{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T04:59:00Z","timestamp":1769749140083,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,2,29]],"date-time":"2016-02-29T00:00:00Z","timestamp":1456704000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP110104628"],"award-info":[{"award-number":["DP110104628"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,2,29]]},"DOI":"10.1145\/2854038.2854054","type":"proceedings-article","created":{"date-parts":[[2016,3,1]],"date-time":"2016-03-01T15:33:04Z","timestamp":1456846384000},"page":"59-69","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["Exploiting mixed SIMD parallelism by reducing data reorganization overhead"],"prefix":"10.1145","author":[{"given":"Hao","family":"Zhou","sequence":"first","affiliation":[{"name":"UNSW, Australia"}]},{"given":"Jingling","family":"Xue","sequence":"additional","affiliation":[{"name":"UNSW, Australia"}]}],"member":"320","published-online":{"date-parts":[[2016,2,29]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/29873.29875"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.38"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442529"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/996841.996853"},{"key":"e_1_3_2_1_5_1","volume-title":"Intel R 64 and IA-32 Architectures Optimization Reference Manual. Number 248966-030","year":"2014","unstructured":"Intel. Intel R 64 and IA-32 Architectures Optimization Reference Manual. Number 248966-030 . September 2014 . Intel. Intel R 64 and IA-32 Architectures Optimization Reference Manual. Number 248966-030. September 2014."},{"key":"e_1_3_2_1_6_1","first-page":"150","volume-title":"CGO \u201911","author":"Karrenberg R.","unstructured":"R. Karrenberg and S. Hack . Whole-function vectorization . In CGO \u201911 , pages 141\u2013 150 . R. Karrenberg and S. Hack. Whole-function vectorization. In CGO \u201911, pages 141\u2013150."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145824"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462187"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/349299.349320"},{"key":"e_1_3_2_1_10_1","first-page":"29","volume-title":"PACT \u201902","author":"Larsen S.","unstructured":"S. Larsen , E. Witchel , and S. P. Amarasinghe . Increasing and detecting memory address congruence . In PACT \u201902 , pages 18\u2013 29 . S. Larsen, E. Witchel, and S. P. Amarasinghe. Increasing and detecting memory address congruence. In PACT \u201902, pages 18\u201329."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2254064.2254106"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.68"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1133981.1133997"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2150976.2151014"},{"key":"e_1_3_2_1_15_1","unstructured":"V. Porpodas and T. M. Jones. Throttling automatic vectorization: When less is more. In PACT\u201915.  V. Porpodas and T. M. Jones. Throttling automatic vectorization: When less is more. In PACT\u201915."},{"key":"e_1_3_2_1_16_1","first-page":"201","volume-title":"CGO\u201915","author":"Porpodas V.","unstructured":"V. Porpodas , A. Magni , and T. M. Jones . PSLP: Padded SLP automatic vectorization . In CGO\u201915 , pages 190\u2013 201 . V. Porpodas, A. Magni, and T. M. Jones. PSLP: Padded SLP automatic vectorization. In CGO\u201915, pages 190\u2013201."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1133981.1133996"},{"key":"e_1_3_2_1_18_1","first-page":"142","volume-title":"GCC Developers\u2019 Summit\u201907","author":"Rosen I.","unstructured":"I. Rosen , D. Nuzman , and A. Zaks . Loop-aware SLP in GCC . In GCC Developers\u2019 Summit\u201907 , pages 131\u2013 142 . I. Rosen, D. Nuzman, and A. Zaks. Loop-aware SLP in GCC. In GCC Developers\u2019 Summit\u201907, pages 131\u2013142."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/1299042.1299055"},{"key":"e_1_3_2_1_20_1","first-page":"55","volume-title":"PACT \u201902","author":"Shin J.","unstructured":"J. Shin , J. Chame , and M. W. Hall . Compiler-controlled caching in superword register files for multimedia extension architectures . In PACT \u201902 , pages 45\u2013 55 ,. J. Shin, J. Chame, and M. W. Hall. Compiler-controlled caching in superword register files for multimedia extension architectures. In PACT \u201902, pages 45\u201355,."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2005.33"},{"key":"e_1_3_2_1_22_1","first-page":"362","volume-title":"PACT \u201913","author":"Sujon M. H.","unstructured":"M. H. Sujon , R. C. Whaley , and Q. Yi . Vectorization past dependent branches through speculation . In PACT \u201913 , pages 353\u2013 362 . M. H. Sujon, R. C. Whaley, and Q. Yi. Vectorization past dependent branches through speculation. In PACT \u201913, pages 353\u2013362."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2009.18"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1088149.1088172"},{"key":"e_1_3_2_1_25_1","volume-title":"ACM","author":"Zima H.","year":"1991","unstructured":"H. Zima and B. Chapman . Supercompilers for Parallel and Vector Computers . ACM , 1991 . H. Zima and B. Chapman. Supercompilers for Parallel and Vector Computers. ACM, 1991."}],"event":{"name":"CGO '16: 14th Annual IEEE\/ACM International Symposium on Code Generation and Optimization","location":"Barcelona Spain","acronym":"CGO '16","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing","IEEE-CS Computer Society"]},"container-title":["Proceedings of the 2016 International Symposium on Code Generation and Optimization"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2854038.2854054","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2854038.2854054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T19:04:30Z","timestamp":1750273470000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2854038.2854054"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,2,29]]},"references-count":25,"alternative-id":["10.1145\/2854038.2854054","10.1145\/2854038"],"URL":"https:\/\/doi.org\/10.1145\/2854038.2854054","relation":{},"subject":[],"published":{"date-parts":[[2016,2,29]]},"assertion":[{"value":"2016-02-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}