{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:14:08Z","timestamp":1750306448483,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,11,15]],"date-time":"2015-11-15T00:00:00Z","timestamp":1447545600000},"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":[[2015,11,15]]},"DOI":"10.1145\/2832105.2832112","type":"proceedings-article","created":{"date-parts":[[2015,11,9]],"date-time":"2015-11-09T16:29:04Z","timestamp":1447086544000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Experiences in extending parallware to support OpenACC"],"prefix":"10.1145","author":[{"given":"Jacobo","family":"Lobeiras","sequence":"first","affiliation":[{"name":"Appentra Solutions, A Coru\u00f1a, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel","family":"Arenaz","sequence":"additional","affiliation":[{"name":"Appentra Solutions & University of A Coru\u00f1a, A Coru\u00f1a, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oscar","family":"Hern\u00e1ndez","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Tennessee"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2015,11,15]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"OpenCL: The Open Standard for Parallel Programming of Heterogeneous Systems. http:\/\/www.khronos.org\/opencl 2015.  OpenCL: The Open Standard for Parallel Programming of Heterogeneous Systems. http:\/\/www.khronos.org\/opencl 2015."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2013.04.003"},{"key":"e_1_3_2_1_3_1","unstructured":"Appentra. Parallware: The OpenMP-enabling Source-to-Source Compiler. http:\/\/www.appentra.com\/products\/parallware May 2015.  Appentra. Parallware: The OpenMP-enabling Source-to-Source Compiler. http:\/\/www.appentra.com\/products\/parallware May 2015."},{"key":"e_1_3_2_1_4_1","volume-title":"2015 Rice Oil and Gas HPC Workshop","author":"Arenaz M.","year":"2015","unstructured":"M. Arenaz , J. Dom\u00ednguez , and A. Crespo . Democratization of HPC in the Oil & Gas Industry through Automatic Parallelization with Parallware . 2015 Rice Oil and Gas HPC Workshop , Mar. 2015 . M. Arenaz, J. Dom\u00ednguez, and A. Crespo. Democratization of HPC in the Oil & Gas Industry through Automatic Parallelization with Parallware. 2015 Rice Oil and Gas HPC Workshop, Mar. 2015."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/782814.782842"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1391956.1391959"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/125826.125925"},{"key":"e_1_3_2_1_8_1","unstructured":"Barcelona Supercomputing Center (BSC). The OmpSs Programming Model. http:\/\/pm.bsc.es\/ompss 2015.  Barcelona Supercomputing Center (BSC). The OmpSs Programming Model. http:\/\/pm.bsc.es\/ompss 2015."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.546612"},{"key":"e_1_3_2_1_10_1","volume-title":"Scientific and Engineering Computation. The MIT Press","author":"Chapman B.","year":"2007","unstructured":"B. Chapman , G. Jost , and R. Pas . Using OpenMP: Portable Shared Memory Parallel Programming . Scientific and Engineering Computation. The MIT Press , 2007 . B. Chapman, G. Jost, and R. Pas. Using OpenMP: Portable Shared Memory Parallel Programming. Scientific and Engineering Computation. The MIT Press, 2007."},{"key":"e_1_3_2_1_11_1","first-page":"1","volume-title":"Proceedings of the 1996 Conference of the Centre for Advanced Studies on Collaborative Research, CASCON '96","author":"Chow J.-H.","year":"1996","unstructured":"J.-H. Chow , L. E. Lyon , and V. Sarkar . Automatic Parallelization for Symmetric Shared-memory Multiprocessors . In Proceedings of the 1996 Conference of the Centre for Advanced Studies on Collaborative Research, CASCON '96 , pages 1 -- 14 . IBM Press , 1996 . J.-H. Chow, L. E. Lyon, and V. Sarkar. Automatic Parallelization for Symmetric Shared-memory Multiprocessors. In Proceedings of the 1996 Conference of the Centre for Advanced Studies on Collaborative Research, CASCON '96, pages 1--14. IBM Press, 1996."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.385"},{"key":"e_1_3_2_1_14_1","first-page":"225","volume-title":"Proceeding of the 2012 Forum on Specification and Design Languages","author":"Gerndt M.","year":"2012","unstructured":"M. Gerndt , A. Hollmann , M. Meyer , M. Schreiber , and J. Weidendorfer . Invasive Computing with iOMP . In Proceeding of the 2012 Forum on Specification and Design Languages , Vienna, Austria , September 18-20, 2012 , pages 225 -- 231 , 2012. M. Gerndt, A. Hollmann, M. Meyer, M. Schreiber, and J. Weidendorfer. Invasive Computing with iOMP. In Proceeding of the 2012 Forum on Specification and Design Languages, Vienna, Austria, September 18-20, 2012, pages 225--231, 2012."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 9th European Conference on Antenas and Propagation, EuCap 2015","author":"G\u00f3mez-Sousa H.","year":"2015","unstructured":"H. G\u00f3mez-Sousa , M. Arenaz , O. Rubi\u00f1os-L\u00f3pez , and J. Mart\u00ednez-Lorenzo . Novel Source-to-Source Compiler Approach for the Automatic Parallelization of Codes based on the Method of Moments . In Proceedings of the 9th European Conference on Antenas and Propagation, EuCap 2015 , Apr. 2015 . H. G\u00f3mez-Sousa, M. Arenaz, O. Rubi\u00f1os-L\u00f3pez, and J. Mart\u00ednez-Lorenzo. Novel Source-to-Source Compiler Approach for the Automatic Parallelization of Codes based on the Method of Moments. In Proceedings of the 9th European Conference on Antenas and Propagation, EuCap 2015, Apr. 2015."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"key":"e_1_3_2_1_18_1","first-page":"v11","article-title":"Intel Math Kernel Library","author":"Intel","year":"2014","unstructured":"Intel . Intel Math Kernel Library , Reference Manual , 2014 . v11 .2. Intel. Intel Math Kernel Library, Reference Manual, 2014. v11.2.","journal-title":"Reference Manual"},{"volume-title":"Aug.","year":"2015","key":"e_1_3_2_1_19_1","unstructured":"Intel. Intel Architecture Instruction Set Extensions Programming Reference , Aug. 2015 . Intel. Intel Architecture Instruction Set Extensions Programming Reference, Aug. 2015."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e89-d.2.399"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/UCC.2014.77"},{"key":"e_1_3_2_1_22_1","volume-title":"The OpenMP Implementation of NAS Parallel Benchmarks and its Performance. Technical report","author":"Jin H.","year":"1999","unstructured":"H. Jin , H. Jin , M. Frumkin , M. Frumkin , J. Yan , and J. Yan . The OpenMP Implementation of NAS Parallel Benchmarks and its Performance. Technical report , NASA Ames Research Center (NAS System Division) , 1999 . H. Jin, H. Jin, M. Frumkin, M. Frumkin, J. Yan, and J. Yan. The OpenMP Implementation of NAS Parallel Benchmarks and its Performance. Technical report, NASA Ames Research Center (NAS System Division), 1999."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31832-3_7"},{"key":"e_1_3_2_1_24_1","series-title":"Lecture Notes in Computer Science (LNCS)","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1007\/978-3-319-17248-4_3","volume-title":"High Performance Computing Systems. Performance Modeling, Benchmarking, and Simulation","author":"Juckeland G.","year":"2015","unstructured":"G. Juckeland , W. Brantley , S. Chandrasekaran , B. Chapman , S. Che , M. Colgrove , H. Feng , A. Grund , R. Henschel , W.-M. W.- Hwu , H. Li , M. S. Muller , W. E. Nagel , M. Perminov , P. Shelepugin , K. Skadron , J. Stratton , A. Titov , K. Wang , M. van Waveren , B. Whitney , S. Wienke , R. Xu , and K. Kumaran . SPEC ACCEL: A Standard Application Suite for Measuring Hardware Accelerator Performance . In S. A. Jarvis, S. A. Wright, and S. D. Hammond, editors, High Performance Computing Systems. Performance Modeling, Benchmarking, and Simulation , volume 8966 of Lecture Notes in Computer Science (LNCS) , pages 46 -- 67 . Springer International Publishing , 2015 . G. Juckeland, W. Brantley, S. Chandrasekaran, B. Chapman, S. Che, M. Colgrove, H. Feng, A. Grund, R. Henschel, W.-M. W.-Hwu, H. Li, M. S. Muller, W. E. Nagel, M. Perminov, P. Shelepugin, K. Skadron, J. Stratton, A. Titov, K. Wang, M. van Waveren, B. Whitney, S. Wienke, R. Xu, and K. Kumaran. SPEC ACCEL: A Standard Application Suite for Measuring Hardware Accelerator Performance. In S. A. Jarvis, S. A. Wright, and S. D. Hammond, editors, High Performance Computing Systems. Performance Modeling, Benchmarking, and Simulation, volume 8966 of Lecture Notes in Computer Science (LNCS), pages 46--67. Springer International Publishing, 2015."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.877759"},{"key":"e_1_3_2_1_26_1","volume-title":"GPU Technology Conference (GTC)","author":"Larking J.","year":"2015","unstructured":"J. Larking . Advanced OpenACC Programming . http:\/\/on-demand.gputechconf.com\/gtc\/2015\/presentation\/S5195-Jeff-Larkin.pdf , GPU Technology Conference (GTC) , Mar. 2015 . J. Larking. Advanced OpenACC Programming. http:\/\/on-demand.gputechconf.com\/gtc\/2015\/presentation\/S5195-Jeff-Larkin.pdf, GPU Technology Conference (GTC), Mar. 2015."},{"key":"e_1_3_2_1_27_1","volume-title":"GPU Technology Conference (GTC)","author":"Larking J.","year":"2015","unstructured":"J. Larking . Comparing OpenACC and OpenMP Performance and Programmability. http:\/\/on-demand.gputechconf.com\/gtc\/2015\/presentation\/S5196-Jeff-Larkin.pdf , GPU Technology Conference (GTC) , Mar. 2015 . J. Larking. Comparing OpenACC and OpenMP Performance and Programmability. http:\/\/on-demand.gputechconf.com\/gtc\/2015\/presentation\/S5196-Jeff-Larkin.pdf, GPU Technology Conference (GTC), Mar. 2015."},{"key":"e_1_3_2_1_28_1","volume-title":"GPU Technology Conference (GTC)","author":"Larking J.","year":"2015","unstructured":"J. Larking . Comparing OpenACC and OpenMP Performance and Programmability. http:\/\/on-demand.gputechconf.com\/gtc\/2015\/presentation\/S5196-Jeff-Larkin.pdf , GPU Technology Conference (GTC) , Mar. 2015 . J. Larking. Comparing OpenACC and OpenMP Performance and Programmability. http:\/\/on-demand.gputechconf.com\/gtc\/2015\/presentation\/S5196-Jeff-Larkin.pdf, GPU Technology Conference (GTC), Mar. 2015."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/301104.301108"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the OpenMPCon Developers Conference","author":"Lobeiras J.","year":"2015","unstructured":"J. Lobeiras and M. Arenaz . A Success Case using Parallware: The NAS Parallel Benchmark EP . In Proceedings of the OpenMPCon Developers Conference , 2015 . J. Lobeiras and M. Arenaz. A Success Case using Parallware: The NAS Parallel Benchmark EP. In Proceedings of the OpenMPCon Developers Conference, 2015."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/850943.853051"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.706049"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/258492.258520"},{"key":"e_1_3_2_1_34_1","volume-title":"CUDA C Best Practices Guide (SDK Documentation)","author":"NVIDIA.","year":"2015","unstructured":"NVIDIA. CUDA C Best Practices Guide (SDK Documentation) , 2015 . v7.0. NVIDIA. CUDA C Best Practices Guide (SDK Documentation), 2015. v7.0."},{"key":"e_1_3_2_1_35_1","volume-title":"CUDA C Programming Guide (SDK Documentation)","author":"NVIDIA.","year":"2015","unstructured":"NVIDIA. CUDA C Programming Guide (SDK Documentation) , 2015 . v7.0. NVIDIA. CUDA C Programming Guide (SDK Documentation), 2015. v7.0."},{"key":"e_1_3_2_1_36_1","unstructured":"NVIDIA. NVIDIA OpenACC Toolkit. http:\/\/developer.nvidia.com\/openacc July 2015.  NVIDIA. NVIDIA OpenACC Toolkit. http:\/\/developer.nvidia.com\/openacc July 2015."},{"key":"e_1_3_2_1_37_1","unstructured":"OpenACC Architecture Review Board. The OpenACC API Specification for Parallel Programming. http:\/\/www.openacc.org May 2015.  OpenACC Architecture Review Board. The OpenACC API Specification for Parallel Programming. http:\/\/www.openacc.org May 2015."},{"key":"e_1_3_2_1_38_1","unstructured":"OpenMP Architecture Review Board. OpenMP Application Program Interface Version 4.0. http:\/\/www.openmp.org July 2013.  OpenMP Architecture Review Board. OpenMP Application Program Interface Version 4.0. http:\/\/www.openmp.org July 2013."},{"key":"e_1_3_2_1_39_1","volume-title":"Texas A&M","author":"Rus S.","year":"2006","unstructured":"S. Rus and L. Rauchwerger . Compiler technology for migrating sequential code to multi-threaded Architectures. Technical report , Texas A&M University , 2006 . S. Rus and L. Rauchwerger. Compiler technology for migrating sequential code to multi-threaded Architectures. Technical report, Texas A&M University, 2006."},{"key":"e_1_3_2_1_40_1","volume-title":"Software Productivity Research in High Performance Computing. CTWatch Quarterly, 2(4A)","author":"Squires S.","year":"2006","unstructured":"S. Squires , M. V. D. Vanter , and L. Votta . Software Productivity Research in High Performance Computing. CTWatch Quarterly, 2(4A) , 2006 . S. Squires, M. V. D. Vanter, and L. Votta. Software Productivity Research in High Performance Computing. CTWatch Quarterly, 2(4A), 2006."},{"key":"e_1_3_2_1_41_1","volume-title":"The SPEC ACCEL V1.0 benchmark. https:\/\/www.spec.org\/accel","author":"Standard Performance Evaluation Corporation (SPEC).","year":"2015","unstructured":"Standard Performance Evaluation Corporation (SPEC). The SPEC ACCEL V1.0 benchmark. https:\/\/www.spec.org\/accel , 2015 . Standard Performance Evaluation Corporation (SPEC). The SPEC ACCEL V1.0 benchmark. https:\/\/www.spec.org\/accel, 2015."},{"key":"e_1_3_2_1_42_1","first-page":"274","volume-title":"Chen. Combining Loop Transformations Considering Caches and Scheduling. In Proceedings of the 29th Annual ACM\/IEEE International Symposium on Microarchitecture, MICRO 29","author":"Wolf M. E.","year":"1996","unstructured":"M. E. Wolf , D. E. Maydan , and D.- K. Chen. Combining Loop Transformations Considering Caches and Scheduling. In Proceedings of the 29th Annual ACM\/IEEE International Symposium on Microarchitecture, MICRO 29 , pages 274 -- 286 , Washington, DC, USA , 1996 . IEEE Computer Society. M. E. Wolf, D. E. Maydan, and D.-K. Chen. Combining Loop Transformations Considering Caches and Scheduling. In Proceedings of the 29th Annual ACM\/IEEE International Symposium on Microarchitecture, MICRO 29, pages 274--286, Washington, DC, USA, 1996. IEEE Computer Society."},{"key":"e_1_3_2_1_43_1","volume-title":"HPC Wire","author":"Wolfe M.","year":"2014","unstructured":"M. Wolfe . Compilers and More : MPI+X . HPC Wire , July 2014 . M. Wolfe. Compilers and More: MPI+X. HPC Wire, July 2014."},{"key":"e_1_3_2_1_44_1","unstructured":"M. Wolfe. OpenACC and CUDA Unified Memory. http:\/\/www.pgroup.com\/lit\/articles\/insider\/v6n2a4.htm Mar. 2015.  M. Wolfe. OpenACC and CUDA Unified Memory. http:\/\/www.pgroup.com\/lit\/articles\/insider\/v6n2a4.htm Mar. 2015."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/335231.335238"},{"key":"e_1_3_2_1_46_1","volume-title":"Supercompilers for Parallel and Vector Computers","author":"Zima H.","year":"1991","unstructured":"H. Zima and B. Chapman . Supercompilers for Parallel and Vector Computers . ACM Press , New York, NY, USA , 1991 . H. Zima and B. Chapman. Supercompilers for Parallel and Vector Computers. ACM Press, New York, NY, USA, 1991."}],"event":{"name":"SC15: The International Conference for High Performance Computing, Networking, Storage and Analysis","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS\\DATC IEEE Computer Society"],"location":"Austin Texas","acronym":"SC15"},"container-title":["Proceedings of the Second Workshop on Accelerator Programming using Directives"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2832105.2832112","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2832105.2832112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:43:04Z","timestamp":1750225384000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2832105.2832112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,11,15]]},"references-count":45,"alternative-id":["10.1145\/2832105.2832112","10.1145\/2832105"],"URL":"https:\/\/doi.org\/10.1145\/2832105.2832112","relation":{},"subject":[],"published":{"date-parts":[[2015,11,15]]},"assertion":[{"value":"2015-11-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}