{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:31:47Z","timestamp":1755793907763,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031460760"},{"type":"electronic","value":"9783031460777"}],"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\/978-3-031-46077-7_16","type":"book-chapter","created":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T11:01:58Z","timestamp":1699268518000},"page":"241-254","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Fast Shared-Memory Barrier Synchronization for\u00a0a\u00a01024-Cores RISC-V Many-Core Cluster"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7576-0803","authenticated-orcid":false,"given":"Marco","family":"Bertuletti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5772-6377","authenticated-orcid":false,"given":"Samuel","family":"Riedel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7508-599X","authenticated-orcid":false,"given":"Yichao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4475-5718","authenticated-orcid":false,"given":"Alessandro","family":"Vanelli-Coralli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8068-3806","authenticated-orcid":false,"given":"Luca","family":"Benini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,7]]},"reference":[{"key":"16_CR1","unstructured":"runAI200 The Most Efficient AI Compute Engine Available. https:\/\/www.untether.ai\/products1. Accessed 31 Mar 2023"},{"key":"16_CR2","unstructured":"3GPP: 5G; NR; Physical layer procedures for data (3GPP TS 38.214 version 17.5.0 Release 17). Technical Specification (TS) 38.214, 3rd Generation Partnership Project (3GPP) (03 2023), version 17.5.0"},{"key":"16_CR3","unstructured":"Andersch, M., et al.: NVIDIA Hopper Architecture In-Depth (2022). https:\/\/developer.nvidia.com\/blog\/nvidia-hopper-architecture-in-depth\/. Accessed 31 Mar 2023"},{"key":"16_CR4","doi-asserted-by":"publisher","unstructured":"Cavalcante, M., Riedel, S., Pullini, A., Benini, L.: MemPool: A shared-L1 memory many-core cluster with a low-latency interconnect. In: 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 701\u2013706 (2021). https:\/\/doi.org\/10.23919\/DATE51398.2021.9474087","DOI":"10.23919\/DATE51398.2021.9474087"},{"key":"16_CR5","doi-asserted-by":"publisher","unstructured":"Ditzel, D., et al.: Accelerating ML recommendation with over a thousand RISC-V\/tensor processors on esperanto\u2019s ET-SoC-1 chip. In: 2021 IEEE Hot Chips 33 Symposium (HCS), pp. 1\u201323 (2021). https:\/\/doi.org\/10.1109\/HCS52781.2021.9566904","DOI":"10.1109\/HCS52781.2021.9566904"},{"key":"16_CR6","doi-asserted-by":"publisher","unstructured":"Gao, W., Fang, J., Huang, C., Xu, C., Wang, Z.: Optimizing barrier synchronization on ARMv8 many-core architectures. In: 2021 IEEE International Conference on Cluster Computing (CLUSTER), pp. 542\u2013552 (2021). https:\/\/doi.org\/10.1109\/Cluster48925.2021.00044","DOI":"10.1109\/Cluster48925.2021.00044"},{"issue":"3","key":"16_CR7","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1109\/TPDS.2020.3028691","volume":"32","author":"F Glaser","year":"2021","unstructured":"Glaser, F., Tagliavini, G., Rossi, D., Haugou, G., Huang, Q., Benini, L.: Energy-efficient hardware-accelerated synchronization for shared-L1-memory multiprocessor clusters. IEEE Trans. Parallel Distrib. Syst. 32(3), 633\u2013648 (2021). https:\/\/doi.org\/10.1109\/TPDS.2020.3028691","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"16_CR8","unstructured":"Harris, M., Perelygin, K.: Cooperative groups: flexible CUDA thread programming (2017). https:\/\/developer.nvidia.com\/blog\/cooperative-groups\/. Accessed 31 Mar 2023"},{"key":"16_CR9","unstructured":"Hoefler, T., Mehlan, T., Mietke, F., Rehm, W.: A survey of barrier algorithms for coarse grained supercomputers. Chemnitzer Informatik Berichte (2004)"},{"key":"16_CR10","doi-asserted-by":"publisher","first-page":"1608","DOI":"10.1007\/978-0-387-09766-4_23","volume-title":"Encyclopedia of Parallel Computing","author":"JF JaJa","year":"2011","unstructured":"JaJa, J.F.: PRAM (Parallel Random Access Machines). In: Padua, D. (ed.) Encyclopedia of Parallel Computing, pp. 1608\u20131615. Springer, Boston (2011). https:\/\/doi.org\/10.1007\/978-0-387-09766-4_23"},{"issue":"5","key":"16_CR11","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1093\/BIB\/BBQ015","volume":"11","author":"H Li","year":"2010","unstructured":"Li, H., Homer, N.: A survey of sequence alignment algorithms for next-generation sequencing. Brief. Bioinform. 11(5), 473\u2013483 (2010). https:\/\/doi.org\/10.1093\/BIB\/BBQ015","journal-title":"Brief. Bioinform."},{"issue":"1","key":"16_CR12","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1145\/103727.103729","volume":"9","author":"JM Mellor-Crummey","year":"1991","unstructured":"Mellor-Crummey, J.M., Scott, M.L.: Algorithms for scalable synchronization on shared-memory multiprocessors. ACM Trans. Comput. Syst. 9(1), 21\u201365 (1991). https:\/\/doi.org\/10.1145\/103727.103729","journal-title":"ACM Trans. Comput. Syst."},{"key":"16_CR13","doi-asserted-by":"publisher","unstructured":"Mohamed El Maarouf, A.K., Giraud, L., Guermouche, A., Guignon, T.: Combining reduction with synchronization barrier on multi-core processors. Concurrency Comput. Pract. Experience 35(1), e7402 (2023). https:\/\/doi.org\/10.1002\/cpe.7402","DOI":"10.1002\/cpe.7402"},{"issue":"11s","key":"16_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3511094","volume":"54","author":"R Muralidhar","year":"2022","unstructured":"Muralidhar, R., Borovica-Gajic, R., Buyya, R.: Energy efficient computing systems: architectures, abstractions and modeling to techniques and standards. ACM Comput. Surv. 54(11s), 1\u201337 (2022). https:\/\/doi.org\/10.1145\/3511094","journal-title":"ACM Comput. Surv."},{"key":"16_CR15","doi-asserted-by":"publisher","unstructured":"Riedel, S., Cavalcante, M., Andri, R., Benini, L.: MemPool: a scalable manycore architecture with a low-latency shared L1 memory (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.17742","DOI":"10.48550\/arXiv.2303.17742"},{"key":"16_CR16","doi-asserted-by":"publisher","unstructured":"Theis, T.N., Wong, H.P.: The end of Moore\u2019s law: a new beginning for information technology. In: Computing in Science Engineering, vol. 19, pp. 41\u201350 (2017). https:\/\/doi.org\/10.1109\/MCSE.2017.29","DOI":"10.1109\/MCSE.2017.29"},{"issue":"5","key":"16_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3400032","volume":"19","author":"V Venkataramani","year":"2020","unstructured":"Venkataramani, V., Kulkarni, A., Mitra, T., Peh, L.S.: SPECTRUM: a software-defined predictable many-core architecture for LTE\/5G baseband processing. ACM Trans. Embed. Comput. Syst. 19(5), 1\u201328 (2020). https:\/\/doi.org\/10.1145\/3400032","journal-title":"ACM Trans. Embed. Comput. Syst."},{"key":"16_CR18","doi-asserted-by":"publisher","unstructured":"Villa, O., Palermo, G., Silvano, C.: Efficiency and scalability of barrier synchronization on NoC based many-core architectures. In: Proceedings of the 2008 International Conference on Compilers, Architectures and Synthesis for Embedded Systems, pp. 81\u201390. CASES 2008, Association for Computing Machinery, New York, NY, USA (2008). https:\/\/doi.org\/10.1145\/1450095.1450110","DOI":"10.1145\/1450095.1450110"},{"issue":"11","key":"16_CR19","doi-asserted-by":"publisher","first-page":"1845","DOI":"10.1109\/TC.2020.3027900","volume":"70","author":"F Zaruba","year":"2021","unstructured":"Zaruba, F., Schuiki, F., Hoefler, T., Benini, L.: Snitch: a tiny pseudo dual-issue processor for area and energy efficient execution of floating-point intensive workloads. IEEE Trans. Comput. 70(11), 1845\u20131860 (2021). https:\/\/doi.org\/10.1109\/TC.2020.3027900","journal-title":"IEEE Trans. Comput."}],"container-title":["Lecture Notes in Computer Science","Embedded Computer Systems: Architectures, Modeling, and Simulation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46077-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T11:03:43Z","timestamp":1699268623000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46077-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031460760","9783031460777"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46077-7_16","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":"7 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SAMOS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Embedded Computer Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Samos","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"2 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"samos2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/samos-conference.com\/wp\/","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":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45","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":"11","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":"7","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":"24% - 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":"4","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":"2","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)"}}]}}