{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T18:11:56Z","timestamp":1758823916718,"version":"3.38.0"},"reference-count":31,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:00:00Z","timestamp":1634688000000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.sagepub.com\/licence-information-for-chorus"}],"funder":[{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}],"id":[{"id":"10.13039\/100006132","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":[[2021,1]]},"abstract":"<jats:p> In this work, we collect data from runs of Krylov subspace methods and pipelined Krylov algorithms in an effort to understand and model the impact of machine noise and other sources of variability on performance. We find large variability of Krylov iterations between compute nodes for standard methods that is reduced in pipelined algorithms, directly supporting conjecture, as well as large variation between statistical distributions of runtimes across iterations. Based on these results, we improve upon a previously introduced nondeterministic performance model by allowing iterations to fluctuate over time. We present our data from runs of various Krylov algorithms across multiple platforms as well as our updated non-stationary model that provides good agreement with observations. We also suggest how it can be used as a predictive tool. <\/jats:p>","DOI":"10.1177\/1094342020966835","type":"journal-article","created":{"date-parts":[[2020,10,20]],"date-time":"2020-10-20T10:12:24Z","timestamp":1603188744000},"page":"47-59","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":2,"title":["Understanding performance variability in standard and pipelined parallel Krylov solvers"],"prefix":"10.1177","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8830-6861","authenticated-orcid":false,"given":"Hannah","family":"Morgan","sequence":"first","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}]},{"given":"Patrick","family":"Sanan","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"given":"Matthew","family":"Knepley","sequence":"additional","affiliation":[{"name":"University at Buffalo, Buffalo, NY, USA"}]},{"given":"Richard Tran","family":"Mills","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}]}],"member":"179","published-online":{"date-parts":[[2020,10,20]]},"reference":[{"key":"bibr1-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1007\/11602569_31"},{"volume-title":"Cray Inc., White Paper WP-Aries01-1112","year":"2012","author":"Alverson B","key":"bibr2-1094342020966835"},{"key":"bibr3-1094342020966835","unstructured":"Balay S, Abhyankar S, Adams MF, et al. (2018a) PETSc users manual. Technical Report ANL-95\/11\u2014Revision 3.10, Argonne National Laboratory. Available at: http:\/\/www.mcs.anl.gov\/petsc. (accessed 1 October 2019)"},{"key":"bibr4-1094342020966835","unstructured":"Balay S, Abhyankar S, Adams MF, et al. (2018b) PETSc Web page. Available at: http:\/\/www.mcs.anl.gov\/petsc (accessed 1 October 2019)."},{"key":"bibr5-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2006.311846"},{"key":"bibr6-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1017\/S0269964806060414"},{"key":"bibr7-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(89)90045-9"},{"key":"bibr8-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126926"},{"key":"bibr9-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2017.04.005"},{"key":"bibr10-1094342020966835","volume-title":"Mathematical Methods of Statistics","volume":"9","author":"Cram\u00e9r H","year":"2016"},{"key":"bibr11-1094342020966835","first-page":"5829","volume":"9","author":"David HA","year":"2004","journal-title":"Encyclopedia of Statistical Sciences"},{"key":"bibr12-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5219920"},{"key":"bibr13-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2013.06.001"},{"key":"bibr14-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1137\/12086563X"},{"key":"bibr15-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48158-3_2"},{"key":"bibr16-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.76"},{"key":"bibr17-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2014.10"},{"key":"bibr18-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362692"},{"key":"bibr19-1094342020966835","first-page":"1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Hoefler T","year":"2010"},{"key":"bibr20-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5205-5_15"},{"volume-title":"Code for Q Workshop","year":"2016","author":"Kumaran K","key":"bibr21-1094342020966835"},{"key":"bibr22-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3820"},{"volume-title":"Cray User Group Proceedings","year":"2017","author":"Parker S","key":"bibr23-1094342020966835"},{"key":"bibr24-1094342020966835","doi-asserted-by":"publisher","DOI":"10.5194\/tcd-2-111-2008"},{"volume-title":"Iterative Methods for Sparse Linear Systems","year":"1996","author":"Saad Y","key":"bibr25-1094342020966835"},{"key":"bibr26-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470398"},{"key":"bibr27-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2015.7477467"},{"key":"bibr28-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2006.57"},{"key":"bibr29-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1016\/0168-9274(95)00079-A"},{"key":"bibr30-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511615115"},{"key":"bibr31-1094342020966835","doi-asserted-by":"publisher","DOI":"10.1137\/0913035"}],"container-title":["The International Journal of High Performance Computing Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1094342020966835","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/1094342020966835","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1094342020966835","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1094342020966835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T18:15:07Z","timestamp":1741025707000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/1094342020966835"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,20]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1177\/1094342020966835"],"URL":"https:\/\/doi.org\/10.1177\/1094342020966835","relation":{},"ISSN":["1094-3420","1741-2846"],"issn-type":[{"type":"print","value":"1094-3420"},{"type":"electronic","value":"1741-2846"}],"subject":[],"published":{"date-parts":[[2020,10,20]]}}}