{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T19:20:34Z","timestamp":1729624834222,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,5]]},"DOI":"10.1109\/ipdps.2011.311","type":"proceedings-article","created":{"date-parts":[[2011,9,12]],"date-time":"2011-09-12T20:28:25Z","timestamp":1315859305000},"page":"1567-1576","source":"Crossref","is-referenced-by-count":0,"title":["Achieving Target MTTF by Duplicating Reliability-Critical Components in High Performance Computing Systems"],"prefix":"10.1109","author":[{"given":"Nithin","family":"Nakka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alok","family":"Choudhary","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gary","family":"Grider","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Bent","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Nunez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satsangat","family":"Khalsa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"crossref","first-page":"1322","DOI":"10.1109\/T-C.1971.223134","article-title":"arithmetic error codes: cost and effectiveness studies for application in digital system design","volume":"c 20","author":"avizienis","year":"1971","journal-title":"IEEE Transactions on Computers"},{"key":"ref32","article-title":"The 5ESS switching system","volume":"64","year":"1985","journal-title":"AT&T Tech Journal"},{"year":"0","key":"ref31","article-title":"AT&T 5ESS™ from top to bottom"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/FTCS.1991.146709"},{"key":"ref10","article-title":"Workload, performance, and reliability of digital computing systems","author":"castillo","year":"1981","journal-title":"the 11th FTCS"},{"key":"ref11","first-page":"575","article-title":"Jon Stearley: What Supercomputers Say: A Study of Five System Logs","author":"oliner","year":"2007","journal-title":"Proc DSN"},{"key":"ref12","article-title":"A Fault Diagnosis and Prognosis Service for TeraGrid Clusters","author":"lan","year":"2007","journal-title":"Proc of TeraGrid'07"},{"key":"ref13","article-title":"Exploring Meta–learning to Improve Failure Prediction in Supercomputing Clusters","author":"gujrati","year":"2007","journal-title":"Proceedings of ICPP"},{"key":"ref14","article-title":"Using Adaptive Fault Tolerance to Improve Application Robustness on the TeraGrid","author":"li","year":"2007","journal-title":"Proc of TeraGrid'07"},{"key":"ref15","first-page":"1647","article-title":"Adaptive Fault Management of Parallel Applications for High Performance Computing","volume":"57","author":"lan","year":"0","journal-title":"IEEE Transactions on Computers"},{"key":"ref16","article-title":"Fault–aware job scheduling for Bluegene\/L systems","author":"oliner","year":"2004","journal-title":"Proceedings of the 18th IPDPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2001.941425"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.1999.809458"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2002.1003565"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1168857.1168870"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/511334.511362"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2005.62"},{"key":"ref3","article-title":"Failure data–driven selective node–level duplication to improve MTTF in High Performance Computing Systems","author":"nakka","year":"2009","journal-title":"Proc HPCS 2009"},{"key":"ref6","article-title":"Failure analysis and modelling of a VAX cluster system","author":"tang","year":"1990","journal-title":"Fault Tolerant Computing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1147\/rd.201.0005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2004.1311948"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2006.5"},{"key":"ref7","article-title":"Networked Windows NT system field failure data analysis","author":"xu","year":"1999","journal-title":"Proc PRDC"},{"key":"ref2","article-title":"Subtleties in tolerating correlated failures","author":"nath","year":"2006","journal-title":"Proceedings of NSD1'06"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/6420.6422"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/FTCS.1998.689454"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/24.994913"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/40.755464"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/12.980007"},{"key":"ref24","first-page":"84","article-title":"AR –SMT: A micro architectural approach to fault tolerance in microprocessors","author":"rotenberg","year":"1999","journal-title":"Proceedings of the Twenty–Ninth International Symposium on Fault–Tolerant Computing Systems"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1109\/ISCA.1995.524578","article-title":"Simultaneous multithreading: Maximizing on-chip parallelism","author":"tullsen","year":"1995","journal-title":"Proceedings 22nd Annual International Symposium on Computer Architecture ISCA"},{"key":"ref26","first-page":"25","article-title":"Transient fault detection via simultaneous multithreading","author":"reinhardt","year":"2000","journal-title":"Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat No RS00201) ISCA"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/378993.379247"}],"event":{"name":"Distributed Processing, Workshops and Phd Forum (IPDPSW)","start":{"date-parts":[[2011,5,16]]},"location":"Anchorage, AK, USA","end":{"date-parts":[[2011,5,20]]}},"container-title":["2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx5\/6008655\/6008799\/06008954.pdf?arnumber=6008954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T12:25:02Z","timestamp":1686313502000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/ieeexplore.ieee.org\/document\/6008954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,5]]},"references-count":33,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/ipdps.2011.311","relation":{},"subject":[],"published":{"date-parts":[[2011,5]]}}}