{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T08:25:11Z","timestamp":1765268711496,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030710576"},{"type":"electronic","value":"9783030710583"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-71058-3_8","type":"book-chapter","created":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T17:03:25Z","timestamp":1614618205000},"page":"127-143","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Optimization of the Himeno Benchmark for SX-Aurora TSUBASA"],"prefix":"10.1007","author":[{"given":"Akito","family":"Onodera","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4463-8359","authenticated-orcid":false,"given":"Kazuhiko","family":"Komatsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soya","family":"Fujimoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoko","family":"Isobe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4186-5014","authenticated-orcid":false,"given":"Masayuki","family":"Sato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3350-1413","authenticated-orcid":false,"given":"Hiroaki","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,3,2]]},"reference":[{"key":"8_CR1","unstructured":"Himeno benchmark. http:\/\/i.riken.jp\/en\/supercom\/documents\/himenobmt\/. Accessed 10 Aug 2020"},{"key":"8_CR2","unstructured":"Intel Xeon Gold 6126 Processor. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/processors\/xeon\/scalable\/gold-processors\/gold-6126.html. Accessed 10 August 2020"},{"key":"8_CR3","unstructured":"MVAPICH: MPI over InfiniBand, Omni-Path, Ethernet\/iWARP, and RoCE. http:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/. Accessed 12 Aug 2020"},{"key":"8_CR4","unstructured":"NEC SX-Aurora TSUBASA. https:\/\/www.nec.com\/en\/global\/solutions\/hpc\/sx\/index.html. Accessed 12 Aug 2020"},{"key":"8_CR5","unstructured":"NVIDIA V100 TENSOR CORE GPU. https:\/\/www.nvidia.com\/en-us\/data-center\/v100\/. Accessed 10 Aug 2020"},{"key":"8_CR6","unstructured":"STREAM: Sustainable Memory Bandwidth in High Performance Computers. https:\/\/www.cs.virginia.edu\/stream\/. Accessed 10 Aug 2020"},{"key":"8_CR7","unstructured":"SX-Aurora TSUBASA C\/C++ Compiler User\u2019s Guide. https:\/\/www.hpc.nec\/documents\/sdk\/pdfs\/g2af01e-C++UsersGuide-018.pdf. Accessed 15 Aug 2020"},{"key":"8_CR8","unstructured":"SX-Aurora TSUBASA PROGINF\/FTRACE User\u2019s Guide. https:\/\/www.hpc.nec\/documents\/sdk\/pdfs\/g2at03e-PROGINF_FTRACE_User_Guide_en.pdf. Accessed 15 Aug 2020"},{"key":"8_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-030-25636-4_10","volume-title":"Parallel Computing Technologies","author":"IV Afanasyev","year":"2019","unstructured":"Afanasyev, I.V., Voevodin, V.V., Voevodin, V.V., Komatsu, K., Kobayashi, H.: Analysis of relationship between SIMD-processing features used in NVIDIA GPUs and NEC SX-Aurora TSUBASA vector processors. In: Malyshkin, V. (ed.) PaCT 2019. LNCS, vol. 11657, pp. 125\u2013139. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-25636-4_10"},{"key":"8_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/3-540-61053-7_53","volume-title":"Compiler Construction","author":"JW Davidson","year":"1996","unstructured":"Davidson, J.W., Jinturkar, S.: Aggressive loop unrolling in a retargetable, optimizing compiler. In: Gyim\u00f3thy, T. (ed.) CC 1996. LNCS, vol. 1060, pp. 59\u201373. Springer, Heidelberg (1996). https:\/\/doi.org\/10.1007\/3-540-61053-7_53"},{"key":"8_CR11","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1140\/epjst\/e2012-01634-y","volume":"210","author":"A Hart","year":"2012","unstructured":"Hart, A., Ansaloni, R., Gray, A.: Porting and scaling OpenACC applications on massively-parallel, GPU-accelerated supercomputers. Eur. Phys. J. Spec. Top. 210, 5\u201316 (2012). https:\/\/doi.org\/10.1140\/epjst\/e2012-01634-y","journal-title":"Eur. Phys. J. Spec. Top."},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Komatsu, K., Kishitani, T., Sato, M., Kobayashi, H.: An appropriate computing system and its system parameters selection based on bottleneck prediction of applications. In: 2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 768\u2013777 (2019)","DOI":"10.1109\/IPDPSW.2019.00127"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Komatsu, K., et al.: Performance evaluation of a vector supercomputer SX-aurora tsubasa. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018. IEEE Press (2018)","DOI":"10.1109\/SC.2018.00057"},{"key":"8_CR14","doi-asserted-by":"publisher","first-page":"012043","DOI":"10.1088\/1742-6596\/180\/1\/012043","volume":"180","author":"S Matsuoka","year":"2009","unstructured":"Matsuoka, S., Aoki, T., Endo, T., Nukada, A., Kato, T., Hasegawa, A.: GPU accelerated computing-from hype to mainstream, the rebirth of vector computing. J. Phys.: Conf. Ser. 180, 012043 (2009). https:\/\/doi.org\/10.1088\/1742-6596\/180\/1\/012043","journal-title":"J. Phys.: Conf. Ser."},{"key":"8_CR15","doi-asserted-by":"publisher","unstructured":"Phillips, E.H., Fatica, M.: Implementing the himeno benchmark with CUDA on GPU clusters. In: 2010 IEEE International Symposium on Parallel Distributed Processing (IPDPS), pp. 1\u201310 (2010). https:\/\/doi.org\/10.1109\/IPDPS.2010.5470394","DOI":"10.1109\/IPDPS.2010.5470394"},{"key":"8_CR16","doi-asserted-by":"publisher","first-page":"33","DOI":"10.18420\/btw2019-ws-03","volume-title":"BTW 2019 - Workshopband","author":"J Pietrzyk","year":"2019","unstructured":"Pietrzyk, J., Habich, D., Damme, P., Lehner, W.: First investigations of the vector supercomputer SX-aurora TSUBASA as a co-processor for database systems. In: Meyer, H., Ritter, N., Thor, A., Nicklas, D., Heuer, A., Klettke, M. (eds.) BTW 2019 - Workshopband, pp. 33\u201350. Gesellschaft f\u00fcr Informatik, Bonn (2019). https:\/\/doi.org\/10.18420\/btw2019-ws-03"},{"key":"8_CR17","doi-asserted-by":"publisher","unstructured":"Sarkar, V.: Optimized unrolling of nested loops. In: Proceedings of the 14th International Conference on Supercomputing, ICS 2000, pp. 153\u2013166. Association for Computing Machinery, New York (2000). https:\/\/doi.org\/10.1145\/335231.335246","DOI":"10.1145\/335231.335246"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Van Werkhoven, B., Maassen, J., Seinstra, F.J., Bal, H.E.: Performance models for CPU-GPU data transfers. In: 2014 14th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing, pp. 11\u201320 (2014)","DOI":"10.1109\/CCGrid.2014.16"},{"issue":"4","key":"8_CR19","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009). https:\/\/doi.org\/10.1145\/1498765.1498785","journal-title":"Commun. ACM"},{"key":"8_CR20","unstructured":"Yamada, Y., Momose, S.: Vector engine processor of NEC\u2019s brand-new supercomputer SX-aurora TSUBASA. In: Proceedings of A Symposium on High Performance Chips, Hot Chips, vol. 30, pp. 19\u201321 (2018)"}],"container-title":["Lecture Notes in Computer Science","Benchmarking, Measuring, and Optimizing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-71058-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T17:11:10Z","timestamp":1614618670000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-71058-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030710576","9783030710583"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-71058-3_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 March 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Bench","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Benchmarking, Measuring and Optimization","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bench2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.benchcouncil.org\/bench20\/index.html","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":"28","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":"12","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":"1","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":"43% - 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":"4.7","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":"3.5","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}