{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T07:06:34Z","timestamp":1761807994521,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,3,17]],"date-time":"2016-03-17T00:00:00Z","timestamp":1458172800000},"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":[],"published-print":{"date-parts":[[2016,3,17]]},"DOI":"10.1145\/2892208.2892210","type":"proceedings-article","created":{"date-parts":[[2016,3,14]],"date-time":"2016-03-14T13:11:18Z","timestamp":1457961078000},"page":"240-250","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["Automatic data layout generation and kernel mapping for CPU+GPU architectures"],"prefix":"10.1145","author":[{"given":"Deepak","family":"Majeti","sequence":"first","affiliation":[{"name":"Rice University, USA"}]},{"given":"Kuldeep S.","family":"Meel","sequence":"additional","affiliation":[{"name":"Rice University, USA"}]},{"given":"Rajkishore","family":"Barik","sequence":"additional","affiliation":[{"name":"Intel, USA"}]},{"given":"Vivek","family":"Sarkar","sequence":"additional","affiliation":[{"name":"Rice University, USA"}]}],"member":"320","published-online":{"date-parts":[[2016,3,17]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"\u201cC++ Accelerated Massive Parallelism \u201d http:\/\/msdn.microsoft.com\/ en-us\/library\/vstudio\/hh265137.aspx."},{"volume-title":"Habanero-C","key":"e_1_3_2_1_2_1","unstructured":"\u201cHabanero-C,\u201d https:\/\/wiki.rice.edu\/confluence\/display\/ HABANERO\/Habanero-C."},{"key":"e_1_3_2_1_3_1","unstructured":"\u201cHalliburton Services \u201d http:\/\/www.halliburton.com\/en-US\/."},{"key":"e_1_3_2_1_4_1","unstructured":"\u201cPolyBench\/GPU \u201d http:\/\/www.cse.ohio-state.edu\/ \u223c pouchet\/ software\/polybench\/GPU\/."},{"volume-title":"The CUDA Specification","year":"2015","key":"e_1_3_2_1_5_1","unstructured":"\u201cThe CUDA Specification,\u201d 2015, www.nvidia.com."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/155090.155101"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1869459.1869469"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2544137.2544165"},{"key":"e_1_3_2_1_9_1","volume-title":"CDSC Research Applications","author":"Center for Domain Specific Computing","year":"2009","unstructured":"Center for Domain Specific Computing, \u201cCDSC Research Applications,\u201d 2009, http:\/\/www.cdsc.ucla.edu\/research\/."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063401"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2004.1255787"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/645677.663795"},{"key":"e_1_3_2_1_14_1","unstructured":"Springer Berlin Heidelberg 2000 pp. 149\u2013163."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"e_1_3_2_1_16_1","first-page":"11","volume-title":"In Proceedings of Innovative Parallel Computing, ser. InPar\u201912","author":"Jui S.","unstructured":"S. I-Jui, G. Liu, and W.-M. Hwu, \u201cDL: A data layout transformation system for heterogeneous computing,\u201d in In Proceedings of Innovative Parallel Computing, ser. InPar\u201912, May, pp. 1\u201311."},{"key":"e_1_3_2_1_17_1","volume-title":"The Intel Threading Building Blocks","author":"Intel Corporation","year":"2006","unstructured":"Intel Corporation, \u201cThe Intel Threading Building Blocks,\u201d 2006, https: \/\/www.threadingbuildingblocks.org\/\/."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/224170.224495"},{"volume-title":"OpenCL: The open standard for parallel programming of heterogeneous systems","year":"2010","key":"e_1_3_2_1_20_1","unstructured":"Khronos, \u201cOpenCL: The open standard for parallel programming of heterogeneous systems,\u201d 2010, http:\/\/www.khronos.org\/opencl\/."},{"volume-title":"The OpenACC: Application Programming Interface","year":"2011","key":"e_1_3_2_1_21_1","unstructured":"Khronos, \u201cThe OpenACC: Application Programming Interface,\u201d 2011, www.openacc-standard.org\/."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/143103.143136"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628102"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669121"},{"key":"e_1_3_2_1_26_1","volume-title":"The International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms, ser. HeteroPar \u201913","author":"Majeti D.","year":"2013","unstructured":"D. Majeti, R. Barik, J. Zhao, V. Sarkar, and M. Grossman, \u201cCompiler Driven Data Layout Transformation for Heterogeneous Platforms,\u201d in The International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms, ser. HeteroPar \u201913. Aachen, Germany: LNCS, 2013."},{"key":"e_1_3_2_1_27_1","first-page":"4986","article-title":"Performance Impact of Data Layout on the GPUaccelerated IDW Interpolation","volume":"1402","author":"Mei G.","year":"2014","unstructured":"G. Mei and H. Tian, \u201cPerformance Impact of Data Layout on the GPUaccelerated IDW Interpolation,\u201d CoRR, vol. abs\/1402.4986, 2014.","journal-title":"CoRR"},{"key":"e_1_3_2_1_28_1","volume-title":"NVIDIA Corportation","author":"NVIDIA","year":"2014","unstructured":"NVIDIA, \u201cCUDA Toolkit Documentation v6.5,\u201d in NVIDIA Corportation, 2014. {Online}. Available: http:\/\/docs.nvidia.com\/cuda\/"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6494993"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626400000214"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2007.36"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/647042.713813"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.413.0233"},{"key":"e_1_3_2_1_34_1","volume-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","author":"Stratton J. A.","year":"2012","unstructured":"J. A. Stratton, C. Rodrigues, I.-J. Sung, N. Obeid, L.-W. Chang, N. Anssari, G. D. Liu, and W.-M. W. Hwu, \u201cParboil: A revised benchmark suite for scientific and commercial throughput computing,\u201d Center for Reliable and High-Performance Computing, 2012."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854336"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555266"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01205185"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442523"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2011.20"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2095050.2095103"}],"event":{"name":"CGO '16: 14th Annual IEEE\/ACM International Symposium on Code Generation and Optimization","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing","IEEE-CS Computer Society"],"location":"Barcelona Spain","acronym":"CGO '16"},"container-title":["Proceedings of the 25th International Conference on Compiler Construction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2892208.2892210","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2892208.2892210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:53:53Z","timestamp":1750222433000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2892208.2892210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3,17]]},"references-count":38,"alternative-id":["10.1145\/2892208.2892210","10.1145\/2892208"],"URL":"https:\/\/doi.org\/10.1145\/2892208.2892210","relation":{},"subject":[],"published":{"date-parts":[[2016,3,17]]},"assertion":[{"value":"2016-03-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}