{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T06:27:47Z","timestamp":1774592867488,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,6,1]],"date-time":"2016-06-01T00:00:00Z","timestamp":1464739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ARM Inc","award":["PollyLabs"],"award-info":[{"award-number":["PollyLabs"]}]},{"name":"Swissuniversities","award":["ComPASC"],"award-info":[{"award-number":["ComPASC"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1145\/2925426.2926286","type":"proceedings-article","created":{"date-parts":[[2016,6,10]],"date-time":"2016-06-10T13:04:07Z","timestamp":1465563847000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":36,"title":["Polly-ACC Transparent compilation to heterogeneous hardware"],"prefix":"10.1145","author":[{"given":"Tobias","family":"Grosser","sequence":"first","affiliation":[{"name":"Department of Computer Science, ETH Zurich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"Department of Computer Science, ETH Zurich"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2016,6]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Bolt C++ template library. http:\/\/developer.amd.com\/tools-and-sdks\/opencl-zone\/bolt-c-template-library\/. Accessed: 2016-01-21.  Bolt C++ template library. http:\/\/developer.amd.com\/tools-and-sdks\/opencl-zone\/bolt-c-template-library\/. Accessed: 2016-01-21."},{"key":"e_1_3_2_1_2_1","unstructured":"boostorg\/compute: A C++ GPU computing library for OpenCL. https:\/\/github.com\/boostorg\/compute. Accessed: 2016-01-21.  boostorg\/compute: A C++ GPU computing library for OpenCL. https:\/\/github.com\/boostorg\/compute. Accessed: 2016-01-21."},{"key":"e_1_3_2_1_3_1","unstructured":"Oak Ridge Leadership Computing Facility - Summit. https:\/\/www.olcf.ornl.gov\/summit\/. Accessed: 2015-11-16.  Oak Ridge Leadership Computing Facility - Summit. https:\/\/www.olcf.ornl.gov\/summit\/. Accessed: 2015-11-16."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/822085.823319"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/73560.73561"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Mehdi\n       \n      Amini Fabien\n       \n      Coelho Fran\u00c3\u011fois\n       \n      Irigoin and \n      \n      \n      Ronan\n       \n      Keryell\n    .\n      \n  \n   \n  Static compilation analysis for host-accelerator communication optimization. In Sanjay Rajopadhye and Michelle Mills Strout editors Languages and Compilers for Parallel Computing volume \n  7146\n   of \n  Lecture Notes in Computer Science pages \n  237\n  --\n  251\n  . \n  Springer Berlin Heidelberg 2013\n  .  Mehdi Amini Fabien Coelho Fran\u00c3\u011fois Irigoin and Ronan Keryell. Static compilation analysis for host-accelerator communication optimization. In Sanjay Rajopadhye and Michelle Mills Strout editors Languages and Compilers for Parallel Computing volume 7146 of Lecture Notes in Computer Science pages 237--251. Springer Berlin Heidelberg 2013.","DOI":"10.1007\/978-3-642-36036-7_16"},{"key":"e_1_3_2_1_7_1","volume-title":"IMPACT: Second Int. Workshop on Polyhedral Compilation Techniques HiPEAC","author":"Amini Mehdi","year":"2012"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Ping\n       \n      An Alin\n       \n      Jula Silvius\n       \n      Rus Steven\n       \n      Saunders Tim\n       \n      Smith Gabriel\n       \n      Tanase Nathan\n       \n      Thomas Nancy\n       \n      Amato and \n      \n      \n      Lawrence\n       \n      Rauchwerger\n    .\n      \n  \n   \n  STAPL: An adaptive generic parallel c++ library. In HenryG. Dietz editor Languages and Compilers for Parallel Computing volume \n  2624\n   of \n  Lecture Notes in Comp\n  . Sci. pages \n  193\n  --\n  208\n  . \n  Springer Berlin Heidelberg 2003\n  .   Ping An Alin Jula Silvius Rus Steven Saunders Tim Smith Gabriel Tanase Nathan Thomas Nancy Amato and Lawrence Rauchwerger. STAPL: An adaptive generic parallel c++ library. In HenryG. Dietz editor Languages and Compilers for Parallel Computing volume 2624 of Lecture Notes in Comp. Sci. pages 193--208. Springer Berlin Heidelberg 2003.","DOI":"10.1007\/3-540-35767-X_13"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.17"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 15th Workshop on Compilers for Parallel Computers (CPC'10)","author":"Baghdadi Soufiane","year":"2010"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11970-5_14"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2597809.2597818"},{"key":"e_1_3_2_1_13_1","first-page":"12014","article-title":"Productivity-oriented library for CUDA","volume":"1","author":"Bell Nathan","year":"2012","journal-title":"Astrophysics Source Code Library"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/2023025.2023037"},{"key":"e_1_3_2_1_15_1","first-page":"2015","article-title":"OpenMP Application Program Interface","author":"Architecture Review Board MP","year":"2013","journal-title":"Version 4.0. http:\/\/www.openmp.org\/mp-documents\/OpenMP4.0.0.pdf"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1379022.1375595"},{"key":"e_1_3_2_1_17_1","unstructured":"Sharan Chetlur Cliff Woolley Philippe Vandermersch Jonathan Cohen John Tran Bryan Catanzaro and Evan Shelhamer. cuDNN: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 2014.  Sharan Chetlur Cliff Woolley Philippe Vandermersch Jonathan Cohen John Tran Bryan Catanzaro and Evan Shelhamer. cuDNN: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 2014."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.70"},{"key":"e_1_3_2_1_19_1","unstructured":"Nvidia Corporation. CUBLAS LIBRARY - User Guide. http:\/\/docs.nvidia.com\/cuda\/pdf\/CUBLAS_Library.pdf September 2015. Accessed: 2016-01-21.  Nvidia Corporation. CUBLAS LIBRARY - User Guide. http:\/\/docs.nvidia.com\/cuda\/pdf\/CUBLAS_Library.pdf September 2015. Accessed: 2016-01-21."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/2755753.2757063"},{"key":"e_1_3_2_1_21_1","unstructured":"Caps Enterprise. HMPP Directives HMPP Workbench 3.0. https:\/\/www.olcf.ornl.gov\/wp-content\/uploads\/2012\/02\/HMPPWorkbench-3.0_HMPP_Directives_ReferenceManual.pdf. Accessed: 2015-11-16.  Caps Enterprise. HMPP Directives HMPP Workbench 3.0. https:\/\/www.olcf.ornl.gov\/wp-content\/uploads\/2012\/02\/HMPPWorkbench-3.0_HMPP_Directives_ReferenceManual.pdf. Accessed: 2015-11-16."},{"key":"e_1_3_2_1_22_1","volume-title":"Proc. of the BSDCan Conference","author":"Evans Jason","year":"2006"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/49418"},{"key":"e_1_3_2_1_24_1","unstructured":"Kate Gregory and Ade Miller. C++ AMP: accelerated massive parallelism with Microsoft Visual C++. 2014.  Kate Gregory and Ade Miller. C++ AMP: accelerated massive parallelism with Microsoft Visual C++. 2014."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626412500107"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751248"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2743016"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807627"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186736.1186737"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304619"},{"key":"e_1_3_2_1_31_1","unstructured":"A Kravets A Monakov and A Belevantsev. Graphite-opencl: Automatic parallelization of some loops in polyhedra representation. GCC Developers\u00e2\u0102Ź Summit GCC Developers\u00e2\u0102Ź Summit 2010.  A Kravets A Monakov and A Belevantsev. Graphite-opencl: Automatic parallelization of some loops in polyhedra representation. GCC Developers\u00e2\u0102Ź Summit GCC Developers\u00e2\u0102Ź Summit 2010."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/977395.977673"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.36"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600704"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735698"},{"key":"e_1_3_2_1_36_1","volume-title":"LLVM Developers Meeting","author":"Margiolas Christos","year":"2015"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2014.115"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2892208.2892217"},{"key":"e_1_3_2_1_39_1","unstructured":"NVIDIA. CUDA Programming Guide. http:\/\/docs.nvidia.com\/cuda\/pdf\/CUDA_C_Programming_Guide.pdf September 2015. Accessed: 2016-01-21.  NVIDIA. CUDA Programming Guide. http:\/\/docs.nvidia.com\/cuda\/pdf\/CUDA_C_Programming_Guide.pdf September 2015. Accessed: 2016-01-21."},{"key":"e_1_3_2_1_40_1","unstructured":"Louis-No\u00ebl Pouchet. Polybench C 3.2. http:\/\/www.cs.ucla.edu\/~pouchet\/software\/polybench\/. Accessed: 2015-11-16.  Louis-No\u00ebl Pouchet. Polybench C 3.2. http:\/\/www.cs.ucla.edu\/~pouchet\/software\/polybench\/. Accessed: 2015-11-16."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Gabe\n       \n      Rudy MalikMurtaza\n       \n      Khan Mary\n       \n      Hall Chun\n       \n      Chen and \n      \n      \n      Jacqueline\n       \n      Chame\n    .\n      \n  \n   \n  A programming language interface to describe transformations and code generation. In Keith Cooper John Mellor-Crummey and Vivek Sarkar editors Languages and Compilers for Parallel Computing volume \n  6548\n   of \n  Lecture Notes in Computer Science pages \n  136\n  --\n  150\n  . \n  Springer Berlin Heidelberg 2011\n  .   Gabe Rudy MalikMurtaza Khan Mary Hall Chun Chen and Jacqueline Chame. A programming language interface to describe transformations and code generation. In Keith Cooper John Mellor-Crummey and Vivek Sarkar editors Languages and Compilers for Parallel Computing volume 6548 of Lecture Notes in Computer Science pages 136--150. Springer Berlin Heidelberg 2011.","DOI":"10.1007\/978-3-642-19595-2_10"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.69"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/2220077.2220227"},{"key":"e_1_3_2_1_45_1","first-page":"6327","article-title":"An integer set library for the polyhedral model. In Mathematical Software (ICMS'10)","author":"Verdoolaege Sven","year":"2010","journal-title":"LNCS"},{"key":"e_1_3_2_1_47_1","unstructured":"Sven Verdoolaege. Presburger formulas and polyhedral compilation 2016.  Sven Verdoolaege. Presburger formulas and polyhedral compilation 2016."},{"key":"e_1_3_2_1_48_1","volume-title":"Second International Workshop on Polyhedral Compilation Techniques (IMPACT\u00e2\u0102Ź12)","author":"Verdoolaege Sven","year":"2012"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400713"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32820-6_85"}],"event":{"name":"ICS '16: 2016 International Conference on Supercomputing","location":"Istanbul Turkey","acronym":"ICS '16","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 2016 International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2925426.2926286","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2925426.2926286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T19:04:25Z","timestamp":1750273465000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2925426.2926286"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6]]},"references-count":49,"alternative-id":["10.1145\/2925426.2926286","10.1145\/2925426"],"URL":"https:\/\/doi.org\/10.1145\/2925426.2926286","relation":{},"subject":[],"published":{"date-parts":[[2016,6]]},"assertion":[{"value":"2016-06-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}