{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:24:31Z","timestamp":1742948671579,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"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_13","type":"book-chapter","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T09:04:32Z","timestamp":1673341472000},"page":"233-252","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Haica: A High Performance Computing & Artificial Intelligence Fused Computing Architecture"],"prefix":"10.1007","author":[{"given":"Zhengbo","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuoning","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,11]]},"reference":[{"key":"13_CR1","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.micpro.2017.12.009","volume":"57","author":"V Arunachalam","year":"2018","unstructured":"Arunachalam, V., Raj, A.N.J., Hampannavar, N., Bidul, C.: Efficient dual-precision floating-point fused-multiply-add architecture. Microprocess. Microsyst. 57, 23\u201331 (2018)","journal-title":"Microprocess. Microsyst."},{"key":"13_CR2","unstructured":"Chen, Z., Wu, T., Liu, X., Zheng, F., Ding, Y., Li, H.: Design and implementation of a multi-precision mixed floating point fused multiply add component. In: Proceedings of HPC China (2018). (in Chinese)"},{"issue":"2","key":"13_CR3","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/MM.2021.3061394","volume":"41","author":"J Choquette","year":"2021","unstructured":"Choquette, J., Gandhi, W., Giroux, O., Stam, N., Krashinsky, R.: Nvidia a100 tensor core GPU: performance and innovation. IEEE Micro 41(2), 29\u201335 (2021)","journal-title":"IEEE Micro"},{"issue":"3","key":"13_CR4","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1109\/TASLP.2015.2509257","volume":"24","author":"L Dong","year":"2015","unstructured":"Dong, L., Wei, F., Xu, K., Liu, S., Zhou, M.: Adaptive multi-compositionality for recursive neural network models. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(3), 422\u2013431 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Haidar, A., Tomov, S., Dongarra, J., Higham, N.J.: Harnessing GPU tensor cores for fast FP16 arithmetic to speed up mixed-precision iterative refinement solvers. In: SC18: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 603\u2013613. IEEE (2018)","DOI":"10.1109\/SC.2018.00050"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Han, Y., Zhang, G.J., Huang, X., Wang, Y.: A moist physics parameterization based on deep learning. J. Adv. Model. Earth Syst. 12(9), e2020MS002076 (2020)","DOI":"10.1029\/2020MS002076"},{"issue":"5","key":"13_CR7","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1109\/4.62143","volume":"25","author":"E Hokenek","year":"1990","unstructured":"Hokenek, E., Montoye, R.K., Cook, P.W.: Second-generation risc floating point with multiply-add fused. IEEE J. Solid-State Circuits 25(5), 1207\u20131213 (1990)","journal-title":"IEEE J. Solid-State Circuits"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Jia, W., et al.: Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201314. IEEE (2020)","DOI":"10.1109\/SC41405.2020.00009"},{"key":"13_CR9","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":"13_CR10","unstructured":"Kalamkar, D., et al.: A study of bfloat16 for deep learning training. arXiv preprint arXiv:1905.12322 (2019)"},{"key":"13_CR11","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"issue":"3","key":"13_CR12","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1016\/0743-7315(89)90030-0","volume":"7","author":"VP Kumar","year":"1989","unstructured":"Kumar, V.P., Tsai, Y.C.: Designing linear systolic arrays. J. Parallel Distrib. Comput. 7(3), 441\u2013463 (1989)","journal-title":"J. Parallel Distrib. Comput."},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Kurth, T., et al.: Exascale deep learning for climate analytics. In: SC18: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 649\u2013660. IEEE (2018)","DOI":"10.1109\/SC.2018.00054"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Lang, T., Bruguera, J.D.: Floating-point fused multiply-add with reduced latency. In: Proceedings. In: IEEE International Conference on Computer Design: VLSI in Computers and Processors, pp. 145\u2013150. IEEE (2002)","DOI":"10.1109\/ICCD.2002.1106762"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Mohammadi, F.G., Shenavarmasouleh, F., Amini, M.H., Arabnia, H.R.: Malware detection using artificial bee colony algorithm. In: Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers, pp. 568\u2013572 (2020)","DOI":"10.1145\/3410530.3414598"},{"issue":"1","key":"13_CR16","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/s12045-016-0292-x","volume":"21","author":"V Rajaraman","year":"2016","unstructured":"Rajaraman, V.: IEEE standard for floating point numbers. Resonance 21(1), 11\u201330 (2016)","journal-title":"Resonance"},{"key":"13_CR17","unstructured":"Tannenbaum, D.C., Iyer, S.: Logic circuitry configurable to perform 32-bit or dual 16-bit floating-point operations, uS Patent 9,465,578 (11 October 2016)"},{"key":"13_CR18","unstructured":"Wu, T.: The research and implementation of high performance vector FMAC unit for LTE. Ph.D. thesis, National University of Defense Technology (2011). (in Chinese)"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Xiao, Z., Xu, X., Xing, H., Luo, S., Dai, P., Zhan, D.: RTFN: a robust temporal feature network for time series classification. arXiv preprint arXiv:2011.11829 (2020)","DOI":"10.1016\/j.ins.2021.04.053"},{"key":"13_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107338","volume":"229","author":"Z Xiao","year":"2021","unstructured":"Xiao, Z., Xu, X., Xing, H., Song, F., Wang, X., Zhao, B.: A federated learning system with enhanced feature extraction for human activity recognition. Knowl.-Based Syst. 229, 107338 (2021)","journal-title":"Knowl.-Based Syst."},{"issue":"7","key":"13_CR21","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1109\/TC.2019.2895031","volume":"68","author":"H Zhang","year":"2019","unstructured":"Zhang, H., Chen, D., Ko, S.B.: Efficient multiple-precision floating-point fused multiply-add with mixed-precision support. IEEE Trans. Comput. 68(7), 1035\u20131048 (2019)","journal-title":"IEEE Trans. Comput."},{"issue":"1","key":"13_CR22","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/TC.2019.2936192","volume":"69","author":"H Zhang","year":"2019","unstructured":"Zhang, H., Chen, D., Ko, S.B.: New flexible multiple-precision multiply-accumulate unit for deep neural network training and inference. IEEE Trans. Comput. 69(1), 26\u201338 (2019)","journal-title":"IEEE Trans. Comput."}],"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_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T22:40:45Z","timestamp":1728686445000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22677-9_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031226762","9783031226779"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22677-9_13","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)"}}]}}