular accelerator for sparse rnns. In: 2019 28th International Conference on Parallel Architectures and Compilation Techniques (PACT), pp. 1\u201314. IEEE (2019)","DOI":"10.1109\/PACT.2019.00009"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, Z., Han, S.: Spatten: efficient sparse attention architecture with cascade token and head pruning. In: HPCA2021, pp. 97\u2013110. IEEE (2021)","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Yazdanbakhsh, A., Samadi, K., Kim, N.S., et al.: Ganax: a unified mimd-simd acceleration for generative adversarial networks. In: ISCA2018, pp. 650\u2013661. IEEE (2018)","DOI":"10.1109\/ISCA.2018.00060"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Horowitz, M.: 1.1 computing's energy problem (and what we can do about it). In: 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC), pp. 10\u201314. IEEE (2014)","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Chakrabarty, A., Collier, M., Mukhopadhyay, S.: Matrix-based nonblocking routing algorithm for Bene\u0161 networks. In: 2009 Computation World: Future Computing, Service Computation, Cognitive, Adaptive, Content, Patterns, pp. 551\u2013556. IEEE (2009)","DOI":"10.1109\/ComputationWorld.2009.72"},{"issue":"2","key":"28_CR20","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1145\/3296957.3173176","volume":"53","author":"H Kwon","year":"2018","unstructured":"Kwon, H., Samajdar, A., et al.: Maeri: enabling flexible dataflow mapping over dnn accelerators via reconfigurable interconnects. ACM SIGPLAN Notices 53(2), 461\u2013475 (2018)","journal-title":"ACM SIGPLAN Notices"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Chen, Y.-H., Krishna, T., Emer, J.S., Sze, V.: Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J. Solid-State Circuits 52(1), 127\u2013138 (2017)","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, S., Du, Z., Zhang, L., et al.: Cambricon-X: an accelerator for sparse neural networks. In: MICRO2016, pp. 1\u201312. IEEE (2016)","DOI":"10.1109\/MICRO.2016.7783723"},{"issue":"2","key":"28_CR23","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/3140659.3080254","volume":"45","author":"A Parashar","year":"2017","unstructured":"Parashar, A., Rhu, M., et al.: SCNN: An accelerator for compressed-sparse convolutional neural networks. ACM SIGARCH Comput. Arch. News 45(2), 27\u201340 (2017)","journal-title":"ACM SIGARCH Comput. Arch. News"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Gondimalla, A., Chesnut, N., Thottethodi, M., et al.: Sparten: a sparse tensor accelerator for convolutional neural networks. In: MICRO2019, pp. 151\u2013165 (2019)","DOI":"10.1145\/3352460.3358291"},{"issue":"3","key":"28_CR25","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1145\/3007787.3001163","volume":"44","author":"S Han","year":"2016","unstructured":"Han, S., Liu, X., Mao, H., et al.: EIE: Efficient inference engine on compressed deep neural network. ACM SIGARCH Comput. Arch. News 44(3), 243\u2013254 (2016)","journal-title":"ACM SIGARCH Comput. Arch. News"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Hegde, K., Asghari-Moghaddam, H., Pellauer, M., et al.: Extensor: an accelerator for sparse tensor algebra. In: MICRO2019, pp. 319\u2013333 (2019)","DOI":"10.1145\/3352460.3358275"},{"issue":"2","key":"28_CR27","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1109\/JETCAS.2019.2910232","volume":"9","author":"YH Chen","year":"2019","unstructured":"Chen, Y.H., Yang, T.J., Emer, J., et al.: Eyeriss v2: A flexible accelerator for emerging deep neural networks on mobile devices. IEEE J. Emerg. Sel. Top. Circuits Syst. 9(2), 292\u2013308 (2019)","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst."},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Lu, W., Yan, G., Li, J., et al.: Flexflow: a flexible dataflow accelerator architecture for convolutional neural network. In: HPCA2017, pp. 553\u2013564. IEEE (2017)","DOI":"10.1109\/HPCA.2017.29"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-22677-9_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T09:11:19Z","timestamp":1673341879000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22677-9_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031226762","9783031226779"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22677-9_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"11 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Copenhagen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denmark","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":"10 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"91","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":"33","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":"10","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":"36% - 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":"5","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)"}}]}}