{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:15:42Z","timestamp":1742991342705,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031396977"},{"type":"electronic","value":"9783031396984"}],"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\/978-3-031-39698-4_18","type":"book-chapter","created":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T06:02:40Z","timestamp":1692770560000},"page":"260-274","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-level Parallel Integer\/Floating-Point Arithmetic Architecture for\u00a0Deep Learning Instructions"],"prefix":"10.1007","author":[{"given":"Hongbing","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Libo","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dezun","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongwen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liquan","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,24]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"IEEE standard for floating-point arithmetic. IEEE Std 754-2019 (Revision of IEEE 754-2008), pp. 1\u201384 (2019). https:\/\/doi.org\/10.1109\/IEEESTD.2019.8766229","DOI":"10.1109\/IEEESTD.2019.8766229"},{"issue":"2","key":"18_CR2","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/MM.2019.2899330","volume":"39","author":"M Arafa","year":"2019","unstructured":"Arafa, M., et al.: Cascade lake: next generation Intel Xeon scalable processor. IEEE Micro 39(2), 29\u201336 (2019)","journal-title":"IEEE Micro"},{"key":"18_CR3","unstructured":"Arm: Arm A64 instruction set architecture - Armv9, for Armv9-a architecture profile (2021). https:\/\/developer.arm.com\/documentation\/ddi0602\/2021-12"},{"issue":"2","key":"18_CR4","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1093\/qjmam\/4.2.236","volume":"4","author":"AD Booth","year":"1951","unstructured":"Booth, A.D.: A signed binary multiplication technique. Q. J. Mech. Appl. Math. 4(2), 236\u2013240 (1951)","journal-title":"Q. J. Mech. Appl. Math."},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Brunie, N.: Modified fused multiply and add for exact low precision product accumulation. In: 2017 IEEE 24th Symposium on Computer Arithmetic (ARITH), pp. 106\u2013113. IEEE (2017)","DOI":"10.1109\/ARITH.2017.29"},{"key":"18_CR6","unstructured":"Dan, Z., et al.: IEEE standard for floating-point arithmetic. IEEE Std 754-2008, pp. 1\u201370 (2008)"},{"key":"18_CR7","unstructured":"Hauser, J.: Berkeley testfloat (2018). https:\/\/www.jhauser.us\/arithmetic\/testfloat.html"},{"issue":"5","key":"18_CR8","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1109\/TC.2011.77","volume":"61","author":"L Huang","year":"2011","unstructured":"Huang, L., Ma, S., Shen, L., Wang, Z., Xiao, N.: Low-cost binary128 floating-point FMA unit design with SIMD support. IEEE Trans. Comput. 61(5), 745\u2013751 (2011)","journal-title":"IEEE Trans. Comput."},{"key":"18_CR9","unstructured":"Kalamkar, D., et al.: A study of BFLOAT16 for deep learning training. arXiv preprint arXiv:1905.12322 (2019)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Kaul, H., et al.: A 1.45 GHz 52-to-162GFLOPS\/W variable-precision floating-point fused multiply-add unit with certainty tracking in 32 nm CMOS. In: 2012 IEEE International Solid-State Circuits Conference, pp. 182\u2013184. IEEE (2012)","DOI":"10.1109\/ISSCC.2012.6176987"},{"issue":"4","key":"18_CR11","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1109\/TVLSI.2020.3044752","volume":"29","author":"S Mach","year":"2020","unstructured":"Mach, S., Schuiki, F., Zaruba, F., Benini, L.: FPnew: an open-source multiformat floating-point unit architecture for energy-proportional transprecision computing. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 29(4), 774\u2013787 (2020)","journal-title":"IEEE Trans. Very Large Scale Integr. (VLSI) Syst."},{"issue":"2","key":"18_CR12","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1109\/TVLSI.2021.3128435","volume":"30","author":"W Mao","year":"2021","unstructured":"Mao, W., et al.: A configurable floating-point multiple-precision processing element for HPC and AI converged computing. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 30(2), 213\u2013226 (2021)","journal-title":"IEEE Trans. Very Large Scale Integr. (VLSI) Syst."},{"key":"18_CR13","unstructured":"Micikevicius, P., et al.: Mixed precision training. arXiv preprint arXiv:1710.03740 (2017)"},{"issue":"8","key":"18_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3469029","volume":"54","author":"MS Murshed","year":"2021","unstructured":"Murshed, M.S., Murphy, C., Hou, D., Khan, N., Ananthanarayanan, G., Hussain, F.: Machine learning at the network edge: a survey. ACM Comput. Surv. (CSUR) 54(8), 1\u201337 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Schmookler, M.S., Nowka, K.J.: Leading zero anticipation and detection-a comparison of methods. In: Proceedings 15th IEEE Symposium on Computer Arithmetic, ARITH-15 2001, pp. 7\u201312. IEEE (2001)","DOI":"10.1109\/ARITH.2001.930098"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Sevilla, J., Heim, L., Ho, A., Besiroglu, T., Hobbhahn, M., Villalobos, P.: Compute trends across three eras of machine learning. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2022)","DOI":"10.1109\/IJCNN55064.2022.9891914"},{"issue":"3","key":"18_CR17","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1109\/TCSI.2016.2525042","volume":"63","author":"J Sohn","year":"2016","unstructured":"Sohn, J., Swartzlander, E.E.: A fused floating-point four-term dot product unit. IEEE Trans. Circuits Syst. I Regul. Pap. 63(3), 370\u2013378 (2016)","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"issue":"02","key":"18_CR18","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1109\/TVLSI.2022.3226185","volume":"31","author":"H Tan","year":"2023","unstructured":"Tan, H., Tong, G., Huang, L., Xiao, L., Xiao, N.: Multiple-mode-supporting floating-point FMA unit for deep learning processors. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 31(02), 253\u2013266 (2023)","journal-title":"IEEE Trans. Very Large Scale Integr. (VLSI) Syst."},{"key":"18_CR19","unstructured":"Vanholder, H.: Efficient inference with tensorrt. In: GPU Technology Conference, vol. 1, p. 2 (2016)"},{"issue":"7","key":"18_CR20","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."},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, H., Lee, H.J., Ko, S.B.: Efficient fixed\/floating-point merged mixed-precision multiply-accumulate unit for deep learning processors. In: 2018 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1\u20135. IEEE (2018)","DOI":"10.1109\/ISCAS.2018.8351354"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2023: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-39698-4_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T16:34:23Z","timestamp":1729960463000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-39698-4_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031396977","9783031396984"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-39698-4_18","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":"24 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","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":"164","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":"49","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":"0","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":"30% - 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":"3.98","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":"4","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)"}}]}}