{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T06:04:27Z","timestamp":1774591467060,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2014,6,23]],"date-time":"2014-06-23T00:00:00Z","timestamp":1403481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2014,6,23]]},"DOI":"10.1145\/2600212.2600219","type":"proceedings-article","created":{"date-parts":[[2014,6,20]],"date-time":"2014-06-20T13:06:05Z","timestamp":1403269565000},"page":"13-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Transparent checkpoint-restart over infiniband"],"prefix":"10.1145","author":[{"given":"Jiajun","family":"Cao","sequence":"first","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory","family":"Kerr","sequence":"additional","affiliation":[{"name":"Northeastern Universiy, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kapil","family":"Arya","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gene","family":"Cooperman","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2014,6,23]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161063"},{"key":"e_1_3_2_1_2_1","unstructured":"T. Bedeir. Building an RDMA-capable application with IB Verbs. Technical report http:\/\/www.hpcadvisorycouncil.com\/ August 2010.sloppyhttp:\/\/www.hpcadvisorycouncil.com\/pdf\/building-an-rdma-capable- application-with-ib-verbs.pdf.  T. Bedeir. Building an RDMA-capable application with IB Verbs. Technical report http:\/\/www.hpcadvisorycouncil.com\/ August 2010.sloppyhttp:\/\/www.hpcadvisorycouncil.com\/pdf\/building-an-rdma-capable- application-with-ib-verbs.pdf."},{"key":"e_1_3_2_1_3_1","volume-title":"Berkeley","author":"Bonachea D.","year":"2002","unstructured":"D. Bonachea . GASNet specification, v1.1. Technical report UCB\/CSD-02--1207, U. of California , Berkeley , October 2002 . http:\/\/digitalassets.lib.berkeley.edu\/techreports\/ucb\/text\/CSD-02--1207.pdf. D. Bonachea. GASNet specification, v1.1. Technical report UCB\/CSD-02--1207, U. of California, Berkeley, October 2002. http:\/\/digitalassets.lib.berkeley.edu\/techreports\/ucb\/text\/CSD-02--1207.pdf."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342006067469"},{"key":"e_1_3_2_1_5_1","volume-title":"Introduction to UPC and language specification. Technical report CCS-tr-99--157","author":"Carlson W. W.","year":"1999","unstructured":"W. W. Carlson , J. M. Draper , D. E. Culler , K. Yelick , E. Brooks , and K. Warren . Introduction to UPC and language specification. Technical report CCS-tr-99--157 , IDA Center for Computing Sciences , 1999 . http:\/\/upc.lbl.gov\/publications\/upctr.pdf. W. W. Carlson, J. M. Draper, D. E. Culler, K. Yelick, E. Brooks, and K. Warren. Introduction to UPC and language specification. Technical report CCS-tr-99--157, IDA Center for Computing Sciences, 1999. http:\/\/upc.lbl.gov\/publications\/upctr.pdf."},{"key":"e_1_3_2_1_6_1","volume-title":"Proc. of 2005 IEEE Computer Society International Conference on Cluster Computing","author":"Cooperman G.","year":"2005","unstructured":"G. Cooperman , J. Ansel , and X. Ma . Adaptive checkpointing for master-worker style parallelism (extended abstract) . In Proc. of 2005 IEEE Computer Society International Conference on Cluster Computing . IEEE Press , 2005 . conf. proc. on CD. G. Cooperman, J. Ansel, and X. Ma. Adaptive checkpointing for master-worker style parallelism (extended abstract). In Proc. of 2005 IEEE Computer Society International Conference on Cluster Computing. IEEE Press, 2005. conf. proc. on CD."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2006.106"},{"key":"e_1_3_2_1_8_1","volume-title":"Tutorial for DMTCP plugins, accessed","author":"MTCP","year":"2014","unstructured":"D MTCP team. Tutorial for DMTCP plugins, accessed Apr. , 2014 . http:\/\/dmtcp.sourceforge.net\/api.html. DMTCP team. Tutorial for DMTCP plugins, accessed Apr., 2014. http:\/\/dmtcp.sourceforge.net\/api.html."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/762761.762821"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2006.26"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2013.6702626"},{"key":"e_1_3_2_1_13_1","unstructured":"GWU High-Performance Computing Laboratory. UPC NAS parallel benchmarks. http:\/\/threads.hpcl.gwu.edu\/sites\/npb-upc accessed Jan. 2014 2014.  GWU High-Performance Computing Laboratory. UPC NAS parallel benchmarks. http:\/\/threads.hpcl.gwu.edu\/sites\/npb-upc accessed Jan. 2014 2014."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/46\/1\/067"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1551609.1551619"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 21$^st$ IEEE International Parallel and Distributed Processing Symposium (IPDPS) \/ 12$^th$ IEEE Workshop on Dependable Parallel, Distributed and Network-Centric Systems","author":"Hursey J.","year":"2007","unstructured":"J. Hursey , J. M. Squyres , T. I. Mattox , and A. Lumsdaine . The design and implementation of checkpoint\/restart process fault tolerance for Open MPI . In Proceedings of the 21$^st$ IEEE International Parallel and Distributed Processing Symposium (IPDPS) \/ 12$^th$ IEEE Workshop on Dependable Parallel, Distributed and Network-Centric Systems . IEEE Computer Society , March 2007 . J. Hursey, J. M. Squyres, T. I. Mattox, and A. Lumsdaine. The design and implementation of checkpoint\/restart process fault tolerance for Open MPI. In Proceedings of the 21$^st$ IEEE International Parallel and Distributed Processing Symposium (IPDPS) \/ 12$^th$ IEEE Workshop on Dependable Parallel, Distributed and Network-Centric Systems. IEEE Computer Society, March 2007."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2005.33"},{"key":"e_1_3_2_1_18_1","first-page":"531","volume-title":"CCGRID","author":"Jiang W.","year":"2004","unstructured":"W. Jiang , J. Liu , H.-W. Jin , D. K. Panda , W. Gropp , and R. Thakur . High performance MPI-2 one-sided communication over InfiniBand . In CCGRID , pages 531 -- 538 , 2004 . W. Jiang, J. Liu, H.-W. Jin, D. K. Panda, W. Gropp, and R. Thakur. High performance MPI-2 one-sided communication over InfiniBand. In CCGRID, pages 531--538, 2004."},{"key":"e_1_3_2_1_19_1","volume-title":"May","author":"Kerr G.","year":"2011","unstructured":"G. Kerr . Dissecting a small InfiniBand application using the Verbs API. arxiv:1105.1827v2 {cs.dc} technical report, arXiv.org , May 2011 . G. Kerr. Dissecting a small InfiniBand application using the Verbs API. arxiv:1105.1827v2 {cs.dc} technical report, arXiv.org, May 2011."},{"key":"e_1_3_2_1_20_1","volume-title":"July 8--10","author":"Kerr G.","year":"2011","unstructured":"G. Kerr , A. Brick , G. Cooperman , and S. Bratus . Checkpoint-restart: Proprietary hardware and the 'spiderweb API ', July 8--10 2011 . talk: abstract at http:\/\/recon.cx\/2011\/schedule\/events\/112.en.html; video at https:\/\/archive.org\/details\/Recon_2011_Checkpoint_Restart. G. Kerr, A. Brick, G. Cooperman, and S. Bratus. Checkpoint-restart: Proprietary hardware and the 'spiderweb API', July 8--10 2011. talk: abstract at http:\/\/recon.cx\/2011\/schedule\/events\/112.en.html; video at https:\/\/archive.org\/details\/Recon_2011_Checkpoint_Restart."},{"key":"e_1_3_2_1_21_1","first-page":"323","volume-title":"2007 USENIX Annual Technical Conference","author":"Laadan O.","year":"2007","unstructured":"O. Laadan and J. Nieh . Transparent checkpoint-restart of multiple processes for commodity clusters . In 2007 USENIX Annual Technical Conference , pages 323 -- 336 , 2007 . O. Laadan and J. Nieh. Transparent checkpoint-restart of multiple processes for commodity clusters. In 2007 USENIX Annual Technical Conference, pages 323--336, 2007."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2005.347039"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/1111682.1111713"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/1060289.1060323"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005056139"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005056139"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IDAACS.2007.4488396"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/1251254.1251255"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1189256.1189257"},{"key":"e_1_3_2_1_30_1","first-page":"271","volume-title":"Proceedings of the Linux Symposium (Volume Two)","author":"Woodruff B.","year":"2005","unstructured":"B. Woodruff , S. Hefty , R. Dreier , and H. Rosenstock . Introduction to the InfiniBand core software . In Proceedings of the Linux Symposium (Volume Two) , pages 271 -- 282 , July 2005 . B. Woodruff, S. Hefty, R. Dreier, and H. Rosenstock. Introduction to the InfiniBand core software. In Proceedings of the Linux Symposium (Volume Two), pages 271--282, July 2005."}],"event":{"name":"HPDC'14: The 23rd International Symposium on High-Performance Parallel and Distributed Computing","location":"Vancouver BC Canada","acronym":"HPDC'14","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 23rd international symposium on High-performance parallel and distributed computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2600212.2600219","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2600212.2600219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:10:26Z","timestamp":1750234226000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2600212.2600219"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,6,23]]},"references-count":29,"alternative-id":["10.1145\/2600212.2600219","10.1145\/2600212"],"URL":"https:\/\/doi.org\/10.1145\/2600212.2600219","relation":{},"subject":[],"published":{"date-parts":[[2014,6,23]]},"assertion":[{"value":"2014-06-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}