{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:14:09Z","timestamp":1750306449123,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":19,"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\/2832087.2832089","type":"proceedings-article","created":{"date-parts":[[2015,11,11]],"date-time":"2015-11-11T13:07:06Z","timestamp":1447247226000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Performance analysis of OpenMP on a GPU using a CORAL proxy application"],"prefix":"10.1145","author":[{"given":"Gheorghe-Teodor","family":"Bercea","sequence":"first","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY and Imperial College London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlo","family":"Bertolli","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel F.","family":"Antao","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arpith C.","family":"Jacob","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandre E.","family":"Eichenberger","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Chen","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zehra","family":"Sura","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyojin","family":"Sung","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Rokos","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Appelhans","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"O'Brien","sequence":"additional","affiliation":[{"name":"IBM T.J. Watson Research Center, Yorktown Heights, NY"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2015,11,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2833157.2833161"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/LLVM-HPC.2014.10"},{"key":"e_1_3_2_1_3_1","unstructured":"Github repository for extended Clang implementation supporting OpenMP 4.0. https:\/\/github.com\/clang-omp\/clang_trunk.  Github repository for extended Clang implementation supporting OpenMP 4.0. https:\/\/github.com\/clang-omp\/clang_trunk."},{"key":"e_1_3_2_1_4_1","unstructured":"CORAL award announcement. http:\/\/energy.gov\/articles\/department-energy-awards-425-million-next-generation-supercomputing-technologies.  CORAL award announcement. http:\/\/energy.gov\/articles\/department-energy-awards-425-million-next-generation-supercomputing-technologies."},{"key":"e_1_3_2_1_5_1","unstructured":"CUDA toolkit webpage. http:\/\/docs.nvidia.com\/cuda\/index.html.  CUDA toolkit webpage. http:\/\/docs.nvidia.com\/cuda\/index.html."},{"key":"e_1_3_2_1_6_1","unstructured":"A proposal for OpenMP offloading on GPUs in gcc. https:\/\/gcc.gnu.org\/ml\/gcc\/2015-03\/msg00331.html.  A proposal for OpenMP offloading on GPUs in gcc. https:\/\/gcc.gnu.org\/ml\/gcc\/2015-03\/msg00331.html."},{"key":"e_1_3_2_1_7_1","volume-title":"LLNL","author":"Karlin I.","year":"2012","unstructured":"I. Karlin . LULESH Programming Model and Performance Ports Overview. Technical report , LLNL , 2012 . https:\/\/codesign.llnl.gov\/pdfs\/lulesh_Ports.pdf. I. Karlin. LULESH Programming Model and Performance Ports Overview. Technical report, LLNL, 2012. https:\/\/codesign.llnl.gov\/pdfs\/lulesh_Ports.pdf."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.115"},{"key":"e_1_3_2_1_9_1","unstructured":"The LLVM Compiler Infrastructure webpage. http:\/\/llvm.org\/.  The LLVM Compiler Infrastructure webpage. http:\/\/llvm.org\/."},{"key":"e_1_3_2_1_10_1","unstructured":"LLVM Backend component for NVPTX archietecture (Nvidia GPUs). http:\/\/llvm.org\/docs\/NVPTXUsage.html.  LLVM Backend component for NVPTX archietecture (Nvidia GPUs). http:\/\/llvm.org\/docs\/NVPTXUsage.html."},{"key":"e_1_3_2_1_11_1","unstructured":"LULESH webpage. https:\/\/codesign.llnl.gov\/lulesh.php.  LULESH webpage. https:\/\/codesign.llnl.gov\/lulesh.php."},{"key":"e_1_3_2_1_13_1","volume-title":"July","author":"Application Program Interface MP","year":"2013","unstructured":"Open MP Application Program Interface , version 4.0 edition , July 2013 . http:\/\/www.openmp.org\/mpdocuments\/OpenMP4.0.0.pdf. OpenMP Application Program Interface, version 4.0 edition, July 2013. http:\/\/www.openmp.org\/mpdocuments\/OpenMP4.0.0.pdf."},{"key":"e_1_3_2_1_14_1","unstructured":"Github repository for libomptarget offloading and GPU OpenMP runtime. https:\/\/github.com\/clang-omp\/libomptarget.  Github repository for libomptarget offloading and GPU OpenMP runtime. https:\/\/github.com\/clang-omp\/libomptarget."},{"key":"e_1_3_2_1_15_1","unstructured":"OpenACC webpage. http:\/\/openacc.org.  OpenACC webpage. http:\/\/openacc.org."},{"key":"e_1_3_2_1_16_1","unstructured":"OpenCL standard webpage. https:\/\/www.khronos.org\/opencl.  OpenCL standard webpage. https:\/\/www.khronos.org\/opencl."},{"key":"e_1_3_2_1_17_1","unstructured":"OpenMP standard webpage. http:\/\/openmp.org\/.  OpenMP standard webpage. http:\/\/openmp.org\/."},{"key":"e_1_3_2_1_18_1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/978-3-319-11454-5_16","volume-title":"L. DeRose","author":"Ozen G.","year":"2014","unstructured":"G. Ozen , E. Ayguade , and J. Labarta . On the roles of the programmer, the compiler and the runtime system when programming accelerators in OpenMP . In L. DeRose , B. de Supinski, S. Olivier, B. Chapman, and M. M\u00c3ijller, editors, Using and Improving OpenMP for Devices, Tasks , and More, volume 8766 of Lecture Notes in Computer Science , pages 215 -- 229 . Springer International Publishing , 2014 . G. Ozen, E. Ayguade, and J. Labarta. On the roles of the programmer, the compiler and the runtime system when programming accelerators in OpenMP. In L. DeRose, B. de Supinski, S. Olivier, B. Chapman, and M. M\u00c3ijller, editors, Using and Improving OpenMP for Devices, Tasks, and More, volume 8766 of Lecture Notes in Computer Science, pages 215--229. Springer International Publishing, 2014."},{"key":"e_1_3_2_1_19_1","unstructured":"CUDA-enable STL Thrust Library March 2015. http:\/\/docs.nvidia.com\/cuda\/thrust. CUDA-enable STL Thrust Library March 2015. http:\/\/docs.nvidia.com\/cuda\/thrust."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555254"}],"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 6th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2832087.2832089","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2832087.2832089","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\/2832087.2832089"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,11,15]]},"references-count":19,"alternative-id":["10.1145\/2832087.2832089","10.1145\/2832087"],"URL":"https:\/\/doi.org\/10.1145\/2832087.2832089","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"}}]}}