{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T18:18:40Z","timestamp":1778869120752,"version":"3.51.4"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031159213","type":"print"},{"value":"9783031159220","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-15922-0_10","type":"book-chapter","created":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T23:03:37Z","timestamp":1663628617000},"page":"145-158","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Just-in-Time Compilation and\u00a0Link-Time Optimization for\u00a0OpenMP Target Offloading"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6468-6839","authenticated-orcid":false,"given":"Shilei","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4987-8116","authenticated-orcid":false,"given":"Joseph","family":"Huber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5397-4402","authenticated-orcid":false,"given":"John","family":"Tramm","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8449-8579","authenticated-orcid":false,"given":"Barbara","family":"Chapman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7870-8963","authenticated-orcid":false,"given":"Johannes","family":"Doerfert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,20]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Huber, J., et al.: Efficient Execution of OpenMP on GPUs. In: IEEE\/ACM International Symposium on Code Generation and Optimization, CGO 2022, Seoul, Republic of Korea, 2\u20136 April 2022, pp. 41\u201352 (2022)","DOI":"10.1109\/CGO53902.2022.9741290"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Juckeland, G., et al.: SPEC ACCEL: A standard application suite for measuring hardware accelerator performance. In: High Performance Computing Systems. Performance Modeling, Benchmarking, and Simulation - 5th International Workshop, PMBS 2014, New Orleans, LA, USA, 16 November 2014. Revised Selected Papers. vol. 8966, pp. 46\u201367 (2014)","DOI":"10.1007\/978-3-319-17248-4_3"},{"key":"10_CR3","doi-asserted-by":"publisher","unstructured":"Romano, P.K., Horelik, N.E., Herman, B.R., Nelson, A.G., Forget, B.: OpenMC: a state-of-the-art Monte Carlo code for research and development. Ann. Nucl. Energy 82, 90\u201397 (2015). https:\/\/doi.org\/10.1016\/j.anucene.2014.07.048, https:\/\/doi.org\/10.1016\/j.anucene.2014.07.048","DOI":"10.1016\/j.anucene.2014.07.048"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Tramm, J., et al.: Toward portable GPU acceleration of the OpenMC Monte Carlo particle transport code. In: International Conference on Physics of Reactors (PHYSOR 2022). Pittsburgh, USA (2022)","DOI":"10.13182\/PHYSOR22-37847"},{"key":"10_CR5","unstructured":"Tramm, J.R., Siegel, A.R., Islam, T., Schulz, M.: XSBench - the development and verification of a performance abstraction for Monte Carlo reactor analysis. In: PHYSOR (2014)"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Tramm, J.R., Siegel, A.R., Forget, B., Josey, C.: Performance analysis of a reduced data movement algorithm for Neutron cross Section data in Monte Carlo simulations. In: Solving Software Challenges for Exascale - International Conference on Exascale Applications and Software, EASC 2014, Stockholm, Sweden, 2\u20133 April 2014, Revised Selected Papers. vol. 8759, pp. 39\u201356 (2014)","DOI":"10.1007\/978-3-319-15976-8_3"},{"key":"10_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/978-3-319-65578-9_7","volume-title":"Scaling OpenMP for Exascale Performance and Portability","author":"P Atkinson","year":"2017","unstructured":"Atkinson, P., McIntosh-Smith, S.: On the performance of parallel tasking runtimes for an irregular fast multipole method application. In: de Supinski, B.R., Olivier, S.L., Terboven, C., Chapman, B.M., M\u00fcller, M.S. (eds.) IWOMP 2017. LNCS, vol. 10468, pp. 92\u2013106. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-65578-9_7"},{"key":"10_CR8","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.actamat.2013.09.036","volume":"62","author":"JL Fattebert","year":"2014","unstructured":"Fattebert, J.L., Wickett, M., Turchi, P.: Phase-field modeling of coring during solidification of au-ni alloy using quaternions and calphad input. Acta Materialia 62, 89\u2013104 (2014). https:\/\/doi.org\/10.1016\/j.actamat.2013.09.036","journal-title":"Acta Materialia"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Bertolli, C., et al.: Coordinating GPU threads for OpenMP 4.0 in LLVM. In: Proceedings of the 2014 LLVM Compiler Infrastructure in HPC, LLVM 2014, New Orleans, LA, USA, 17 November 2014, pp. 12\u201321 (2014)","DOI":"10.1109\/LLVM-HPC.2014.10"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Bertolli, C., et al.: Integrating GPU support for OpenMP offloading directives into clang. In: Proceedings of the Second Workshop on the LLVM Compiler Infrastructure in HPC, LLVM 2015, Austin, Texas, USA, 15 November 2015. pp. 5:1\u20135:11 (2015)","DOI":"10.1145\/2833157.2833161"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"\u00d6zen, G., Atzeni, S., Wolfe, M., Southwell, A., Klimowicz, G.: OpenMP GPU Offload in Flang and LLVM. In: 2018 IEEE\/ACM 5th Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC), pp. 1\u20139 (2018)","DOI":"10.1109\/LLVM-HPC.2018.8639434"},{"issue":"2","key":"10_CR12","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1145\/857076.857077","volume":"35","author":"J Aycock","year":"2003","unstructured":"Aycock, J.: A brief history of just-in-time. ACM Comput. Surv. 35(2), 97\u2013113 (2003)","journal-title":"ACM Comput. Surv."},{"key":"10_CR13","unstructured":"The Khronos Group Inc.: SPIR Overview (2022). https:\/\/www.khronos.org\/spir\/"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Peng, H., Shann, J.J.: Translating OpenACC to LLVM IR with SPIR kernels. In: 15th IEEE\/ACIS International Conference on Computer and Information Science, ICIS 2016, Okayama, Japan, 26\u201329 June 2016. pp. 1\u20136 (2016)","DOI":"10.1109\/ICIS.2016.7550823"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Ha, O., Kuh, I., Tchamgoue, G.M., Jun, Y.: On-the-fly detection of data races in OpenMP programs. In: Proceedings of the 10th Workshop on Parallel and Distributed Systems: Testing, Analysis, and Debugging, PADTAD 2012, Minneapolis, MN, USA, 16 July 2012. pp. 1\u201310 (2012)","DOI":"10.1145\/2338967.2336808"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Luk, C., Pin: building customized program analysis tools with dynamic instrumentation. In: Proceedings of the ACM SIGPLAN 2005 Conference on Programming Language Design and Implementation, Chicago, IL, USA, 12\u201315 June 2005. pp. 190\u2013200 (2005)","DOI":"10.1145\/1065010.1065034"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Gaikwad, S., Nisbet, A., Luj\u00e1n, M.: Hosting OpenMP programs on Java virtual machines. In: Proceedings of the 16th ACM SIGPLAN International Conference on Managed Programming Languages and Runtimes, MPLR 2019, Athens, Greece, 21\u201322 October 2019. pp. 63\u201371 (2019)","DOI":"10.1145\/3357390.3361031"},{"key":"10_CR18","unstructured":"Glek, T., Hubicka, J.: Optimizing real world applications with GCC link time optimization. arXiv preprint arXiv:1010.2196 (2010)"},{"key":"10_CR19","unstructured":"Murphy, M., Sundaram, A.: Improving GPU application performance with NVIDIA CUDA 11.2 device link time optimization, February 2021. https:\/\/developer.nvidia.com\/blog\/improving-gpu-app-performance-with-cuda-11-2-device-lto\/"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Ant\u00e3o, S.F., et al.: Offloading support for OpenMP in clang and LLVM. In: Third Workshop on the LLVM Compiler Infrastructure in HPC, LLVM-HPC@SC 2016, Salt Lake City, UT, USA, 14 November 2016. pp. 1\u201311 (2016)","DOI":"10.1109\/LLVM-HPC.2016.006"},{"key":"10_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/978-3-030-28596-8_11","volume-title":"OpenMP: Conquering the Full Hardware Spectrum","author":"J Doerfert","year":"2019","unstructured":"Doerfert, J., Diaz, J.M.M., Finkel, H.: The TRegion interface and compiler optimizations for OpenMP target regions. In: Fan, X., de Supinski, B.R., Sinnen, O., Giacaman, N. (eds.) IWOMP 2019. LNCS, vol. 11718, pp. 153\u2013167. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-28596-8_11"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Tiotto, E., Mahjour, B., Tsang, W., Xue, X., Islam, T., Chen, W.: OpenMP 4.5 Compiler optimization for GPU offloading. IBM J. Res. Dev. 64(3\/4), 14:1\u201314:11 (2020)","DOI":"10.1147\/JRD.2019.2962428"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Doerfert, J., Patel, A., Huber, J., Tian, S., Diaz, J.M.M., Chapman, B., Georgakoudis, G.: Co-Designing an OpenMP GPU runtime and optimizations for near-zero overhead execution. In: 36th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2022, St. Petersburg, FL USA, 15\u201319 May 2023. IEEE (2022)","DOI":"10.1109\/IPDPS53621.2022.00055"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Doerfert, J., et al.: Breaking the vendor lock \u2013 performance portable programming through OpenMP as target independent runtime layer. In: International Conference on Parallel Architectures and Compilation Techniques, PACT (2022, to appear)","DOI":"10.1145\/3559009.3569687"},{"key":"10_CR25","doi-asserted-by":"publisher","unstructured":"Moses, W.S., Ivanov, I.R., Domke, J., Endo, T., Doerfert, J., Zinenko, O.: High-performance GPU-to-CPU transpilation and optimization via high-level parallel constructs (2022). https:\/\/doi.org\/10.48550\/ARXIV.2207.00257, https:\/\/arxiv.org\/abs\/2207.00257","DOI":"10.48550\/ARXIV.2207.00257"}],"container-title":["Lecture Notes in Computer Science","OpenMP in a Modern World: From Multi-device Support to Meta Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-15922-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T06:06:06Z","timestamp":1701065166000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-15922-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031159213","9783031159220"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-15922-0_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"20 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IWOMP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on OpenMP","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chattanooga, TN","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.iwomp.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"13","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"11","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"85% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.76","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.8","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}