{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:13:04Z","timestamp":1763467984159,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2010,6,2]],"date-time":"2010-06-02T00:00:00Z","timestamp":1275436800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100006192","name":"Advanced Scientific Computing Research","doi-asserted-by":"publisher","award":["DE-AC02-06CH11357DE-SC00003777"],"award-info":[{"award-number":["DE-AC02-06CH11357DE-SC00003777"]}],"id":[{"id":"10.13039\/100006192","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","award":["DE-AC05-00OR22725","DE-AC02-06CH11357DE-SC00003777"],"award-info":[{"award-number":["DE-AC05-00OR22725","DE-AC02-06CH11357DE-SC00003777"]}],"id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2010,6,2]]},"DOI":"10.1145\/1810085.1810120","type":"proceedings-article","created":{"date-parts":[[2010,6,8]],"date-time":"2010-06-08T12:37:34Z","timestamp":1276000654000},"page":"253-262","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":31,"title":["Speeding up Nek5000 with autotuning and specialization"],"prefix":"10.1145","author":[{"given":"Jaewook","family":"Shin","sequence":"first","affiliation":[{"name":"Argonne National Laboratory, Argonne, IL"}]},{"given":"Mary W.","family":"Hall","sequence":"additional","affiliation":[{"name":"University of Utah, Salt Lake City, UT"}]},{"given":"Jacqueline","family":"Chame","sequence":"additional","affiliation":[{"name":"USC \/ ISI, Marina del Rey, CA"}]},{"given":"Chun","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Utah, Salt Lake City, UT"}]},{"given":"Paul F.","family":"Fischer","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Argonne, IL"}]},{"given":"Paul D.","family":"Hovland","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Argonne, IL"}]}],"member":"320","published-online":{"date-parts":[[2010,6,2]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"http:\/\/nek5000.mcs.anl.gov.  http:\/\/nek5000.mcs.anl.gov."},{"key":"e_1_3_2_1_2_1","unstructured":"2009 INCITE Fact Sheet 2009. http:\/\/www.sc.doe.gov\/ascr\/incite\/index.html.  2009 INCITE Fact Sheet 2009. http:\/\/www.sc.doe.gov\/ascr\/incite\/index.html."},{"key":"e_1_3_2_1_3_1","volume-title":"The 19th International Workshop on Languages and Compilers for Parallel Computing (LCPC 2006","author":"Barthou Denis","year":"2006","unstructured":"Denis Barthou , Sebastien Donadio , Alexandre Duchateau , William Jalby , and Eric Courtois . Iterative compilation by exploration of kernel decomposition . In The 19th International Workshop on Languages and Compilers for Parallel Computing (LCPC 2006 ), New Orleans, LA , 2006 . Denis Barthou, Sebastien Donadio, Alexandre Duchateau, William Jalby, and Eric Courtois. Iterative compilation by exploration of kernel decomposition. In The 19th International Workshop on Languages and Compilers for Parallel Computing (LCPC 2006), New Orleans, LA, 2006."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263662"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1177\/109434200001400303"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2005.10"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511546792","volume-title":"High-Order Methods for Incompressible Fluid Flow","author":"Deville M. O.","year":"2002","unstructured":"M. O. Deville , P. F. Fischer , and E. H. Mund . High-Order Methods for Incompressible Fluid Flow . Cambridge , 2002 . M. O. Deville, P. F. Fischer, and E. H. Mund. High-Order Methods for Incompressible Fluid Flow. Cambridge, 2002."},{"key":"e_1_3_2_1_10_1","first-page":"125","article-title":"Petascale algorithms for reactor hydrodynamics","author":"Fischer Paul","year":"2008","unstructured":"Paul Fischer , James Lottes , David Pointer , and Andrew Siegel . Petascale algorithms for reactor hydrodynamics . Journal of Physics: Conference Series , 125 , 2008 . Paul Fischer, James Lottes, David Pointer, and Andrew Siegel. Petascale algorithms for reactor hydrodynamics. Journal of Physics: Conference Series, 125, 2008.","journal-title":"Journal of Physics: Conference Series"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/504210.504213"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13374-9_4"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161004"},{"key":"e_1_3_2_1_16_1","first-page":"461","volume-title":"9th International Euro-Par Conference","author":"Jos\u00e9","year":"2003","unstructured":"Jos\u00e9 R. Herrero and Juan J. Navarro. Improving performance of hypermatrix Cholesky factorization . In 9th International Euro-Par Conference , pages 461 -- 469 , 2003 . Jos\u00e9 R. Herrero and Juan J. Navarro. Improving performance of hypermatrix Cholesky factorization. In 9th International Euro-Par Conference, pages 461--469, 2003."},{"volume-title":"Intel Fortran Compiler User and Reference Guides","year":"2008","key":"e_1_3_2_1_17_1","unstructured":"Intel. Intel Fortran Compiler User and Reference Guides , 2008 . http:\/\/www.intel.com\/cd\/software\/products\/asmo-na\/eng\/406088.htm. Intel. Intel Fortran Compiler User and Reference Guides, 2008. http:\/\/www.intel.com\/cd\/software\/products\/asmo-na\/eng\/406088.htm."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/780732.780735"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454119"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(84)90128-1"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2007.21"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375594"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840306"},{"key":"e_1_3_2_1_25_1","volume-title":"Exploiting superword-level locality in multimedia extension architectures. Journal of Instruction Level Parallelism (JILP), 5:1--28","author":"Shin Jaewook","year":"2003","unstructured":"Jaewook Shin , Jacqueline Chame , and Mary W. Hall . Exploiting superword-level locality in multimedia extension architectures. Journal of Instruction Level Parallelism (JILP), 5:1--28 , 2003 . Jaewook Shin, Jacqueline Chame, and Mary W. Hall. Exploiting superword-level locality in multimedia extension architectures. Journal of Instruction Level Parallelism (JILP), 5:1--28, 2003."},{"key":"e_1_3_2_1_26_1","volume-title":"The Fourth International Workshop on Automatic Performance Tuning","author":"Shin Jaewook","year":"2009","unstructured":"Jaewook Shin , Mary W. Hall , Jacqueline Chame , Chun Chen , and Paul D. Hovland . Autotuning and specialization: Speeding up matrix multiply for small matrices with compiler technology . In The Fourth International Workshop on Automatic Performance Tuning , October 2009 . Jaewook Shin, Mary W. Hall, Jacqueline Chame, Chun Chen, and Paul D. Hovland. Autotuning and specialization: Speeding up matrix multiply for small matrices with compiler technology. In The Fourth International Workshop on Automatic Performance Tuning, October 2009."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161054"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/331532.331599"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2009.33"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/16\/1\/071"},{"key":"e_1_3_2_1_31_1","volume-title":"SuperComputing","author":"Clint Whaley R.","year":"1998","unstructured":"R. Clint Whaley and Jack J. Dongarra . Automatically tuned linear algebra software . In SuperComputing , 1998 . R. Clint Whaley and Jack J. Dongarra. Automatically tuned linear algebra software. In SuperComputing, 1998."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370637"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840444"}],"event":{"name":"ICS'10: International Conference on Supercomputing","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"],"location":"Tsukuba Ibaraki Japan","acronym":"ICS'10"},"container-title":["Proceedings of the 24th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1810085.1810120","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1810085.1810120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T11:23:24Z","timestamp":1750245804000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1810085.1810120"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,6,2]]},"references-count":28,"alternative-id":["10.1145\/1810085.1810120","10.1145\/1810085"],"URL":"https:\/\/doi.org\/10.1145\/1810085.1810120","relation":{},"subject":[],"published":{"date-parts":[[2010,6,2]]},"assertion":[{"value":"2010-06-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}