{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:24:13Z","timestamp":1740097453876,"version":"3.37.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319460789"},{"type":"electronic","value":"9783319460796"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-46079-6_33","type":"book-chapter","created":{"date-parts":[[2016,10,5]],"date-time":"2016-10-05T16:01:40Z","timestamp":1475683300000},"page":"470-488","source":"Crossref","is-referenced-by-count":11,"title":["From Describing to Prescribing Parallelism: Translating the SPEC ACCEL OpenACC Suite to OpenMP Target Directives"],"prefix":"10.1007","author":[{"given":"Guido","family":"Juckeland","sequence":"first","affiliation":[]},{"given":"Oscar","family":"Hernandez","sequence":"additional","affiliation":[]},{"given":"Arpith C.","family":"Jacob","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Neilson","sequence":"additional","affiliation":[]},{"given":"Ver\u00f3nica G. Vergara","family":"Larrea","sequence":"additional","affiliation":[]},{"given":"Sandra","family":"Wienke","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Bobyr","sequence":"additional","affiliation":[]},{"given":"William C.","family":"Brantley","sequence":"additional","affiliation":[]},{"given":"Sunita","family":"Chandrasekaran","sequence":"additional","affiliation":[]},{"given":"Mathew","family":"Colgrove","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Grund","sequence":"additional","affiliation":[]},{"given":"Robert","family":"Henschel","sequence":"additional","affiliation":[]},{"given":"Wayne","family":"Joubert","sequence":"additional","affiliation":[]},{"given":"Matthias S.","family":"M\u00fcller","sequence":"additional","affiliation":[]},{"given":"Dave","family":"Raddatz","sequence":"additional","affiliation":[]},{"given":"Pavel","family":"Shelepugin","sequence":"additional","affiliation":[]},{"given":"Brian","family":"Whitney","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Kalyan","family":"Kumaran","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,10,6]]},"reference":[{"key":"33_CR1","unstructured":"Github repository for the extended Clang implementation supporting OpenMP 4.0 (2016). https:\/\/github.com\/clang-omp\/clang_trunk"},{"key":"33_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1007\/978-3-662-48096-0_51","volume-title":"Euro-Par 2015: Parallel Processing","author":"SN Agathos","year":"2015","unstructured":"Agathos, S.N., Papadogiannakis, A., Dimakopoulos, V.V.: Targeting the parallella. In: Tr\u00e4ff, J.L., Hunold, S., Versaci, F. (eds.) Euro-Par 2015. LNCS, vol. 9233, pp. 662\u2013674. Springer, Heidelberg (2015). doi: 10.1007\/978-3-662-48096-0_51"},{"key":"33_CR3","unstructured":"Bertolli, C., Antao, S.F., Bercea, G.T., Jacob, A.C., Eichenberger, A.E., Chen, T., Sura, Z., Sung, H., Rokos, G., Appelhans, D., O\u2019Brien, K.: Integrating GPU support for OpenMP offloading directives into clang. In: Proceedings of 2nd Workshop on the LLVM Compiler Infrastructure in HPC, LLVM 2015, NY, USA, pp. 5:1\u20135:11. ACM, New York (2015). http:\/\/doi.acm.org\/10.1145\/2833157.2833161"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Bertolli, C., Antao, S.F., Eichenberger, A.E., O\u2019Brien, K., Sura, Z., Jacob, A.C., Chen, T., Sallenave, O.: Coordinating GPU threads for OpenMP 4.0 in LLVM (2014)","DOI":"10.1109\/LLVM-HPC.2014.10"},{"key":"33_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1007\/978-3-319-14313-2_37","volume-title":"Euro-Par 2014: Parallel Processing Workshops","author":"E Calore","year":"2014","unstructured":"Calore, E., Schifano, S.F., Tripiccione, R.: On portability, performance and scalability of an MPI OpenCL lattice Boltzmann code. In: Lopes, L., et al. (eds.) Euro-Par 2014. LNCS, vol. 8806, pp. 438\u2013449. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-14313-2_37"},{"key":"33_CR6","unstructured":"Cray: Cray Compiling Environment Release: Overview and Installation Guide (Document: S-5212-84) (2015)"},{"key":"33_CR7","unstructured":"Foundation, F.S.: GCC 6 Release Series: Changes, New Features, and Fixes (2016). https:\/\/gcc.gnu.org\/gcc-6\/changes.html"},{"key":"33_CR8","unstructured":"GCC Wiki: Offloading Support in GCC. https:\/\/gcc.gnu.org\/wiki\/Offloading"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Herdman, J.A., Gaudin, W.P., Perks, O., Beckingsale, D.A., Mallinson, A.C., Jarvis, S.A.: Achieving portability and performance through OpenACC. In: Proceedings of 1st Workshop on Accelerator Programming Using Directives, WACCPD 2014, pp. 19\u201326. IEEE Press, Piscataway (2014). http:\/\/dx.doi.org\/10.1109\/WACCPD.2014.10","DOI":"10.1109\/WACCPD.2014.10"},{"key":"33_CR10","unstructured":"Intel Corporation: Intel $$\\textregistered $$ C++ Compiler 16.0 User and Reference Guide: OpenMP* Support (2015)"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Juckeland, G., Grund, A., Nagel, W.E.: Performance portable applications for hardware accelerators: lessons learned from SPEC ACCEL. In: 2015 IEEE International Parallel and Distributed Processing Symposium Workshop (IPDPSW), pp. 689\u2013698, May 2015","DOI":"10.1109\/IPDPSW.2015.26"},{"key":"33_CR12","series-title":"Lecture Notes in Computer Science","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":"G Juckeland","year":"2015","unstructured":"Juckeland, G., et al.: SPEC ACCEL: a standard application suite for measuring hardware accelerator performance. In: Jarvis, S.A., Wright, S.A., Hammond, S.D. (eds.) PMBS 2014. LNCS, vol. 8966, pp. 46\u201367. Springer, Heidelberg (2015). http:\/\/dx.doi.org\/10.1007\/978-3-319-17248-4_3"},{"key":"33_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/978-3-642-40698-0_7","volume-title":"OpenMP in the Era of Low Power Devices and Accelerators","author":"C Liao","year":"2013","unstructured":"Liao, C., Yan, Y., Supinski, B.R., Quinlan, D.J., Chapman, B.: Early experiences with the OpenMP accelerator model. In: Rendell, A.P., Chapman, B.M., M\u00fcller, M.S. (eds.) IWOMP 2013. LNCS, vol. 8122, pp. 84\u201398. Springer, Heidelberg (2013). http:\/\/dx.doi.org\/10.1007\/978-3-642-40698-0_7"},{"key":"33_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/978-3-319-24595-9_4","volume-title":"OpenMP: Heterogenous Execution and Data Movements","author":"PH Lin","year":"2015","unstructured":"Lin, P.H., Liao, C., Quinlan, D.J., Guzik, S.: Experiences of using the OpenMP accelerator model to port DOE stencil applications. In: Terboven, C., de Supinski, B.R., Reble, P., Chapman, B.M., M\u00fcller, M.S. (eds.) IWOMP 2015. LNCS, vol. 9342, pp. 45\u201359. Springer, Berlin (2015)"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Martineau, M., McIntosh-Smith, S., Boulton, M., Gaudin, W.: An evaluation of emerging many-core parallel programming models. In: Proceedings of 7th International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2016, NY, USA pp. 1\u201310 (2016)","DOI":"10.1145\/2883404.2883420"},{"key":"33_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1007\/978-3-319-11454-5_15","volume-title":"Using and Improving OpenMP for Devices, Tasks, and More","author":"G Mitra","year":"2014","unstructured":"Mitra, G., Stotzer, E., Jayaraj, A., Rendell, A.P.: Implementation and optimization of the OpenMP accelerator model for the TI Keystone II architecture. In: DeRose, L., Supinski, B.R., Olivier, S.L., Chapman, B.M., M\u00fcller, M.S. (eds.) IWOMP 2014. LNCS, vol. 8766, pp. 202\u2013214. Springer, Heidelberg (2014)"},{"key":"33_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1007\/978-3-642-30961-8_17","volume-title":"OpenMP in a Heterogeneous World","author":"MS M\u00fcller","year":"2012","unstructured":"M\u00fcller, M.S., et al.: SPEC OMP2012 \u2014 an application benchmark suite for parallel systems using OpenMP. In: Chapman, B.M., Massaioli, F., M\u00fcller, M.S., Rorro, M. (eds.) IWOMP 2012. LNCS, vol. 7312, pp. 223\u2013236. Springer, Heidelberg (2012). http:\/\/dx.doi.org\/10.1007\/978-3-642-30961-8_17"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"M\u00fcller, M.S., van Waveren, M., Lieberman, R., Whitney, B., Saito, H., Kumaran, K., Baron, J., Brantley, W.C., Parrott, C., Elken, T., Feng, H., Ponder, C.: SPEC MPI2007 - an application benchmark suite for parallel systems using MPI. Concurr. Comput.: Pract. Exper. 22(2), 191\u2013205 (2010). http:\/\/dx.doi.org\/10.1002\/cpe.v22:2","DOI":"10.1002\/cpe.v22:2"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Newburn, C.J., Dmitriev, S., Narayanaswamy, R., Wiegert, J., Murty, R., Chinchilla, F., Deodhar, R., McGuire, R.: Offload compiler runtime for the Intel Xeon Phi\u2122 coprocessor. In: 2013 IEEE 27th International Parallel and Distributed Processing Symposium Workshops and Ph.D. Forum (IPDPSW), pp. 1213\u20131225 (2013)","DOI":"10.1109\/IPDPSW.2013.251"},{"key":"33_CR20","unstructured":"OpenMP Architecture Review Board: OpenMP Application Program Interface. Version 4.0, July 2013. http:\/\/www.openmp.org\/mp-documents\/OpenMP4.0.0.pdf"},{"key":"33_CR21","unstructured":"OpenMP Architecture Review Board: OpenMP Application Program Interface. Version 4.5, November 2015. http:\/\/www.openmp.org\/mp-documents\/openmp-4.5.pdf"},{"key":"33_CR22","unstructured":"Oracle: Oracle $${\\textregistered }$$ Solaris Studio 12.4: OpenMP API User\u2019s Guide (2014). http:\/\/docs.oracle.com\/cd\/E37069_01\/pdf\/E37081.pdf"},{"key":"33_CR23","unstructured":"PathScale: PathScale ENZO 2015 (2015). http:\/\/www.pathscale.com\/enzo"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Pennycook, S.J., Jarvis, S.A.: Developing Performance-Portable Molecular Dynamics Kernels in OpenCL. In: 2012 SC Companion: High Performance Computing, Networking, Storage and Analysis (SCC), pp. 386\u2013395 (2012)","DOI":"10.1109\/SC.Companion.2012.58"},{"key":"33_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/978-3-319-17473-0_4","volume-title":"Languages and Compilers for Parallel Computing","author":"A Sabne","year":"2015","unstructured":"Sabne, A., Sakdhnagool, P., Lee, S., Vetter, J.S.: Evaluating performance portability of OpenACC. In: Brodman, J., Tu, P. (eds.) LCPC 2014. LNCS, vol. 8967, pp. 51\u201366. Springer, Heidelberg (2015). http:\/\/dx.doi.org\/10.1007\/978-3-319-17473-0_4"},{"key":"33_CR26","unstructured":"Strohmeier, E., Simon, H., Dongarra, J., Meurer, M.: The 46th top. 500 list, November 2015. http:\/\/top500.org\/list\/2015\/11\/"},{"key":"33_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"812","DOI":"10.1007\/978-3-319-09873-9_68","volume-title":"Euro-Par 2014 Parallel Processing","author":"S Wienke","year":"2014","unstructured":"Wienke, S., Terboven, C., Beyer, J.C., M\u00fcller, M.S.: A pattern-based comparison of OpenACC and OpenMP for accelerator computing. In: Silva, F., Dutra, I., Santos Costa, V. (eds.) Euro-Par 2014 Parallel Processing. LNCS, vol. 8632, pp. 812\u2013823. Springer, Heidelberg (2014). http:\/\/dx.doi.org\/10.1007\/978-3-319-09873-9_68"},{"key":"33_CR28","unstructured":"Wong, M.: The future of GPU\/accelerator programming models. In: Keynote at the 2nd Workshop on the LLVM Compiler Infrastructure in HPC (2015). https:\/\/llvm-hpc2-workshop.github.io\/slides\/Wong.pdf"},{"key":"33_CR29","unstructured":"Woolley, C.: Profiling and tuning OpenACC code. http:\/\/on-demand.gputechconf.com\/gtc\/2012\/presentations\/S0517B-Monday-Programming-GPUs-OpenACC.pdf"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46079-6_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T19:44:23Z","timestamp":1718826263000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46079-6_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319460789","9783319460796"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46079-6_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}