{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T03:30:36Z","timestamp":1743046236667,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031407437"},{"type":"electronic","value":"9783031407444"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-40744-4_12","type":"book-chapter","created":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T23:03:28Z","timestamp":1693436608000},"page":"179-192","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring the\u00a0Limits of\u00a0Generic Code Execution on\u00a0GPUs via\u00a0Direct (OpenMP) Offload"],"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\/0000-0001-8449-8579","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":[[2023,9,1]]},"reference":[{"key":"12_CR1","doi-asserted-by":"publisher","unstructured":"Ant\u00e3o, S.F., et al.: Offloading Support for OpenMP in Clang and LLVM. In: Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC@SC), 14 November 2016, pp. 1\u201311, IEEE Computer Society, Salt Lake City, UT, USA (2016). https:\/\/doi.org\/10.1109\/LLVM-HPC.2016.006","DOI":"10.1109\/LLVM-HPC.2016.006"},{"key":"12_CR2","doi-asserted-by":"publisher","unstructured":"Bertolli, C., et al.: Integrating GPU support for OpenMP offloading directives into Clang. In: Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC@SC), 15 November 2015, pp. 1\u201311, ACM, Austin, Texas, USA (2015). https:\/\/doi.org\/10.1145\/2833157.2833161","DOI":"10.1145\/2833157.2833161"},{"key":"12_CR3","doi-asserted-by":"publisher","unstructured":"Bertolli, C., et al.: Coordinating GPU threads for OpenMP 4.0 in LLVM. In: Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC@SC), 17 November 2014, pp. 12\u201321. IEEE Computer Society, New Orleans, LA, USA (2014). https:\/\/doi.org\/10.1109\/LLVM-HPC.2014.10","DOI":"10.1109\/LLVM-HPC.2014.10"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Damschen, M., Riebler, H., Vaz, G., Plessl, C.: Transparent offloading of computational hotspots from binary code to Xeon Phi. In: Design, Automation & Test in Europe Conference & Exhibition (DATE), 9\u201313 March 2015, pp. 1078\u20131083, ACM, Grenoble, France (2015). https:\/\/dl.acm.org\/doi\/10.5555\/2755753.2757063","DOI":"10.7873\/DATE.2015.1124"},{"key":"12_CR5","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":"12_CR6","doi-asserted-by":"publisher","unstructured":"Doerfert, J., et al.: Breaking the vendor lock: performance portable programming through openMP as target independent runtime layer. In: International Conference on Parallel Architectures and Compilation Techniques (PACT), 8\u201312 October 2022, pp. 494\u2013504, ACM, Chicago, Illinois (2022). https:\/\/doi.org\/10.1145\/3559009.3569687","DOI":"10.1145\/3559009.3569687"},{"key":"12_CR7","doi-asserted-by":"publisher","unstructured":"Huber, J., et al.: Efficient Execution of OpenMP on GPUs. In: International Symposium on Code Generation and Optimization (CGO), 2\u20136 April 2022, pp. 41\u201352, IEEE, Seoul, Republic of Korea (2022). https:\/\/doi.org\/10.1109\/CGO53902.2022.9741290","DOI":"10.1109\/CGO53902.2022.9741290"},{"key":"12_CR8","doi-asserted-by":"publisher","unstructured":"Jablin, T.B., Prabhu, P., Jablin, J.A., Johnson, N.P., Beard, S.R., August, D.I.: Automatic CPU-GPU communication management and optimization. In: ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI), 4\u20138 June 2011, pp. 142\u2013151, ACM, San Jose, CA, USA (2011). https:\/\/doi.org\/10.1145\/1993498.1993516","DOI":"10.1145\/1993498.1993516"},{"key":"12_CR9","doi-asserted-by":"publisher","unstructured":"Matsumura, K., Zohouri, H.R., Wahib, M., Endo, T., Matsuoka, S.: AN5D: automated stencil framework for high-degree temporal blocking on GPUs. In: International Symposium on Code Generation and Optimization (CGO), February 2020, pp. 199\u2013211, ACM, San Diego, CA, USA (2020). https:\/\/doi.org\/10.1145\/3368826.3377904","DOI":"10.1145\/3368826.3377904"},{"key":"12_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/978-3-030-28596-8_7","volume-title":"OpenMP: Conquering the Full Hardware Spectrum","author":"F Mayer","year":"2019","unstructured":"Mayer, F., Knaust, M., Philippsen, M.: OpenMP on FPGAs\u2014a survey. In: Fan, X., de Supinski, B.R., Sinnen, O., Giacaman, N. (eds.) IWOMP 2019. LNCS, vol. 11718, pp. 94\u2013108. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-28596-8_7"},{"key":"12_CR11","doi-asserted-by":"publisher","unstructured":"Mikushin, D., Likhogrud, N., Zhang, E.Z., Bergstrom, C.: Kernelgen - the design and implementation of a next generation compiler platform for accelerating numerical models on GPUs. In: International Parallel & Distributed Processing Symposium Workshops (IPDPSW), 19\u201323 May 2014, pp. 1011\u20131020, IEEE Computer Society, Phoenix, AZ, USA (2014). https:\/\/doi.org\/10.1109\/IPDPSW.2014.115","DOI":"10.1109\/IPDPSW.2014.115"},{"key":"12_CR12","unstructured":"NVIDIA: Parallel Thread Execution ISA Version 8.1. https:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution\/index.html#stack-manipulation-instructions-alloca (2023)"},{"key":"12_CR13","doi-asserted-by":"publisher","unstructured":"\u00d6zen, G., Atzeni, S., Wolfe, M., Southwell, A., Klimowicz, G.: OpenMP GPU Offload in Flang and LLVM. In: Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC@SC), 13 November 2018, pp. 1\u20139, IEEE, Dallas, TX, USA (2018), https:\/\/doi.org\/10.1109\/LLVM-HPC.2018.8639434","DOI":"10.1109\/LLVM-HPC.2018.8639434"},{"key":"12_CR14","doi-asserted-by":"publisher","unstructured":"Ozen, G., Wolfe, M.: Performant portable openMP. In: ACM SIGPLAN International Conference on Compiler Construction (CC), 2\u20133 April 2022, pp. 156\u2013168, ACM, Seoul, South Korea (2022). https:\/\/doi.org\/10.1145\/3497776.3517780","DOI":"10.1145\/3497776.3517780"},{"key":"12_CR15","doi-asserted-by":"publisher","unstructured":"Pakin, S., Lang, M., Kerbyson, D.J.: The reverse-acceleration model for programming Petascale hybrid systems. IBM J. Res. Develop. 53(5), 8 (2009). https:\/\/doi.org\/10.1147\/JRD.2009.5429074","DOI":"10.1147\/JRD.2009.5429074"},{"key":"12_CR16","doi-asserted-by":"publisher","unstructured":"Silberstein, M., Ford, B., Keidar, I., Witchel, E.: GPUfs: integrating a file system with GPUs. In: Architectural Support for Programming Languages and Operating Systems (ASPLOS), 16\u201320 March 2013, pp. 485\u2013498, ACM, Houston, TX, USA (2013). https:\/\/doi.org\/10.1145\/2451116.2451169","DOI":"10.1145\/2451116.2451169"},{"key":"12_CR17","unstructured":"System Software Work Group, OpenPOWER Foundation: Vector Intrinsics Porting Guide. https:\/\/openpowerfoundation.org\/specifications\/vectorintrinsicportingguide\/ (2018)"},{"key":"12_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/978-3-030-85262-7_11","volume-title":"OpenMP: Enabling Massive Node-Level Parallelism","author":"S Tian","year":"2021","unstructured":"Tian, S., Chesterfield, J., Doerfert, J., Chapman, B.: Experience report: writing a portable GPU runtime with openMP 5.1. In: McIntosh-Smith, S., de Supinski, B.R., Klinkenberg, J. (eds.) IWOMP 2021. LNCS, vol. 12870, pp. 159\u2013169. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-85262-7_11"},{"key":"12_CR19","doi-asserted-by":"publisher","unstructured":"Tian, S., Doerfert, J., Chapman, B.M.: Concurrent execution of deferred openMP target tasks with hidden helper threads. In: Chapman, B., Moreira, J. (eds.) Languages and Compilers for Parallel Computing. LCPC 2020. Lecture Notes in Computer Science, vol. 13149. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-95953-1_4","DOI":"10.1007\/978-3-030-95953-1_4"},{"key":"12_CR20","doi-asserted-by":"publisher","unstructured":"Tian, S., Huber, J., Parasyris, K., Chapman, B.M., Doerfert, J.: Direct GPU compilation and execution for host applications with OpenMP Parallelism. In: Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC@SC), 13\u201318 November 2022, pp. 43\u201351, IEEE, Dallas, TX, USA (2022). https:\/\/doi.org\/10.1109\/LLVM-HPC56686.2022.00010","DOI":"10.1109\/LLVM-HPC56686.2022.00010"},{"key":"12_CR21","unstructured":"Tian, S., Scogland, T., Chapman, B., Doerfert, J.: GPU First - Execution of Legacy CPU Codes on GPUs (2023)"},{"key":"12_CR22","doi-asserted-by":"publisher","unstructured":"Yviquel, H., et al.: The OpenMP Cluster Programming Model. In: Workshop of the International Conference on Parallel Processing (ICPP), 29 August 2022\u20131 September 2022, pp. 1\u201311, ACM, Bordeaux, France (2022). https:\/\/doi.org\/10.1145\/3547276.3548444","DOI":"10.1145\/3547276.3548444"}],"container-title":["Lecture Notes in Computer Science","OpenMP: Advanced Task-Based, Device and Compiler Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-40744-4_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T23:04:40Z","timestamp":1693436680000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40744-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031407437","9783031407444"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40744-4_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 September 2023","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":"Bristol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/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":"20","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":"15","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":"75% - 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","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":"4","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)"}}]}}