{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T22:45:50Z","timestamp":1777675550180,"version":"3.51.4"},"reference-count":26,"publisher":"SAGE Publications","issue":"6","license":[{"start":{"date-parts":[[2019,5,9]],"date-time":"2019-05-09T00:00:00Z","timestamp":1557360000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100001656","name":"Helmholtz-Gemeinschaft","doi-asserted-by":"publisher","award":["VH-NG-1241"],"award-info":[{"award-number":["VH-NG-1241"]}],"id":[{"id":"10.13039\/501100001656","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of High Performance Computing Applications"],"published-print":{"date-parts":[[2019,11]]},"abstract":"<jats:p>With the memory bandwidth of current computer architectures being significantly slower than the (floating point) arithmetic performance, many scientific computations only leverage a fraction of the computational power in today\u2019s high-performance architectures. At the same time, memory operations are the primary energy consumer of modern architectures, heavily impacting the resource cost of large-scale applications and the battery life of mobile devices. This article tackles this mismatch between floating point arithmetic throughput and memory bandwidth by advocating a disruptive paradigm change with respect to how data are stored and processed in scientific applications. Concretely, the goal is to radically decouple the data storage format from the processing format and, ultimately, design a \u201cmodular precision ecosystem\u201d that allows for more flexibility in terms of customized data access. For memory-bounded scientific applications, dynamically adapting the memory precision to the numerical requirements allows for attractive resource savings. In this article, we demonstrate the potential of employing a modular precision ecosystem for the block-Jacobi preconditioner and the PageRank algorithm\u2014two applications that are popular in the communities and at the same characteristic representatives for the field of numerical linear algebra and data analytics, respectively.<\/jats:p>","DOI":"10.1177\/1094342019846547","type":"journal-article","created":{"date-parts":[[2019,5,9]],"date-time":"2019-05-09T23:16:15Z","timestamp":1557443775000},"page":"1069-1078","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":17,"title":["Toward a modular precision ecosystem for high-performance computing"],"prefix":"10.1177","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2177-952X","authenticated-orcid":false,"given":"Hartwig","family":"Anzt","sequence":"first","affiliation":[{"name":"Steinbuch Centre for Computing, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"},{"name":"Innovative Computing Lab, University of Tennessee, Knoxville, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4154-0420","authenticated-orcid":false,"given":"Goran","family":"Flegar","sequence":"additional","affiliation":[{"name":"Departamento de Ingenieria y Ciencia de Computadores, Universitat Jaume I, Castell\u00f3n, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Gr\u00fctzmacher","sequence":"additional","affiliation":[{"name":"Steinbuch Centre for Computing, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrique S","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[{"name":"Departamento de Informatica de Sistemas y Computadores, Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2019,5,9]]},"reference":[{"key":"bibr2-1094342019846547","unstructured":"Anzt H, Dongarra J, Flegar G, et al. (2018) Variable-size batched Gauss\u2013Jordan elimination for block-Jacobi preconditioning on graphics processors. Parallel Computing. DOI: 10.1016\/j.parco.2017.12.006. Available at: http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167819117302107 (accessed 18 June 2018)."},{"key":"bibr3-1094342019846547","doi-asserted-by":"crossref","unstructured":"Anzt H, Dongarra J, Flegar G, et al. (2019) Adaptive precision in block-Jacobi preconditioning for iterative sparse linear system solvers. Concurrency and Computation: Practice and Experience 31(6). DOI: 10.1002\/cpe.4460. Available at: https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1002\/cpe.4460 (accessed 12 March 2018).","DOI":"10.1002\/cpe.4460"},{"key":"bibr4-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1145\/2834800.2834802"},{"key":"bibr5-1094342019846547","first-page":"237","volume-title":"PARA 2010, Part II, LNCS 7134","author":"Anzt H","year":"2010"},{"key":"bibr6-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2008.11.005"},{"key":"bibr7-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1177\/1094342007084026"},{"key":"bibr8-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1137\/17M1122918"},{"key":"bibr9-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1137\/17M1140819"},{"key":"bibr1-1094342019846547","unstructured":"Davis T, Hu Y, Kolodziej S. (2018) SuiteSparse Matrix Collection. Available at: https:\/\/sparse.tamu.edu (accessed April 2018)."},{"key":"bibr10-1094342019846547","doi-asserted-by":"crossref","unstructured":"Dongarra J, Hittinger J, Bell J, et al. (2014) Applied mathematics research for exascale computing. Technical report, US Department of Energy, Office of Science, Advanced Scientific Computing Research Program. Available at: https:\/\/science.energy.gov\/\u223c\/media\/ascr\/pdf\/research\/am\/docs\/EMWGreport.pdf (accessed 29 April 2019).","DOI":"10.2172\/1149042"},{"key":"bibr11-1094342019846547","unstructured":"Duranton M, Bosschere KD, Cohen A, et al. (2015) HiPEAC vision 2015. Available at: https:\/\/www.hipeac.org\/publications\/vision\/ (accessed 29 April 2019)."},{"key":"bibr12-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1080\/17445760601122076"},{"key":"bibr13-1094342019846547","doi-asserted-by":"crossref","unstructured":"Gropp WD, Kaushik DK, Keyes DE, et al. (2000) Latency, bandwidth, and concurrent issue limitations in high-performance CFD. 839\u2013842. DOI: 10.1016\/B978-008043944-0\/50783-6.","DOI":"10.1016\/B978-008043944-0\/50783-6"},{"key":"bibr14-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-10549-5_34"},{"key":"bibr15-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1109\/IA3.2018.00015"},{"key":"bibr16-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1080\/00207169208804096"},{"key":"bibr17-1094342019846547","unstructured":"Higham NJ (1996) Accuracy and stability of numerical algorithms. Society for Industrial and Applied Mathematics. ISBN: 0-89871-355-2."},{"key":"bibr18-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"bibr19-1094342019846547","first-page":"1","author":"IEEE","journal-title":"IEEE Std"},{"key":"bibr20-1094342019846547","unstructured":"Lavignon JF, et al. (2013) ETP4HPC strategic research agenda achieving HPC leadership in Europe. Available at: http:\/\/www.etp4hpc.eu\/ (accessed 29 April 2019)."},{"key":"bibr21-1094342019846547","unstructured":"Lucas R, et al. (2014) Top ten exascale research challenges. US Department Of Energy Report. Available at: http:\/\/science.energy.gov\/\u223c\/media\/ascr\/ascac\/pdf\/meetings\/20140210\/Top10reportFEB14.pdf (accessed 29 April 2019)."},{"key":"bibr22-1094342019846547","first-page":"123","volume-title":"International Green Computing Conference 2010","author":"Molka D","year":"2010"},{"key":"bibr23-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718003"},{"key":"bibr24-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2006.57"},{"key":"bibr25-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78827-0_83"},{"key":"bibr26-1094342019846547","doi-asserted-by":"publisher","DOI":"10.1145\/216585.216588"}],"container-title":["The International Journal of High Performance Computing Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1094342019846547","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/1094342019846547","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1094342019846547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T08:15:50Z","timestamp":1777450550000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/1094342019846547"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,9]]},"references-count":26,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2019,11]]}},"alternative-id":["10.1177\/1094342019846547"],"URL":"https:\/\/doi.org\/10.1177\/1094342019846547","relation":{},"ISSN":["1094-3420","1741-2846"],"issn-type":[{"value":"1094-3420","type":"print"},{"value":"1741-2846","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,9]]}}}