{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T03:18:23Z","timestamp":1761621503329,"version":"3.37.3"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2016YFB0200100"],"award-info":[{"award-number":["2016YFB0200100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91530324"],"award-info":[{"award-number":["91530324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2975832","type":"journal-article","created":{"date-parts":[[2020,2,25]],"date-time":"2020-02-25T04:08:05Z","timestamp":1582603685000},"page":"42674-42688","source":"Crossref","is-referenced-by-count":5,"title":["FT-PBLAS: PBLAS-Based Fault-Tolerant Linear Algebra Computation on High-performance Computing Systems"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4598-1063","authenticated-orcid":false,"given":"Yanchao","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4911-1161","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9956-8119","authenticated-orcid":false,"given":"Guozhen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45255-9_47"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2000.10055"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.701"},{"journal-title":"Nation Supercomputer Center in Guangzhou Home Page","year":"2018","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2872887.2750372"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2004.29"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370309"},{"journal-title":"HTCondor Version 8 7 7 Manual","year":"2018","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68564-7_5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2307\/249577"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1984.1676475"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263591"},{"article-title":"Fault tolerant matrix operations for parallel and distributed systems","year":"1996","author":"kim","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2018.00054"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2014.48"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1016\/j.jpdc.2008.12.002","article-title":"Algorithmic based fault tolerance applied to high performance computing","volume":"69","author":"bosilca","year":"2009","journal-title":"J Parallel Distrib Comput"},{"journal-title":"Accuracy and Stability of Numerical Algorithms","year":"1996","author":"higham","key":"ref17"},{"journal-title":"Open MPI Documentation","year":"2020","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPCASIA.2004.1324026"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063451"},{"key":"ref4","first-page":"1","article-title":"ScaLAPACK: A linear algebra library for message-passing computers","author":"blackford","year":"1997","journal-title":"Proc SIAM Conf Parallel Process Sci Comput"},{"key":"ref27","first-page":"131","article-title":"WuKong: Automatically detecting and localizing bugs that manifest at large system scales","author":"zhou","year":"2013","journal-title":"Proc Int Symp High-Perform Parallel Distrib Comput"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/77626.79170"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/46\/1\/067"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2008.58"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2016.10.002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2016.2606378"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161063"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-016-5588-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"journal-title":"Summit-IBM Power System AC 922 IBM POWER9 22C NVDIA Volta GV100 Dual-Rail Mellannox EDR Infiniband","year":"2020","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2642769.2642774"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/12.57055"},{"key":"ref21","first-page":"767","article-title":"Algorithm based fault tolerant matrix operations for parallel and distributed systems: Block checksum methods","author":"stefanidis","year":"2003","journal-title":"Proc 6th Hellenic-Eur Conf Comput Math Appl"},{"key":"ref24","first-page":"1","article-title":"FTI: High performance fault tolerance interface for hybrid systems","author":"bautistagomez","year":"2011","journal-title":"Proc Conf High Perform Comput Netw Storage Anal"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/12.494099"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.46"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2882394"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09007454.pdf?arnumber=9007454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T19:30:10Z","timestamp":1643311810000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9007454\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2975832","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}