{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T03:48:18Z","timestamp":1772164098511,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,3,25]],"date-time":"2017-03-25T00:00:00Z","timestamp":1490400000000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR0011-13- 3-0001"],"award-info":[{"award-number":["HR0011-13- 3-0001"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,3,25]]},"DOI":"10.1145\/2872362.2872411","type":"proceedings-article","created":{"date-parts":[[2016,3,28]],"date-time":"2016-03-28T09:24:30Z","timestamp":1459157070000},"page":"325-338","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Architecture-Adaptive Code Variant Tuning"],"prefix":"10.1145","author":[{"given":"Saurav","family":"Muralidharan","sequence":"first","affiliation":[{"name":"University of Utah, Salt Lake City, UT, USA"}]},{"given":"Amit","family":"Roy","sequence":"additional","affiliation":[{"name":"University of Utah, Salt Lake City, UT, USA"}]},{"given":"Mary","family":"Hall","sequence":"additional","affiliation":[{"name":"University of Utah, Salt Lake City, UT, USA"}]},{"given":"Michael","family":"Garland","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation, Santa Clara, CA, USA"}]},{"given":"Piyush","family":"Rai","sequence":"additional","affiliation":[{"name":"IIT Kanpur, Kanpur, India"}]}],"member":"320","published-online":{"date-parts":[[2016,3,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1542476.1542481"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/266469.266486"},{"key":"e_1_3_2_1_3_1","unstructured":"S. Baxter. Modern GPU library. http:\/\/nvlabs.github.io\/moderngpu\/."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654078"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01970-8_45"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263662"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 11th International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Bonilla E. V.","year":"2007","unstructured":"E. V. Bonilla, F. V. Agakov, and C. K. I. Williams. Kernel multi-task learning using task-specific features. In Proceedings of the 11th International Conference on Artificial Intelligence and Statistics (AISTATS), 2007."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"e_1_3_2_1_9_1","unstructured":"B. Catanzaro. In-place matrix transposition. https:\/\/github.com\/bryancatanzaro\/inplace."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555253"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2007.32"},{"key":"e_1_3_2_1_12_1","unstructured":"C. Chen. Model-guided empirical optimization for memory hierarchy. In Ph.D dissertation University of Southern California May 2007."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.70"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1137\/070693199"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2737924.2737969"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69330-7_10"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.21236\/ADA479065"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161004"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/1196431"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_24"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470421"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161248"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503268"},{"key":"e_1_3_2_1_25_1","unstructured":"D. Merrill. Back40 Computing natexlaba. http:\/\/code.google.com\/p\/back40computing\/."},{"key":"e_1_3_2_1_26_1","unstructured":"D. Merrill. CUDA Unbound (CUB) natexlabb. http:\/\/nvlabs.github.io\/cub\/."},{"key":"e_1_3_2_1_27_1","volume-title":"Proc. Innovative Parallel Computing (InPar 2012)","author":"Merrill D.","unstructured":"D. Merrill, M. Garland, and A. Grimshaw. Policy-based tuning for performance portability and library co-optimization. In Proc. Innovative Parallel Computing (InPar 2012), May 2012\\natexlaba."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145832"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.59"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2004.61"},{"key":"e_1_3_2_1_31_1","unstructured":"E. Photonics and NVIDIA. CULA $|$ sparse. http:\/\/www.culatools.com\/."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840306"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454155"},{"key":"e_1_3_2_1_34_1","unstructured":"S. Sanfilippo and P. Noordhuis. Redis. http:\/\/redis.io."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2005.29"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161054"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/16\/1\/071"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(00)00087-9"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370637"}],"event":{"name":"ASPLOS '16: Architectural Support for Programming Languages and Operating Systems","location":"Atlanta Georgia USA","acronym":"ASPLOS '16","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the Twenty-First International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2872362.2872411","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2872362.2872411","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2872362.2872411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:40:37Z","timestamp":1763458837000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2872362.2872411"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3,25]]},"references-count":39,"alternative-id":["10.1145\/2872362.2872411","10.1145\/2872362"],"URL":"https:\/\/doi.org\/10.1145\/2872362.2872411","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/2954679.2872411","asserted-by":"object"},{"id-type":"doi","id":"10.1145\/2980024.2872411","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2016,3,25]]},"assertion":[{"value":"2016-03-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}