{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:38:54Z","timestamp":1740123534191,"version":"3.37.3"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T00:00:00Z","timestamp":1554336000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"RoMoL ERC Advanced Grant","award":["GA 321253"],"award-info":[{"award-number":["GA 321253"]}]},{"name":"Juan de la Cierva","award":["JCI-2012-15047"],"award-info":[{"award-number":["JCI-2012-15047"]}]},{"DOI":"10.13039\/501100000654","name":"Marie Curie","doi-asserted-by":"crossref","award":["2013 BP_B 00243"],"award-info":[{"award-number":["2013 BP_B 00243"]}],"id":[{"id":"10.13039\/501100000654","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s11227-019-02841-6","type":"journal-article","created":{"date-parts":[[2019,4,5]],"date-time":"2019-04-05T13:47:01Z","timestamp":1554472021000},"page":"1960-1979","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Efficiency analysis of modern vector architectures: vector ALU sizes, core counts and clock frequencies"],"prefix":"10.1007","volume":"76","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9435-3234","authenticated-orcid":false,"given":"Adrian","family":"Barredo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan M.","family":"Cebrian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mateo","family":"Valero","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Casas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miquel","family":"Moreto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,4,4]]},"reference":[{"key":"2841_CR1","volume-title":"Optimizing performance\/watt of embedded SIMD multiprocessors through a priori application guided power scheduling","author":"RK Albright","year":"2012","unstructured":"Albright RK (2012) Optimizing performance\/watt of embedded SIMD multiprocessors through a priori application guided power scheduling. Oregon State University, Corvallis"},{"key":"2841_CR2","unstructured":"AMD (2000) 3DNow! technology manual. Motorola, Chicago"},{"key":"2841_CR3","unstructured":"Neon. \nhttps:\/\/developer.arm.com\/architectures\/instruction-sets\/simd-isas\/neon\n\n. Accessed 04 Mar 2019"},{"key":"2841_CR4","unstructured":"Asanovic\u0300 K (1998) Vector microprocessors. Ph.D. thesis"},{"issue":"8","key":"2841_CR5","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1109\/TC.1968.229158","volume":"C\u201317","author":"GH Barnes","year":"1968","unstructured":"Barnes GH, Brown RM, Kato M, Kuck DJ, Slotnick DL, Stokes RA (1968) The ILLIAC IV computer. IEEE Trans Comput C\u201317(8):746\u2013757","journal-title":"IEEE Trans Comput"},{"issue":"2","key":"2841_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2024716.2024718","volume":"39","author":"N Binkert","year":"2011","unstructured":"Binkert N, Sardashti S, Sen R, Sewell K, Shoaib M, Vaish N, Hill MD, Wood DA, Beckmann B, Black G, Reinhardt SK, Saidi A, Basu A, Hestness J, Hower DR, Krishna T (2011) The gem5 simulator. ACM SIGARCH Comput Archit News 39(2):1","journal-title":"ACM SIGARCH Comput Archit News"},{"key":"2841_CR7","volume-title":"Programming with POSIX threads","author":"DR Butenhof","year":"1997","unstructured":"Butenhof DR (1997) Programming with POSIX threads. Addison-Wesley Longman Publishing Co. Inc., Boston"},{"key":"2841_CR8","doi-asserted-by":"crossref","unstructured":"Casas M, Moreto M, Alvarez L, Castillo E, Chasapis D, Hayes T (2015) Runtime-aware architectures. In: European Conference on Parallel Processing, pp 16\u201327","DOI":"10.1007\/978-3-662-48096-0_2"},{"key":"2841_CR9","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1007\/s00607-015-0444-y","volume":"97","author":"JM Cebrian","year":"2015","unstructured":"Cebrian JM, Jahre M, Natvig L (2015) ParVec: vectorizing the PARSEC benchmark suite. Computing 97:1077\u20131100","journal-title":"Computing"},{"issue":"12","key":"2841_CR10","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1007\/s00607-013-0366-5","volume":"96","author":"JM Cebri\u00e1n","year":"2014","unstructured":"Cebri\u00e1n JM, Natvig L, Meyer JC (2014) Performance and energy impact of parallelization and vectorization techniques in modern microprocessors. Computing 96(12):1179\u20131193","journal-title":"Computing"},{"key":"2841_CR11","unstructured":"Chapman B (2007) The multicore programming challenge. In: Advanced Parallel Processing Technologies; 7th International Symposium, (7th APPT'07), Lecture Notes in Computer Science (LNCS), vol 4847. Springer-Verlag, New York, p 3"},{"key":"2841_CR12","unstructured":"ITRS (2011) International technology roadmap for semiconductors"},{"key":"2841_CR13","unstructured":"CRAY (1984) The CRAY X-MP series of computer systems"},{"issue":"5","key":"2841_CR14","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1109\/JSSC.1974.1050511","volume":"9","author":"R Dennard","year":"1974","unstructured":"Dennard R, Gaensslen F, Rideout V, Bassous E, LeBlanc A (1974) Design of ion-implanted MOSFET\u2019s with very small physical dimensions. IEEE J Solid State Circuits 9(5):256\u2013268","journal-title":"IEEE J Solid State Circuits"},{"key":"2841_CR15","unstructured":"Espasa R (1997) Advanced vector architectures. Ph.D. thesis, Universitat Polit\u00e8cnica de Catalunya"},{"key":"2841_CR16","doi-asserted-by":"crossref","unstructured":"Espasa R, Valero M, Smith JE (1998) Vector architectures: past, present and future. In: Proceeding ICS \u201998 Proceedings of the 12th International Conference on Supercomputing, pp 425\u2013432","DOI":"10.1145\/277830.277935"},{"key":"2841_CR17","volume-title":"Motorola AltiVec technology","author":"S Fuller","year":"1998","unstructured":"Fuller S (1998) Motorola AltiVec technology. Motorola, Chicago"},{"issue":"2S","key":"2841_CR18","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1049\/pi-b-1.1956.0038","volume":"103","author":"A Haley","year":"1956","unstructured":"Haley A (1956) DEUCE: a high-speed general-purpose computer. Proc IEEE Part B Radio Electron Eng 103(2S):165\u2013173","journal-title":"Proc IEEE Part B Radio Electron Eng"},{"key":"2841_CR19","volume-title":"Computer architecture: a quantitative approach","author":"JL Hennessy","year":"2017","unstructured":"Hennessy JL, Patterson DA (2017) Computer architecture: a quantitative approach, 6th edn. Morgan Kaufmann Publishers Inc., San Francisco","edition":"6"},{"key":"2841_CR20","doi-asserted-by":"crossref","unstructured":"Hu Z, Buyuktosunoglu A, Srinivasan V, Zyuban V, Jacobson H, Bose P (2004) Microarchitectural techniques for power gating of execution units. In: Proceedings of the 2004 International Symposium on Low Power Electronics and Design\u2014ISLPED \u201904, ACM Press, New York, p\u00a032","DOI":"10.1145\/1013235.1013249"},{"key":"2841_CR21","doi-asserted-by":"crossref","unstructured":"Inoue H (2016) How SIMD width affects energy efficiency: a case study on sorting. In: 2016 IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS XIX), IEEE, pp 1\u20133","DOI":"10.1109\/CoolChips.2016.7503679"},{"key":"2841_CR22","unstructured":"Inter Corporation (2012) Intel 64 and IA-32 architectures software developer\u2019s manual volume 1: basic architecture"},{"key":"2841_CR23","unstructured":"Intel Corporation (2015) Intel 64 and IA-32 architectures software developer\u2019s manual volume 2A: instruction set reference"},{"key":"2841_CR24","volume-title":"Parallel computers two: architecture, programming and algorithms","author":"RW Hockney","year":"1988","unstructured":"Hockney RW, Jesshope RC (1988) Parallel computers two: architecture, programming and algorithms, 2nd edn. IOP Publishing Ltd., Bristol","edition":"2"},{"key":"2841_CR25","doi-asserted-by":"crossref","unstructured":"Jimborean A, Koukos K, Spiliopoulos V, Black-Schaffer D, Kaxiras S (2014) Fix the code. Don\u2019t tweak the hardware: a new compiler approach to voltage-frequency scaling. In: Annual IEEE\/ACM International Symposium","DOI":"10.1145\/2544137.2544161"},{"issue":"1","key":"2841_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2200\/S00119ED1V01Y200805CAC004","volume":"3","author":"S Kaxiras","year":"2008","unstructured":"Kaxiras S, Martonosi M (2008) Computer architecture techniques for power-efficiency. Synth Lect Comput Archit 3(1):1\u2013207","journal-title":"Synth Lect Comput Archit"},{"key":"2841_CR27","doi-asserted-by":"crossref","unstructured":"Koukos K, Black-Schaffer D, Spiliopoulos V, Kaxiras S (2013) Towards more efficient execution: a decoupled access-execute approach. In: International Conference on Supercomputing (ICS)","DOI":"10.1145\/2464996.2465012"},{"key":"2841_CR28","doi-asserted-by":"crossref","unstructured":"Lee Y, Avizienis R, Bishara A, Xia R, Lockhart D, Batten C (2011) Exploring the tradeoffs between programmability and efficiency in data-parallel accelerators. In: International Symposium on Computer Architecture (ISCA), pp 129\u2013140","DOI":"10.1145\/2024723.2000080"},{"key":"2841_CR29","doi-asserted-by":"crossref","unstructured":"Lemuet C, Sampson J, Francois J, Jouppi N (2006) The potential energy efficiency of vector acceleration. In: ACM\/IEEE SC 2006 conference (SC\u201906), IEEE, p 1","DOI":"10.1109\/SC.2006.62"},{"key":"2841_CR30","doi-asserted-by":"crossref","unstructured":"Li S, Ahn JH, Strong RD, Brockman JB, Tullsen DM, Jouppi NP (2009) McPAT: an integrated power, area, and timing modeling framework for multicore and manycore architectures. In: Proceedings of the 42nd Annual ACM\/IEEE International Symposium on Microarchitecture (MICRO), pp 469\u2013480","DOI":"10.1145\/1669112.1669172"},{"key":"2841_CR31","unstructured":"Li H, Bhunia S, Chen Y, Vijaykumar TN, Roy K (2003) Deterministic clock gating for microprocessor power reduction. In: International Symposium on High-Performance Computer Architecture (HPCA)"},{"key":"2841_CR32","doi-asserted-by":"crossref","unstructured":"Majzoub S (2010) Voltage island design in multi-core SIMD processors. In: 2010 5th international design and test workshop, IEEE, pp 18\u201323","DOI":"10.1109\/IDT.2010.5724399"},{"issue":"4","key":"2841_CR33","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1109\/2.917539","volume":"34","author":"T Mudge","year":"2001","unstructured":"Mudge T (2001) Power: a first-class architectural design constraint. Computer 34(4):52\u201358","journal-title":"Computer"},{"key":"2841_CR34","unstructured":"NEC (2017) Vector supercomputer SX series: SX-aurora TSUBASA. \nhttps:\/\/www.nec.com\/en\/global\/solutions\/hpc\/sx\/vector_engine.html\n\n. Accessed 04 Mar 2019"},{"key":"2841_CR35","unstructured":"Russell RM (1971) The CRAY-1 computer system. In: Proceedings of Communication, ACM Computer Proceedings of WJCC Communication, ACM. McCarthy J, Time sharing computer systems Pt. I, AFIPS Press NJ 36(12):657\u2013675"},{"issue":"1","key":"2841_CR36","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1145\/359327.359336","volume":"21","author":"RM Russell","year":"1978","unstructured":"Russell RM (1978) The CRAY-1 computer system. Commun ACM 21(1):63\u201372","journal-title":"Commun ACM"},{"key":"2841_CR37","doi-asserted-by":"crossref","unstructured":"Satish N, Kim C, Chhugani J, Saito H, Krishnaiyer R, Smelyanskiy M, Girkar M, Dubey P (2012) Can traditional programming bridge the ninja performance gap for parallel computing applications? In: Proceedings of the 39th Annual International Symposium on Computer Architecture (ISCA), pp 440\u2013451","DOI":"10.1109\/ISCA.2012.6237038"},{"key":"2841_CR38","doi-asserted-by":"crossref","unstructured":"Sodani A (2015) Knights landing (KNL): 2nd generation Intel Xeon Phi processor. In: IEEE Hot Chips 27 Symposium (HCS)","DOI":"10.1109\/HOTCHIPS.2015.7477467"},{"issue":"2","key":"2841_CR39","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MM.2017.35","volume":"37","author":"N Stephens","year":"2017","unstructured":"Stephens N, Biles S, Boettcher M, Eapen J, Eyole M, Gabrielli G, Horsnell M, Magklis G, Martinez A, Premillieu N, Reid A, Rico A, Walker P (2017) The ARM scalable vector extension. IEEE Micro 37(2):26\u201339","journal-title":"IEEE Micro"},{"key":"2841_CR40","unstructured":"The Green 500 (2018). \nhttps:\/\/www.top500.org\/green500\/\n\n. Accessed 4 Mar 2019"},{"key":"2841_CR41","doi-asserted-by":"crossref","unstructured":"Usami K, Goto Y, Matsunaga K, Koyama S, Ikebuchi D, Amano H, Nakamura H (2011) On-chip detection methodology for break-even time of power gated function units. In: IEEE\/ACM International Symposium on Low Power Electronics and Design, IEEE, pp 241\u2013246","DOI":"10.1109\/ISLPED.2011.5993643"},{"key":"2841_CR42","unstructured":"Villa L, Espasa R, Valero M, Effective usage of vector registers in advanced vector architectures. In: Proceedings 1997 International Conference on Parallel Architectures and Compilation Techniques, IEEE Computer Society, pp 250\u2013260"},{"key":"2841_CR43","doi-asserted-by":"crossref","unstructured":"Watson WJ (1972) The TI ASC: a highly modular and flexible super computer architecture. In: Proceedings of the December 5\u20137, 1972, Fall Joint Computer Conference, Part I (AFIPS), pp 221\u2013228","DOI":"10.1145\/1479992.1480022"},{"key":"2841_CR44","unstructured":"Wilkinson JH (1954) The Pilot ACE. In: Automatic Digital Computation. Her Majesty's Stationery Office, London, pp 5\u201314. Reprinted in [99, pp 193\u2013199] and [1248, pp 219\u2013228]"},{"key":"2841_CR45","unstructured":"Wu Q, Martonosi M, Clark D, Reddi V, Connors D, Wu Y, Lee J, Brooks D, A dynamic compilation framework for controlling microprocessor energy and performance. In: 38th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO\u201905), IEEE, pp 271\u2013282"},{"issue":"1","key":"2841_CR46","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1145\/216585.216588","volume":"23","author":"WA Wulf","year":"1995","unstructured":"Wulf WA, McKee SA (1995) Hitting the memory wall. ACM SIGARCH Comput Archit News 23(1):20\u201324","journal-title":"ACM SIGARCH Comput Archit News"},{"key":"2841_CR47","doi-asserted-by":"crossref","unstructured":"Xi S, Jacobson H, Bose P, Wei GY, Brooks D (2015) Quantifying sources of error in McPAT and potential impacts on architectural studies. In: International Symposium on High Performance Computer Architecture (HPCA), pp 577\u2013589","DOI":"10.1109\/HPCA.2015.7056064"},{"issue":"6","key":"2841_CR48","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1109\/TC.2011.106","volume":"61","author":"X Yang","year":"2012","unstructured":"Yang X, Wang Z, Xue J, Zhou Y (2012) The reliability wall for exascale supercomputing. IEEE Trans Comput 61(6):767\u2013779","journal-title":"IEEE Trans Comput"},{"key":"2841_CR49","unstructured":"Yoshida T (2016) Introduction of fujitsu\u2019s hpc processor for the post-k computer. In: Hot Chips 28 Symposium (HCS) (Hot Chips' 16)"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-019-02841-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-019-02841-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-019-02841-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,2]],"date-time":"2020-04-02T23:17:01Z","timestamp":1585869421000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-019-02841-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,4]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["2841"],"URL":"https:\/\/doi.org\/10.1007\/s11227-019-02841-6","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2019,4,4]]},"assertion":[{"value":"4 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}