{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T22:53:50Z","timestamp":1777676030195,"version":"3.51.4"},"reference-count":60,"publisher":"SAGE Publications","issue":"3-4","license":[{"start":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T00:00:00Z","timestamp":1682294400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100003051","name":"NEDO","doi-asserted-by":"crossref","award":["JPNP16007"],"award-info":[{"award-number":["JPNP16007"]}],"id":[{"id":"10.13039\/501100003051","id-type":"DOI","asserted-by":"crossref"}]},{"name":"JST PRESTO","award":["JPMJPR20MA"],"award-info":[{"award-number":["JPMJPR20MA"]}]},{"name":"JST-CREST","award":["JPMJCR19F5"],"award-info":[{"award-number":["JPMJCR19F5"]}]},{"name":"JSPS KAKENHI","award":["JP22H03600"],"award-info":[{"award-number":["JP22H03600"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of High Performance Computing Applications"],"published-print":{"date-parts":[[2023,7]]},"abstract":"<jats:p>In this thought-provoking article, we discuss certain myths and legends that are folklore among members of the high-performance computing community. We gathered these myths from conversations at conferences and meetings, product advertisements, papers, and other communications such as tweets, blogs, and news articles within and beyond our community. We believe they represent the zeitgeist of the current era of massive change, driven by the end of many scaling laws such as Dennard scaling and Moore\u2019s law. While some laws end, new directions are emerging, such as algorithmic scaling or novel architecture research. Nevertheless, these myths are rarely based on scientific facts, but rather on some evidence or argumentation. In fact, we believe that this is the very reason for the existence of many myths and why they cannot be answered clearly. While it feels like there should be clear answers for each, some may remain endless philosophical debates, such as whether Beethoven was better than Mozart. We would like to see our collection of myths as a discussion of possible new directions for research and industry investment.<\/jats:p>","DOI":"10.1177\/10943420231166608","type":"journal-article","created":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T05:13:56Z","timestamp":1682313236000},"page":"245-259","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":15,"title":["Myths and legends in high-performance computing"],"prefix":"10.1177","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1910-8532","authenticated-orcid":false,"given":"Satoshi","family":"Matsuoka","sequence":"first","affiliation":[{"name":"RIKEN Center for Computational Science, Kobe, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5343-414X","authenticated-orcid":false,"given":"Jens","family":"Domke","sequence":"additional","affiliation":[{"name":"RIKEN Center for Computational Science, Kobe, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7165-2095","authenticated-orcid":false,"given":"Mohamed","family":"Wahib","sequence":"additional","affiliation":[{"name":"RIKEN Center for Computational Science, Kobe, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4575-7213","authenticated-orcid":false,"given":"Aleksandr","family":"Drozd","sequence":"additional","affiliation":[{"name":"RIKEN Center for Computational Science, Kobe, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1333-9797","authenticated-orcid":false,"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich, Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2023,4,24]]},"reference":[{"key":"bibr1-10943420231166608","unstructured":"Abali B, Eickemeyer RJ, Franke H, et al. (2015) Disaggregated and optically interconnected memory: when will it be cost effective? http:\/\/arxiv.org\/abs\/1503.01416"},{"key":"bibr2-10943420231166608","unstructured":"Allied Market Research (2020) Graphic Processing Unit (GPU) market by type (dedicated, integrated, and hybrid), device (computer, tablet, smartphone, gaming console, television, and others), industry vertical (Electronics, IT & telecommunication. Defense & Intelligence, Media & Entertainment, and Others): Global Opportunity Analysis and Industry Forecast, pp. 2020\u20132027. https:\/\/www.alliedmarketresearch.com\/graphic-processing-unit-market"},{"key":"bibr3-10943420231166608","unstructured":"Allied Market Research (2022) Field programmable gate array market by technology (EEPROM, Antifuse, SRAM, flash, and others (EPROM and PROM)), application (data processing, consumer electronics, industrial, military & aerospace, automotive, telecom, and others), and type (high-end, mid-end, and low-end FPGA): global opportunity analysis and industry forecast, pp. 2021\u20132030. https:\/\/www.alliedmarketresearch.com\/field-programmable-gate-array-market"},{"key":"bibr4-10943420231166608","unstructured":"Aytekin C (2022) Neural networks are decision trees. https:\/\/arxiv.org\/abs\/2210.05189"},{"key":"bibr5-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1177\/1094342017738610"},{"key":"bibr6-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356173"},{"key":"bibr7-10943420231166608","doi-asserted-by":"publisher","DOI":"10.5555\/3571885.3571982"},{"key":"bibr8-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"bibr9-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2022.3148491"},{"key":"bibr10-10943420231166608","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.07629"},{"key":"bibr11-10943420231166608","unstructured":"Bi K, Xie L, Zhang H, et al. (2022) Pangu-weather: a 3D high-resolution model for fast and accurate global weather forecast. https:\/\/arxiv.org\/abs\/2211.02556"},{"key":"bibr12-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1029\/2018GL078510"},{"key":"bibr13-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00038"},{"key":"bibr14-10943420231166608","unstructured":"Cutress I (2022a) Interview with Intel\u2019s Raja Koduri: zettascale or ZettaFLOP? Metaverse what? https:\/\/www.anandtech.com\/show\/17298\/interview-with-intels-raja-koduri-zettascale-or-zettaflop-metaverse-what"},{"key":"bibr15-10943420231166608","unstructured":"Cutress I (2022b) The key to Intel\u2019s ZF (ZettaFLOP, 1ZF FP64 system), is the power. Trying to keep within the 40-100 MW per Supercomputer. https:\/\/twitter.com\/IanCutress\/status\/1599452910743478273"},{"key":"bibr16-10943420231166608","first-page":"9","volume-title":"Proceedings of the 3rd USENIX Conference on Hot Topic in Parallelism","author":"Czechowski K","year":"2011"},{"key":"bibr17-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1145\/3570609"},{"key":"bibr18-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5217932"},{"key":"bibr19-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00114"},{"key":"bibr20-10943420231166608","unstructured":"Domke J, Vatai E, Gerofi B, et al. (2022) At the locus of performance: a case study in enhancing CPUs with copious 3D-stacked cache. https:\/\/arxiv.org\/abs\/2204.02235"},{"key":"bibr21-10943420231166608","unstructured":"Frantar E, Ashkboos S, Hoefler T, et al. (2022) GPTQ: accurate post-training quantization for generative pre-trained transformers. https:\/\/arxiv.org\/abs\/2210.17323"},{"key":"bibr22-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2022.01.013"},{"key":"bibr23-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1145\/42411.42415"},{"key":"bibr24-10943420231166608","doi-asserted-by":"publisher","DOI":"10.14529\/jsfi170206"},{"key":"bibr25-10943420231166608","unstructured":"Haus UU (2021) The brave new world of exascale computing: computation is free, data movement is not. https:\/\/minoa-itn.fau.de\/wp-content\/uploads\/2021\/03\/TRR154-MINOA-20210303.pdf"},{"key":"bibr26-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2022.3152681"},{"key":"bibr27-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1145\/3571725"},{"key":"bibr28-10943420231166608","unstructured":"Huang L, Hoefler T (2022) Compressing multidimensional weather and climate data into neural networks. https:\/\/arxiv.org\/abs\/2210.12538"},{"key":"bibr29-10943420231166608","unstructured":"IEEE IRDS\u2122 (2021) International Roadmap for Devices and Systems (IRDS\u2122) 2021 Edition \u2013 Executive Summary. IEEE: IEEE IRDS\u2122 Roadmap. https:\/\/irds.ieee.org\/images\/files\/pdf\/2021\/2021IRDS_ES.pdf"},{"key":"bibr30-10943420231166608","unstructured":"Intersect360 Research (2022) Worldwide HPC and AI training market, 2021 actuals, 2022-26 forecast. https:\/\/www.intersect360.com\/wp-content\/uploads\/Webinar-Intersect360-WW-HPC-AI-Unified-2021-market-size-and-2022-26-forecast.pdf"},{"key":"bibr31-10943420231166608","unstructured":"Ivanov A, Dryden N, Ben-Nun T, et al. (2021) Data movement is all you need: a case study on optimizing transformers. In: Proceedings of Machine Learning and Systems, 3. MLSys 2021)."},{"key":"bibr32-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac3ffa"},{"key":"bibr33-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1145\/2791321.2791345"},{"key":"bibr34-10943420231166608","unstructured":"Keyes D (2022) Efficient computation through tuned approximation. https:\/\/siag-sc.org\/media\/files\/DK-slides.pdf"},{"key":"bibr35-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.26011"},{"key":"bibr36-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1145\/582034.582089"},{"key":"bibr37-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"bibr38-10943420231166608","unstructured":"Lavin A, Krakauer D, Zenil H, et al. (2021) Simulation intelligence: towards a new generation of scientific methods. https:\/\/arxiv.org\/abs\/2112.03235"},{"key":"bibr39-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1816021"},{"key":"bibr40-10943420231166608","unstructured":"Li H, Berger DS, Novakovic S, et al. (2022) Pond: CXL-Based memory pooling systems for cloud platforms. https:\/\/arxiv.org\/abs\/2203.00241"},{"key":"bibr41-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.126.180604"},{"key":"bibr42-10943420231166608","unstructured":"Macrotrends LLC (2022) NVIDIA profit margin 2010-2022. https:\/\/www.macrotrends.net\/stocks\/charts\/NVDA\/nvidia\/profit-margins"},{"key":"bibr43-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-92859-1_7"},{"key":"bibr44-10943420231166608","unstructured":"Matsuoka S, Domke J (2022) Life after Fugaku: what have we learned and how do we proceed as the end of moore\u2019s law approaches? https:\/\/sinews.siam.org\/Details-Page\/life-after-fugaku-what-have-we-learned-and-how-do-we-proceed-as-the-end-of-moores-law-approaches"},{"key":"bibr45-10943420231166608","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.02432"},{"key":"bibr46-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00051"},{"key":"bibr47-10943420231166608","unstructured":"NTT R&D (2020) What is the all-photonics network? https:\/\/www.rd.ntt\/e\/iown\/0002.html"},{"key":"bibr48-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1177\/10943420221090256"},{"key":"bibr49-10943420231166608","unstructured":"Pathak J, Subramanian S, Harrington P, et al. (2022) FourCastNet: a global data-driven high-resolution weather model using adaptive fourier neural operators. https:\/\/arxiv.org\/abs\/2202.11214"},{"key":"bibr50-10943420231166608","unstructured":"Post E (1982) Real programmers don\u2019t use PASCAL. http:\/\/www.ee.ryerson.ca\/\u223celf\/hack\/realmen.html"},{"key":"bibr51-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1810286115"},{"key":"bibr52-10943420231166608","unstructured":"Schulthess TC (2016) Exascale computing: endgame or new beginning for climate modelling. https:\/\/www.ecmwf.int\/sites\/default\/files\/elibrary\/2016\/16804-exascale-computing-endgame-or-new-beginning-climate-modelling.pdf"},{"key":"bibr53-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1145\/3546591.3547527"},{"key":"bibr54-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1145\/1364782.1364802"},{"key":"bibr55-10943420231166608","unstructured":"Sorensen B, Norton A, Joseph E, et al. (2019) Special report for NASA: exploring options for a bespoke supercomputer targeted for weather and climate workloads. Technical Report HR4.0046.10.01.2019. Hyperion Research, LLC. https:\/\/hec.nasa.gov\/news\/reports\/NASA-Hyperion-Research-Bespoke-Weather-HPC-Full-Report.pdf"},{"key":"bibr56-10943420231166608","unstructured":"Strohmaier E, Dongarra J, Simon H, et al. (2022) TOP500. http:\/\/www.top500.org\/"},{"key":"bibr57-10943420231166608","unstructured":"Tesla, Inc (2021) Whitepaper: tesla dojo technology \u2013 a guide to tesla\u2019s configurable floating point formats & arithmetic. https:\/\/tesla-cdn.thron.com\/static\/MXMU3S_tesla-dojo-technology_1WDVZN.pdf"},{"key":"bibr58-10943420231166608","unstructured":"White MJ (2022) Nvidia says falling GPU prices are \u2018a story of the past\u2019. https:\/\/www.digitaltrends.com\/computing\/nvidia-says-falling-gpu-prices-are-over\/"},{"key":"bibr59-10943420231166608","doi-asserted-by":"crossref","unstructured":"Wu CJ, Hsiao ST, Wang JY, et al. (2021) Ultra High Power Cooling Solution for 3D-ICs. In: 2021 Symposium on VLSI Technology, pp. 1\u20132.","DOI":"10.23919\/VLSICircuits52068.2021.9492489"},{"key":"bibr60-10943420231166608","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476176"}],"container-title":["The International Journal of High Performance Computing Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/10943420231166608","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/10943420231166608","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/10943420231166608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T08:17:27Z","timestamp":1777450647000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/10943420231166608"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,24]]},"references-count":60,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["10.1177\/10943420231166608"],"URL":"https:\/\/doi.org\/10.1177\/10943420231166608","relation":{},"ISSN":["1094-3420","1741-2846"],"issn-type":[{"value":"1094-3420","type":"print"},{"value":"1741-2846","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,24]]}}}