{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:18:10Z","timestamp":1740169090715,"version":"3.37.3"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"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":["61502019"],"award-info":[{"award-number":["61502019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011347","name":"State Key Laboratory of Software Development Environment","doi-asserted-by":"publisher","award":["SKLSDE-2018ZX-19"],"award-info":[{"award-number":["SKLSDE-2018ZX-19"]}],"id":[{"id":"10.13039\/501100011347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2018]]},"DOI":"10.1109\/access.2018.2882394","type":"journal-article","created":{"date-parts":[[2018,11,20]],"date-time":"2018-11-20T19:56:26Z","timestamp":1542743786000},"page":"71892-71905","source":"Crossref","is-referenced-by-count":4,"title":["A Lightweight and Flexible Tool for Distinguishing Between Hardware Malfunctions and Program Bugs in Debugging Large-Scale Programs"],"prefix":"10.1109","volume":"6","author":[{"given":"Guozhen","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hailong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Depei","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/IPDPS.2007.370309"},{"year":"2018","journal-title":"HTCondor Version 8 7 7 Manual","key":"ref38"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1145\/2464996.2465001"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1145\/2541940.2541979"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1145\/1995896.1995950"},{"key":"ref30","first-page":"554","article-title":"Rainbow: Efficient memory dependence recording with high replay parallelism for relaxed memory model","author":"qian","year":"2013","journal-title":"Proc IEEE 19th Int Symp High Perform Comput Archit"},{"year":"2005","author":"duell","article-title":"The design and implementation of Berkeley Lab’s linux checkpoint\/restart","key":"ref37"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1007\/s11227-013-0884-0"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1145\/1735970.1736031"},{"key":"ref34","article-title":"SReplay: Deterministic sub-group replay for one-sided communication","author":"qian","year":"2016","journal-title":"Proc Int Conf Supercomput"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1177\/1094342014532297"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1109\/IPDPS.2009.5161063"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1145\/2692916.2555279","article-title":"Detecting silent data corruption through data dynamic monitoring for scientific applications","volume":"49","author":"gomez","year":"2014","journal-title":"ACM SIGPLAN Notices-PPoPP"},{"year":"2018","journal-title":"TotalView for HPC","key":"ref12"},{"year":"2018","journal-title":"HPC Tools ARM DDT","key":"ref13"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/1654059.1654104"},{"year":"2018","journal-title":"MRNet","key":"ref15"},{"year":"2018","journal-title":"Graphlib","key":"ref16"},{"year":"2018","journal-title":"StackWaler API","key":"ref17"},{"year":"2018","journal-title":"LaunchMON","key":"ref18"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1002\/cpe.701"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1145\/2802658.2802660","article-title":"Scalable and fault tolerant failure detection and consensus","author":"katti","year":"2015","journal-title":"Proceedings of the 22nd European MPI Users' Group Meeting"},{"year":"2018","journal-title":"Nation Supercomputer Center in Guangzhou Home Page","key":"ref4"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1007\/978-3-642-40047-6_37"},{"year":"2018","author":"zhang","journal-title":"FCR Library","key":"ref3"},{"year":"2015","author":"dongarra","journal-title":"HPCG Benchmark A New Metric for Ranking High Performance Computing Systems","key":"ref6"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/DSN.2003.1209973"},{"year":"2016","author":"petitet","journal-title":"HPL - a Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.2172\/1081941"},{"year":"2016","author":"dongarra","journal-title":"HPC Challenge Benchmark","key":"ref7"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/2898442.2898444","article-title":"Borg, omega, and kubernetes","volume":"14","author":"burns","year":"2016","journal-title":"Queue"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/TC.1984.1676475"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1177\/1094342009347767"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/SC.2000.10055"},{"key":"ref22","first-page":"499","article-title":"MC-Checker: Detecting memory consistency errors in MPI one-sided applications","author":"chen","year":"2014","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref21","first-page":"12","article-title":"Runtime checking of MPI applications with Marmot","author":"krammer","year":"2005","journal-title":"Proc Mini-Symp Tools Support Parallel Program"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1145\/2063384.2063427"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1145\/2063384.2063451"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1109\/SC.2004.29"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1145\/2493123.2462907"},{"key":"ref26","article-title":"Failure detection and propagation in HPC systems","author":"bosilca","year":"2016","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref43","article-title":"Compiler-directed lightweight checkpointing for fine-grained guaranteed soft error recovery","author":"liu","year":"2016","journal-title":"Proc Int Conf for High Perform Comput Netw Storage Anal"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/SC.2010.27"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08540813.pdf?arnumber=8540813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T00:30:34Z","timestamp":1643243434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8540813\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2882394","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2018]]}}}