{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:23:35Z","timestamp":1750307015969,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2012,3,31]],"date-time":"2012-03-31T00:00:00Z","timestamp":1333152000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000143","name":"Division of Computing and Communication Foundations","doi-asserted-by":"publisher","award":["IIP-1032032CCF-0905459"],"award-info":[{"award-number":["IIP-1032032CCF-0905459"]}],"id":[{"id":"10.13039\/100000143","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000151","name":"Division of Industrial Innovation and Partnerships","doi-asserted-by":"publisher","award":["IIP-1032032CCF-0905459"],"award-info":[{"award-number":["IIP-1032032CCF-0905459"]}],"id":[{"id":"10.13039\/100000151","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2012,3,31]]},"DOI":"10.1145\/2259016.2259020","type":"proceedings-article","created":{"date-parts":[[2012,6,11]],"date-time":"2012-06-11T13:03:31Z","timestamp":1339419811000},"page":"23-32","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Dynamic compilation of data-parallel kernels for vector processors"],"prefix":"10.1145","author":[{"given":"Andrew","family":"Kerr","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory","family":"Diamos","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Yalamanchili","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2012,3,31]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Intel 64 and IA-32 Architectures Optimization Reference Manual. Number 248966-018 in Intel 64 and IA-32 Optimization Manaul","author":"Intel Corporation","year":"2009","unstructured":"Intel Corporation . Intel 64 and IA-32 Architectures Optimization Reference Manual. Number 248966-018 in Intel 64 and IA-32 Optimization Manaul . Intel Corporation , March 2009 . Intel Corporation. Intel 64 and IA-32 Architectures Optimization Reference Manual. Number 248966-018 in Intel 64 and IA-32 Optimization Manaul. Intel Corporation, March 2009."},{"key":"e_1_3_2_1_2_1","volume-title":"March","author":"Intel Corp.","year":"2008","unstructured":"Intel Corp. Intel AVX: New Frontiers in Performance Improvements and Energy Efficiency , March 2008 . Intel Corp. Intel AVX: New Frontiers in Performance Improvements and Energy Efficiency, March 2008."},{"key":"e_1_3_2_1_3_1","volume-title":"December","author":"KHRONOS OpenCL Working Group","year":"2008","unstructured":"KHRONOS OpenCL Working Group . The OpenCL Specification , December 2008 . KHRONOS OpenCL Working Group. The OpenCL Specification, December 2008."},{"key":"e_1_3_2_1_4_1","volume-title":"NVIDIA CUDA Compute Unified Device Architecture","author":"NVIDIA.","year":"2008","unstructured":"NVIDIA. NVIDIA CUDA Compute Unified Device Architecture . NVIDIA Corporation , Santa Clara , California, 2.1 edition, October 2008 . NVIDIA. NVIDIA CUDA Compute Unified Device Architecture. NVIDIA Corporation, Santa Clara, California, 2.1 edition, October 2008."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772954.1772971"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854302"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854301"},{"key":"e_1_3_2_1_8_1","volume-title":"First International Workshop on Characterizing Applications for Heterogeneous Exascale Systems","author":"Wu Haicheng","year":"2011","unstructured":"Haicheng Wu , G. Diamos , Si Li , and S. Yalamanchili . Characterization and transformation of unstructured control flow in gpu applications . In First International Workshop on Characterizing Applications for Heterogeneous Exascale Systems , June 2011 . Haicheng Wu, G. Diamos, Si Li, and S. Yalamanchili. Characterization and transformation of unstructured control flow in gpu applications. In First International Workshop on Characterizing Applications for Heterogeneous Exascale Systems, June 2011."},{"key":"e_1_3_2_1_9_1","volume-title":"NVIDIA Compute PTX: Parallel Thread Execution","author":"NVIDIA.","year":"2008","unstructured":"NVIDIA. NVIDIA Compute PTX: Parallel Thread Execution . NVIDIA Corporation , Santa Clara , California, 1.3 edition, October 2008 . NVIDIA. NVIDIA Compute PTX: Parallel Thread Execution. NVIDIA Corporation, Santa Clara, California, 1.3 edition, October 2008."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1399504.1360617"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.63"},{"key":"e_1_3_2_1_12_1","volume-title":"Universite de Perpignan","author":"Collange Sylvain","year":"2009","unstructured":"Sylvain Collange and David Defour et al. Dynamic detection of uniform and affine vectors in gpgpu computations. Technical report , Universite de Perpignan , University of California Davis , June 2009 . Sylvain Collange and David Defour et al. Dynamic detection of uniform and affine vectors in gpgpu computations. Technical report, Universite de Perpignan, University of California Davis, June 2009."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.62"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306801"},{"key":"e_1_3_2_1_15_1","volume-title":"June","author":"Diamos Gregory","year":"2009","unstructured":"Gregory Diamos , Andrew Kerr , and Sudhakar Yalamanchili . Gpuocelot: A binary translation framework for ptx ., June 2009 . http:\/\/code.google.com\/p\/gpuocelot\/. Gregory Diamos, Andrew Kerr, and Sudhakar Yalamanchili. Gpuocelot: A binary translation framework for ptx., June 2009. http:\/\/code.google.com\/p\/gpuocelot\/."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854318"},{"key":"e_1_3_2_1_17_1","volume-title":"The parboil benchmark suite","author":"IMPACT.","year":"2007","unstructured":"IMPACT. The parboil benchmark suite , 2007 . IMPACT. The parboil benchmark suite, 2007."},{"key":"e_1_3_2_1_18_1","volume-title":"Supercomputing'08","author":"Vasily Volkov","year":"2008","unstructured":"Volkov Vasily and Demmel James W. Benchmarking gpus to tune dense linear algebra . In Supercomputing'08 , Piscataway, NJ, USA , 2008 . Volkov Vasily and Demmel James W. Benchmarking gpus to tune dense linear algebra. In Supercomputing'08, Piscataway, NJ, USA, 2008."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/2190025.2190061"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/1299042.1299055"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.45"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1950365.1950408"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2007.346199"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.38"}],"event":{"name":"CGO '12: Annual IEEE\/ACM International Symposium on Code Generation and Optimization","sponsor":["IEEE CS uArch","SIGPLAN ACM Special Interest Group on Programming Languages","SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"],"location":"San Jose California","acronym":"CGO '12"},"container-title":["Proceedings of the Tenth International Symposium on Code Generation and Optimization"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2259016.2259020","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2259016.2259020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:49:07Z","timestamp":1750236547000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2259016.2259020"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,3,31]]},"references-count":24,"alternative-id":["10.1145\/2259016.2259020","10.1145\/2259016"],"URL":"https:\/\/doi.org\/10.1145\/2259016.2259020","relation":{},"subject":[],"published":{"date-parts":[[2012,3,31]]},"assertion":[{"value":"2012-03-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}