{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:44:36Z","timestamp":1780058676296,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2013,11,17]],"date-time":"2013-11-17T00:00:00Z","timestamp":1384646400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF ITR-HECURA-0833188, NSF CNS 09-58314"],"award-info":[{"award-number":["NSF ITR-HECURA-0833188, NSF CNS 09-58314"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DOE DE-SC0001845"],"award-info":[{"award-number":["DOE DE-SC0001845"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000144","name":"Division of Computer and Network Systems","doi-asserted-by":"publisher","award":["NSF ITR-HECURA-0833188, NSF CNS 09-58314"],"award-info":[{"award-number":["NSF ITR-HECURA-0833188, NSF CNS 09-58314"]}],"id":[{"id":"10.13039\/100000144","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2013,11,17]]},"DOI":"10.1145\/2503210.2503228","type":"proceedings-article","created":{"date-parts":[[2013,10,30]],"date-time":"2013-10-30T12:55:22Z","timestamp":1383137722000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["A 'cool' way of improving the reliability of HPC machines"],"prefix":"10.1145","author":[{"given":"Osman","family":"Sarood","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esteban","family":"Meneses","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laxmikant V.","family":"Kale","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2013,11,17]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"T. Renzenbrink \"Data Centers Use 1.3% of World\u00d5s Total Electricity. A Decline in growth.\" {Online}. Available: http:\/\/www.techthefuture.com\/energy\/  T. Renzenbrink \"Data Centers Use 1.3% of World\u00d5s Total Electricity. A Decline in growth.\" {Online}. Available: http:\/\/www.techthefuture.com\/energy\/"},{"issue":"36908","key":"e_1_3_2_1_2_1","first-page":"129","article-title":"Smart cooling of data centers","volume":"2003","author":"Patel C. D.","year":"2003","unstructured":"C. D. Patel , C. E. Bash , R. Sharma , M. Beitelmal , and R. Friedrich , \" Smart cooling of data centers ,\" ASME Conference Proceedings , vol. 2003 , no. 36908 b, pp. 129 -- 137 , 2003 . C. D. Patel, C. E. Bash, R. Sharma, M. Beitelmal, and R. Friedrich, \"Smart cooling of data centers,\" ASME Conference Proceedings, vol. 2003, no. 36908b, pp. 129--137, 2003.","journal-title":"ASME Conference Proceedings"},{"key":"e_1_3_2_1_3_1","volume-title":"Uptime Institute","author":"Sullivan R. F.","year":"2000","unstructured":"R. F. Sullivan , \"Alternating cold and hot aisles provides more reliable cooling for server farms,\" White Paper , Uptime Institute , 2000 . R. F. Sullivan, \"Alternating cold and hot aisles provides more reliable cooling for server farms,\" White Paper, Uptime Institute, 2000."},{"key":"e_1_3_2_1_4_1","volume-title":"American Power Conversion","author":"Sawyer R.","year":"2004","unstructured":"R. Sawyer , \"Calculating total power requirements for data centers,\" White Paper , American Power Conversion , 2004 . R. Sawyer, \"Calculating total power requirements for data centers,\" White Paper, American Power Conversion, 2004."},{"key":"e_1_3_2_1_5_1","unstructured":"R. American Society of Heating and A.-C. Engineers \"2008 ashrae environmental guidelines for datacom equipment.\" {Online}. Available: http:\/\/tc99.ashraetcs.org\/documents\/ASHRAE_Extended_Environmental_Envelope_Final_Aug_1_2008.pdf  R. American Society of Heating and A.-C. Engineers \"2008 ashrae environmental guidelines for datacom equipment.\" {Online}. Available: http:\/\/tc99.ashraetcs.org\/documents\/ASHRAE_Extended_Environmental_Envelope_Final_Aug_1_2008.pdf"},{"key":"e_1_3_2_1_6_1","unstructured":"A. Liu \"The data center temperature debate.\" {Online}. Available: http:\/\/ezinearticles.com\/?The-Data-Center-Temperature-Debate&id=2637938  A. Liu \"The data center temperature debate.\" {Online}. Available: http:\/\/ezinearticles.com\/?The-Data-Center-Temperature-Debate&id=2637938"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063412"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2012.143"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2005.440"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/957717.957772"},{"key":"e_1_3_2_1_11_1","unstructured":"W.-C. Feng \"The Importance of Being Low Power in High-Performance Computing \" Cyberinfrastructure Technology Watch Quarterly (CTWatch Quarterly) vol. 1 no. 3 August 2005.  W.-C. Feng \"The Importance of Being Low Power in High-Performance Computing \" Cyberinfrastructure Technology Watch Quarterly (CTWatch Quarterly) vol. 1 no. 3 August 2005."},{"key":"e_1_3_2_1_12_1","unstructured":"Ericsson \"Reliability Aspects on Power Supplies \" Technical ReportDesign Note 002 Ericsson Microelectronics April 2000.  Ericsson \"Reliability Aspects on Power Supplies \" Technical ReportDesign Note 002 Ericsson Microelectronics April 2000 ."},{"key":"e_1_3_2_1_13_1","first-page":"17","article-title":"The Chare Kernel parallel programming language and system","author":"Kal\u00e9 L.","year":"1990","unstructured":"L. Kal\u00e9 , \" The Chare Kernel parallel programming language and system ,\" in Proceedings of the International Conference on Parallel Processing , vol. II , Aug. 1990 , pp. 17 -- 25 . L. Kal\u00e9, \"The Chare Kernel parallel programming language and system,\" in Proceedings of the International Conference on Parallel Processing, vol. II, Aug. 1990, pp. 17--25.","journal-title":"Proceedings of the International Conference on Parallel Processing"},{"key":"e_1_3_2_1_14_1","first-page":"177","volume-title":"2004 International Conference on","author":"Srinivasan J.","year":"2004","unstructured":"J. Srinivasan , S. Adve , P. Bose , and J. Rivers , \" The impact of technology scaling on lifetime reliability,\" in Dependable Systems and Networks , 2004 International Conference on , 2004 , pp. 177 -- 186 . J. Srinivasan, S. Adve, P. Bose, and J. Rivers, \"The impact of technology scaling on lifetime reliability,\" in Dependable Systems and Networks, 2004 International Conference on, 2004, pp. 177--186."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2005.440"},{"key":"e_1_3_2_1_16_1","first-page":"209","volume-title":"Proceedings. 18th International","author":"Petrini F.","year":"2004","unstructured":"F. Petrini , K. Davis , and J. Sancho , \" System-level fault-tolerance in large-scale parallel machines with buffered coscheduling,\" in Parallel and Distributed Processing Symposium, 2004 . Proceedings. 18th International , 2004 , pp. 209 --. F. Petrini, K. Davis, and J. Sancho, \"System-level fault-tolerance in large-scale parallel machines with buffered coscheduling,\" in Parallel and Distributed Processing Symposium, 2004. Proceedings. 18th International, 2004, pp. 209--."},{"key":"e_1_3_2_1_17_1","first-page":"93","volume-title":"CA","author":"Zheng G.","year":"2004","unstructured":"G. Zheng , L. Shi , and L. V. Kal\u00e9 , \" FTC-Charm++: An In-Memory Checkpoint-Based Fault Tolerant Runtime for Charm++ and MPI,\" in 2004 IEEE International Conference on Cluster Computing, San Diego , CA , September 2004 , pp. 93 -- 103 . G. Zheng, L. Shi, and L. V. Kal\u00e9, \"FTC-Charm++: An In-Memory Checkpoint-Based Fault Tolerant Runtime for Charm++ and MPI,\" in 2004 IEEE International Conference on Cluster Computing, San Diego, CA, September 2004, pp. 93--103."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2004.11.016"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/361147.361115"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063427"},{"key":"e_1_3_2_1_21_1","volume-title":"Berkeley lab checkpoint\/restart (blcr) for linux clusters,\" in SciDAC","author":"Hargrove P. H.","year":"2006","unstructured":"P. H. Hargrove and J. C. Duell , \" Berkeley lab checkpoint\/restart (blcr) for linux clusters,\" in SciDAC , 2006 . P. H. Hargrove and J. C. Duell, \"Berkeley lab checkpoint\/restart (blcr) for linux clusters,\" in SciDAC, 2006."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.18"},{"key":"e_1_3_2_1_23_1","unstructured":"\"Lulesh \" http:\/\/computation.llnl.gov\/casc\/ShockHydro\/.  \"Lulesh \" http:\/\/computation.llnl.gov\/casc\/ShockHydro\/."},{"key":"e_1_3_2_1_24_1","first-page":"167","volume-title":"Handling application-induced load imbalance using parallel objects,\" in Parallel and Distributed Computing for Symbolic and Irregular Applications","author":"Brunner R. K.","year":"2000","unstructured":"R. K. Brunner and L. V. Kal\u00e9 , \" Handling application-induced load imbalance using parallel objects,\" in Parallel and Distributed Computing for Symbolic and Irregular Applications . World Scientific Publishing , 2000 , pp. 167 -- 181 . R. K. Brunner and L. V. Kal\u00e9, \"Handling application-induced load imbalance using parallel objects,\" in Parallel and Distributed Computing for Symbolic and Irregular Applications. World Scientific Publishing, 2000, pp. 167--181."},{"key":"e_1_3_2_1_26_1","first-page":"2008","article-title":"Massively parallel cosmological simulations with ChaNGa","author":"Jetley P.","year":"2008","unstructured":"P. Jetley , F. Gioachin , C. Mendes , L. V. Kale , and T. R. Quinn , \" Massively parallel cosmological simulations with ChaNGa ,\" in Proceedings of IEEE International Parallel and Distributed Processing Symposium 2008 , 2008 . P. Jetley, F. Gioachin, C. Mendes, L. V. Kale, and T. R. Quinn, \"Massively parallel cosmological simulations with ChaNGa,\" in Proceedings of IEEE International Parallel and Distributed Processing Symposium 2008, 2008.","journal-title":"Proceedings of IEEE International Parallel and Distributed Processing Symposium"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342010394383"},{"key":"e_1_3_2_1_28_1","unstructured":"\"Intel turbo boost technology \" http:\/\/www.intel.com\/technology\/turboboost\/.  \"Intel turbo boost technology \" http:\/\/www.intel.com\/technology\/turboboost\/."},{"key":"e_1_3_2_1_29_1","volume-title":"Exascale computing study: Technology challenges in achieving exascale systems","author":"Kogge P.","year":"2008","unstructured":"P. Kogge , K. Bergman , S. Borkar , D. Campbell , W. Carlson , W. Dally , M. Denneau , P. Franzon , W. Harrod , J. Hiller , S. Karp , S. Keckler , D. Klein , R. Lucas , M. Richards , A. Scarpelli , S. Scott , A. Snavely , T. Sterling , R. S. Williams , and K. Yelick , \" Exascale computing study: Technology challenges in achieving exascale systems ,\" 2008 . P. Kogge, K. Bergman, S. Borkar, D. Campbell, W. Carlson, W. Dally, M. Denneau, P. Franzon, W. Harrod, J. Hiller, S. Karp, S. Keckler, D. Klein, R. Lucas, M. Richards, A. Scarpelli, S. Scott, A. Snavely, T. Sterling, R. S. Williams, and K. Yelick, \"Exascale computing study: Technology challenges in achieving exascale systems,\" 2008."},{"key":"e_1_3_2_1_30_1","unstructured":"\"Top500 supercomputing sites \" http:\/\/top500.org.  \"Top500 supercomputing sites \" http:\/\/top500.org."},{"key":"e_1_3_2_1_31_1","unstructured":"B. Schroeder and G. A. Gibson \"Understanding failures in petascale computers.\"  B. Schroeder and G. A. Gibson \"Understanding failures in petascale computers.\""},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.379"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2008.4510752"},{"key":"e_1_3_2_1_34_1","first-page":"276","volume-title":"ISCA '04","author":"Srinivasan J.","year":"2004","unstructured":"J. Srinivasan , S. V. Adve , P. Bose , and J. A. Rivers , \" The case for lifetime reliability-aware microprocessors,\" in Proceedings of the 31st annual international symposium on Computer architecture, ser . ISCA '04 . Washington, DC, USA: IEEE Computer Society , 2004 , pp. 276 --. {Online}. Available: http:\/\/dl.acm.org\/citation.cfm?id=998680.1006725 J. Srinivasan, S. V. Adve, P. Bose, and J. A. Rivers, \"The case for lifetime reliability-aware microprocessors,\" in Proceedings of the 31st annual international symposium on Computer architecture, ser. ISCA '04. Washington, DC, USA: IEEE Computer Society, 2004, pp. 276--. {Online}. Available: http:\/\/dl.acm.org\/citation.cfm?id=998680.1006725"},{"key":"e_1_3_2_1_35_1","volume-title":"USA","author":"Meneses E.","year":"2012","unstructured":"E. Meneses , X. Ni , and L. V. Kale , \" A Message-Logging Protocol for Multicore Systems,\" in Proceedings of the 2nd Workshop on Fault-Tolerance for HPC at Extreme Scale (FTXS), Boston , USA , June 2012 . E. Meneses, X. Ni, and L. V. Kale, \"A Message-Logging Protocol for Multicore Systems,\" in Proceedings of the 2nd Workshop on Fault-Tolerance for HPC at Extreme Scale (FTXS), Boston, USA, June 2012."},{"key":"e_1_3_2_1_36_1","volume-title":"A fault tolerance protocol with fast fault recovery,\" in Proceedings of the 21st IEEE International Parallel and Distributed Processing Symposium","author":"Chakravorty S.","year":"2007","unstructured":"S. Chakravorty and L. V. Kale , \" A fault tolerance protocol with fast fault recovery,\" in Proceedings of the 21st IEEE International Parallel and Distributed Processing Symposium . IEEE Press , 2007 . S. Chakravorty and L. V. Kale, \"A fault tolerance protocol with fast fault recovery,\" in Proceedings of the 21st IEEE International Parallel and Distributed Processing Symposium. IEEE Press, 2007."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD.2012.12"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063443"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2005.54"}],"event":{"name":"SC13: International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Denver Colorado","acronym":"SC13","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS Computer Society"]},"container-title":["Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2503210.2503228","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2503210.2503228","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:18:55Z","timestamp":1750234735000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2503210.2503228"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,11,17]]},"references-count":38,"alternative-id":["10.1145\/2503210.2503228","10.1145\/2503210"],"URL":"https:\/\/doi.org\/10.1145\/2503210.2503228","relation":{},"subject":[],"published":{"date-parts":[[2013,11,17]]},"assertion":[{"value":"2013-11-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}