{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:11:55Z","timestamp":1750306315331,"version":"3.41.0"},"reference-count":37,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2016,8,17]],"date-time":"2016-08-17T00:00:00Z","timestamp":1471392000000},"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":["ACM Trans. Archit. Code Optim."],"published-print":{"date-parts":[[2016,9,17]]},"abstract":"<jats:p>\n            In the wake of the current trend of increasing the number of cores on a chip, compiler optimizations for improving the memory performance have assumed increased importance. Loop fusion is one such key optimization that can alleviate\n            <jats:italic>memory<\/jats:italic>\n            and\n            <jats:italic>bandwidth wall<\/jats:italic>\n            and thus improve parallel performance. However, we find that loop fusion in interesting memory-intensive applications is prevented by the existence of dependences between temporary variables that appear in different loop nests. Furthermore, known techniques of allowing useful transformations in the presence of temporary variables, such as privatization and expansion, prove insufficient in such cases.\n          <\/jats:p>\n          <jats:p>\n            In this work, we introduce\n            <jats:italic>variable liberalization<\/jats:italic>\n            , a technique that selectively removes dependences on temporary variables in different loop nests to achieve loop fusion while preserving the semantical correctness of the optimized program. This removal of extra-stringent dependences effectively amounts to variable expansion, thus achieving the benefit of an increased degree of freedom for program transformation but without an actual expansion. Hence, there is no corresponding increase in the memory footprint incurred. We implement\n            <jats:italic>liberalization<\/jats:italic>\n            in the Pluto polyhedral compiler and evaluate its performance on nine hot regions in five real applications. Results demonstrate parallel performance improvement of 1.92 \u00d7 over the Intel compiler, averaged over the nine hot regions, and an overall improvement of as much as 2.17 \u00d7 for an entire application, on an eight-core Intel Xeon processor.\n          <\/jats:p>","DOI":"10.1145\/2963101","type":"journal-article","created":{"date-parts":[[2016,8,26]],"date-time":"2016-08-26T12:25:39Z","timestamp":1472214339000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Variable Liberalization"],"prefix":"10.1145","volume":"13","author":[{"given":"Sanyam","family":"Mehta","sequence":"first","affiliation":[{"name":"University of Minnesota, Twin Cities"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pen-Chung","family":"Yew","sequence":"additional","affiliation":[{"name":"University of Minnesota, Twin Cities, Minneapolis, MN"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2016,8,17]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2688500.2688512"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400711"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375595"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/93542.93553"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/646347.690242"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-005-4937-3"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2003.09.005"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/55364.55406"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-006-0012-3"},{"key":"e_1_2_1_10_1","volume-title":"Proceedings of the First International Workshop on Polyhedral Compilation Techniques (IMPACT)","volume":"2011","author":"Grosser Tobias","year":"2011"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/11688839_20"},{"key":"e_1_2_1_12_1","unstructured":"Intel. 2015. \n      Intel\u2019s\n       V\n      Tune\n    .\n   (\n  2015\n  ). Available at www.intel.com\/Software\/Products.  Intel. 2015. Intel\u2019s VTune. (2015). Available at www.intel.com\/Software\/Products."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2491960"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/645671.665526"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(98)00029-5"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/143369.143426"},{"key":"e_1_2_1_17_1","unstructured":"LLNL.\n       2015. ROSE \n      Compiler\n    .\n   (\n  2015\n  ). Available at http:\/\/rosecompiler.org\/.  LLNL. 2015. ROSE Compiler. (2015). Available at http:\/\/rosecompiler.org\/."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/158511.158515"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/258492.258520"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555250"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2737924.2737954"},{"key":"e_1_2_1_23_1","unstructured":"OSU. 2012. PolyOpt: a Polyhedral Optimizer for the ROSE compiler. (2012). Available at http:\/\/www.cse.ohio-state.edu\/pouchet\/software\/polyopt\/.  OSU. 2012. PolyOpt: a Polyhedral Optimizer for the ROSE compiler. (2012). Available at http:\/\/www.cse.ohio-state.edu\/pouchet\/software\/polyopt\/."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375594"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2007.21"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/365151.365152"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.752782"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/40.6.340"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/378795.378852"},{"volume-title":"GCC Research Opportunities Workshop (GROW).","year":"2010","author":"Trifunovic Konrad","key":"e_1_2_1_30_1"},{"volume-title":"GCC Research Opportunities Workshop (GROW).","year":"2011","author":"Trifunovic Konrad","key":"e_1_2_1_31_1"},{"volume-title":"Padua","year":"1994","author":"Tu Peng","key":"e_1_2_1_32_1"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854322"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1183401.1183448"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/1299042.1299056"},{"volume-title":"International Workshop on Polyhedral Compilation Techniques, IMPACT.","year":"2012","author":"Vasilache Nicolas","key":"e_1_2_1_36_1"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888390.1888455"},{"key":"e_1_2_1_38_1","unstructured":"Sven Verdoolaege and Albert Cohen. 2016. Live range reordering. In 6 Workshop on Polyhedral Compilation Techniques (IMPACT Associated with HiPEAC). Prag Czech Republic.  Sven Verdoolaege and Albert Cohen. 2016. Live range reordering. In 6 Workshop on Polyhedral Compilation Techniques (IMPACT Associated with HiPEAC). Prag Czech Republic."}],"container-title":["ACM Transactions on Architecture and Code Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2963101","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2963101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:54:04Z","timestamp":1750222444000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2963101"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8,17]]},"references-count":37,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2016,9,17]]}},"alternative-id":["10.1145\/2963101"],"URL":"https:\/\/doi.org\/10.1145\/2963101","relation":{},"ISSN":["1544-3566","1544-3973"],"issn-type":[{"type":"print","value":"1544-3566"},{"type":"electronic","value":"1544-3973"}],"subject":[],"published":{"date-parts":[[2016,8,17]]},"assertion":[{"value":"2016-03-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2016-06-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2016-08-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}