{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T06:36:42Z","timestamp":1774593402931,"version":"3.50.1"},"publisher-location":"Cham","reference-count":11,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030256357","type":"print"},{"value":"9783030256364","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-25636-4_10","type":"book-chapter","created":{"date-parts":[[2019,7,31]],"date-time":"2019-07-31T20:04:09Z","timestamp":1564603449000},"page":"125-139","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Analysis of Relationship Between SIMD-Processing Features Used in NVIDIA GPUs and NEC SX-Aurora TSUBASA Vector Processors"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0202-1548","authenticated-orcid":false,"given":"Ilya V.","family":"Afanasyev","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1897-1828","authenticated-orcid":false,"given":"Vadim V.","family":"Voevodin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6036-5106","authenticated-orcid":false,"given":"Vladimir V.","family":"Voevodin","sequence":"additional","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"}]},{"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":[[2019,7,17]]},"reference":[{"key":"10_CR1","unstructured":"STREAM Benchmark. \n                      https:\/\/www.cs.virginia.edu\/stream\/"},{"key":"10_CR2","unstructured":"Thrust Library. \n                      https:\/\/thrust.github.io"},{"issue":"9","key":"10_CR3","doi-asserted-by":"publisher","first-page":"3948","DOI":"10.1007\/s11227-017-1993-y","volume":"73","author":"R Egawa","year":"2017","unstructured":"Egawa, R., et al.: Potential of a modern vector supercomputer for practicalapplications: performance evaluation of SX-ACE. J. Supercomput. 73(9), 3948\u20133976 (2017). \n                      https:\/\/doi.org\/10.1007\/s11227-017-1993-y","journal-title":"J. Supercomput."},{"issue":"12","key":"10_CR4","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1109\/PROC.1966.5273","volume":"54","author":"MJ Flynn","year":"1966","unstructured":"Flynn, M.J.: Very high-speed computing systems. Proc. IEEE 54(12), 1901\u20131909 (1966)","journal-title":"Proc. IEEE"},{"issue":"4","key":"10_CR5","first-page":"70","volume":"2","author":"M Harris","year":"2007","unstructured":"Harris, M., et al.: Optimizing parallel reduction in CUDA. Nvidia Dev. Technol. 2(4), 70 (2007)","journal-title":"Nvidia Dev. Technol."},{"key":"10_CR6","unstructured":"Komatsu, K., Egawa, R., Isobe, Y., Ogata, R., Takizawa, H., Kobayashi, H.: An approach to the highest efficiency of the HPCG benchmark on the SX-ACE supercomputer. In: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis (SC15), Poster, pp. 1\u20132, November 2015"},{"key":"10_CR7","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, pp. 54:1\u201354:12. IEEE Press, Piscataway (2018). \n                      http:\/\/dl.acm.org\/citation.cfm?id=3291656.3291728"},{"key":"10_CR8","unstructured":"NVIDIA: Nvidia Tesla P100: The most advanced datacenter accelerator ever built featuring Pascal GP100, the world\u2019s fastest GPU. Whitepaper (2016)"},{"key":"10_CR9","unstructured":"NVIDIA Tesla: V100 GPU architecture (2017)"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Wu, B., Zhao, Z., Zhang, E.Z., Jiang, Y., Shen, X.: Complexity analysis and algorithm design for reorganizing data to minimize non-coalesced memory accesses on GPU. In: ACM SIGPLAN Notices, vol. 48, pp. 57\u201368. ACM (2013)","DOI":"10.1145\/2517327.2442523"},{"key":"10_CR11","unstructured":"Yamada, Y., Momose, S.: Vector engine processor of NECs brand-new supercomputer SX-aurora TSUBASA. In: Intenational Symposium on High Performance Chips (Hot Chips 2018) (2018)"}],"container-title":["Lecture Notes in Computer Science","Parallel Computing Technologies"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-25636-4_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,31]],"date-time":"2019-07-31T20:30:39Z","timestamp":1564605039000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-25636-4_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030256357","9783030256364"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-25636-4_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"17 July 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PaCT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel Computing Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Almaty","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kazakhstan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pact2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ssd.sscc.ru\/conference\/pact2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}