{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:05:34Z","timestamp":1759104334627,"version":"3.44.0"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032063427","type":"print"},{"value":"9783032063434","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-06343-4_1","type":"book-chapter","created":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T13:23:57Z","timestamp":1759065837000},"page":"3-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Discussion of\u00a0Device-Device Collective Communication in\u00a0OpenMP Target Offloading"],"prefix":"10.1007","author":[{"given":"Baodi","family":"Shan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mauricio","family":"Araya-Polo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes","family":"Doerfert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barbara","family":"Chapman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"1_CR1","doi-asserted-by":"publisher","unstructured":"Huber, J., et al.: Efficient execution of openmp on GPUs. In: 2022 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO), pp. 41\u201352 (2022). https:\/\/doi.org\/10.1109\/CGO53902.2022.9741290","DOI":"10.1109\/CGO53902.2022.9741290"},{"key":"1_CR2","doi-asserted-by":"publisher","unstructured":"Klinkenberg, J., Kraus, J., Terboven, C., M\u00fcller, M.S.: Towards locality-aware host-to-device offloading in openmp. In: Espinosa, A., Klemm, M., de\u00a0Supinski, B.R., Cytowski, M., Klinkenberg, J. (eds.) Advancing OpenMP for Future Accelerators - 20th International Workshop on OpenMP, IWOMP 2024, Perth, WA, Australia, 23\u201325 September 2024, Proceedings. Lecture Notes in Computer Science, vol. 15195, pp. 3\u201315. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-72567-8_1","DOI":"10.1007\/978-3-031-72567-8_1"},{"key":"1_CR3","unstructured":"Langer, A., Potluri, S., Newburn, C.J., Goswami, A.: Nvshmem: a partitioned global address space library for nvidia GPU clusters. In: NVIDIA GPU Technology Conference (GTC). NVIDIA (2019). https:\/\/developer.download.nvidia.com\/video\/gputechconf\/gtc\/2019\/presentation\/s9677-nvshmem-a-pgas-library-for-gpu-clusters.pdf"},{"key":"1_CR4","unstructured":"LLNL: Tioga | hpc @ llnl (2025). https:\/\/hpc.llnl.gov\/hardware\/compute-platforms\/tioga. Accessed 16 May 2025"},{"key":"1_CR5","doi-asserted-by":"publisher","unstructured":"Lu, W., et al.: Towards efficient remote openmp offloading. In: OpenMP in a Modern World: From Multi-Device Support to Meta Programming: 18th International Workshop on OpenMP, IWOMP 2022, Chattanooga, TN, USA, 27\u201330 September 2022, Proceedings, pp. 17\u201331. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-15922-0_2","DOI":"10.1007\/978-3-031-15922-0_2"},{"key":"1_CR6","doi-asserted-by":"publisher","unstructured":"Pan, L., Liu, J., Yuan, J., Zhang, R., Li, P., Xiao, Z.: OCCL: a deadlock-free library for GPU collective communication. CoRR abs\/2303.06324 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2303.06324","DOI":"10.48550\/ARXIV.2303.06324"},{"key":"1_CR7","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/978-3-031-07312-0_16","volume-title":"High Performance Computing","author":"A Patel","year":"2022","unstructured":"Patel, A., Doerfert, J.: Remote openmp offloading. In: Varbanescu, A.L., Bhatele, A., Luszczek, P., Marc, B. (eds.) High Performance Computing, pp. 315\u2013333. Springer, Cham (2022)"},{"key":"1_CR8","doi-asserted-by":"publisher","unstructured":"Roa\u00a0Perdomo, D.A., et al.: Memory transfer decomposition: exploring smart data movement through architecture-aware strategies. In: Proceedings of the SC 2023 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC-W 2023, pp. 1958\u20131967. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3624062.3624609","DOI":"10.1145\/3624062.3624609"},{"key":"1_CR9","doi-asserted-by":"publisher","unstructured":"Shan, B., Araya-Polo, M.: Evaluation of programming models and performance for stencil computation on GPGPUs. In: 2024 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 1178\u20131180 (2024). https:\/\/doi.org\/10.1109\/IPDPSW63119.2024.00198","DOI":"10.1109\/IPDPSW63119.2024.00198"},{"key":"1_CR10","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/978-3-031-72567-8_9","volume-title":"Advancing OpenMP for Future Accelerators","author":"B Shan","year":"2024","unstructured":"Shan, B., Araya-Polo, M., Chapman, B.: Evaluation of directive-based programming models for stencil computation on current GPGPU architectures. In: Espinosa, A., Klemm, M., de Supinski, B.R., Cytowski, M., Klinkenberg, J. (eds.) Advancing OpenMP for Future Accelerators, pp. 126\u2013140. Springer, Cham (2024)"},{"key":"1_CR11","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1007\/978-3-031-72567-8_5","volume-title":"Advancing OpenMP for Future Accelerators","author":"B Shan","year":"2024","unstructured":"Shan, B., Araya-Polo, M., Chapman, B.: Towards a scalable and efficient PGAS-based distributed openmp. In: Espinosa, A., Klemm, M., de Supinski, B.R., Cytowski, M., Klinkenberg, J. (eds.) Advancing OpenMP for Future Accelerators, pp. 64\u201378. Springer, Cham (2024)"},{"key":"1_CR12","unstructured":"Shan, B., Araya-Polo, M., Chapman, B.: Diomp-offloading: toward portable distributed heterogeneous openmp (2025). https:\/\/arxiv.org\/abs\/2506.02486"},{"key":"1_CR13","doi-asserted-by":"publisher","unstructured":"Shan, B., Araya-Polo, M., Malik, A.M., Chapman, B.: MPI-based remote openmp offloading: a more efficient and easy-to-use implementation. In: Proceedings of the 14th International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2023, pp. 50\u201359. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3582514.3582519","DOI":"10.1145\/3582514.3582519"},{"key":"1_CR14","doi-asserted-by":"publisher","unstructured":"Soyt\u00fcrk, M.A., Akhtar, P., Tezcan, E., Unat, D.: Monitoring collective communication among GPUs. In: Chaves, R., et al. (eds.) Euro-Par 2021: Parallel Processing Workshops - Euro-Par 2021 International Workshops, Lisbon, Portugal, 30\u201331 August 2021, Revised Selected Papers. Lecture Notes in Computer Science, vol. 13098, pp. 41\u201352. Springer (2021). https:\/\/doi.org\/10.1007\/978-3-031-06156-1_4","DOI":"10.1007\/978-3-031-06156-1_4"},{"key":"1_CR15","doi-asserted-by":"publisher","unstructured":"Torres, R., Ferrer, R., Teruel, X.: A novel set of directives for multi-device programming with openmp. In: 2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 401\u2013410 (2022). https:\/\/doi.org\/10.1109\/IPDPSW55747.2022.00075","DOI":"10.1109\/IPDPSW55747.2022.00075"},{"key":"1_CR16","doi-asserted-by":"publisher","unstructured":"Unat, D., et al.: The landscape of GPU-centric communication. CoRR abs\/2409.09874 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2409.09874","DOI":"10.48550\/ARXIV.2409.09874"},{"key":"1_CR17","unstructured":"Woolley, C.: NCCL: accelerated multi-GPU collective communications. In: NVIDIA GPU Technology Conference (SC15) (2015). https:\/\/images.nvidia.com\/events\/sc15\/pdfs\/NCCL-Woolley.pdf. Technical presentation"}],"container-title":["Lecture Notes in Computer Science","OpenMP: Balancing Productivity and Performance Portability"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06343-4_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T13:23:59Z","timestamp":1759065839000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06343-4_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"ISBN":["9783032063427","9783032063434"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06343-4_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]},"assertion":[{"value":"29 September 2025","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":"Charlotte, NC","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2025","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"}}]}}