{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:47:50Z","timestamp":1785606470019,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T00:00:00Z","timestamp":1752796800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1939140"],"award-info":[{"award-number":["CNS-1939140"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3708035.3736109","type":"proceedings-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T12:10:41Z","timestamp":1752840641000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["OpenSHMEM Performance on Bluefield-3 Data Processing Units (DPUs)"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9151-6607","authenticated-orcid":false,"given":"Michael","family":"Beebe","sequence":"first","affiliation":[{"name":"Texas Tech University, Lubbock, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7450-5787","authenticated-orcid":false,"given":"Benjamin","family":"Michalowicz","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0356-1781","authenticated-orcid":false,"given":"Dhabaleswar K.","family":"Panda","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9961-9051","authenticated-orcid":false,"given":"Yong","family":"Chen","sequence":"additional","affiliation":[{"name":"Texas Tech University, Lubbock, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4984-6209","authenticated-orcid":false,"given":"Wendy","family":"Poole","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, NM, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4531-7453","authenticated-orcid":false,"given":"Steve","family":"Poole","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, NM, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,18]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Argonne National Laboratory. [n. d.]. MPICH: high performance and widely portable implementation of the Message Passing Interface (MPI) standard. https:\/\/www.mpich.org\/"},{"key":"e_1_3_3_1_3_2","volume-title":"The Portals 4.2 Network Programming Interface","author":"D. Barrett, Brian W. and Brightwell, Ron and Hemmert, K. Scott and Wheeler, Kyle B. and Underwood, Keith","year":"2018","unstructured":"Barrett, Brian W. and Brightwell, Ron and Hemmert, K. Scott and Wheeler, Kyle B. and Underwood, Keith D.2018. The Portals 4.2 Network Programming Interface. Technical Report SAND2018-12790. Sandia National Laboratories."},{"key":"e_1_3_3_1_4_2","unstructured":"Barrett Brian W. and Smith Stan and Dinan James and Seager Kayla and Grant Ryan E.2016. Sandia OpenSHMEM. https:\/\/www.osti.gov\/biblio\/1312730"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.2172\/1846897"},{"key":"e_1_3_3_1_6_2","first-page":"1","volume-title":"Proceedings of the Fourth Conference on Partitioned Global Address Space Programming Model","author":"Lauren Chapman, Barbara and Curtis, Tony and Pophale, Swaroop and Poole, Stephen and Kuehn, Jeff and Koelbel, Chuck and Smith,","year":"2010","unstructured":"Chapman, Barbara and Curtis, Tony and Pophale, Swaroop and Poole, Stephen and Kuehn, Jeff and Koelbel, Chuck and Smith, Lauren. 2010. Introducing OpenSHMEM: SHMEM for the PGAS community. In Proceedings of the Fourth Conference on Partitioned Global Address Space Programming Model. 1\u20133."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.23919\/ISC.2024.10528935"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2017.46"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2015.15"},{"key":"e_1_3_3_1_10_2","series-title":"Lecture Notes in Computer Science","volume-title":"OpenSHMEM and Related Technologies. OpenSHMEM in the Era of Exascale and Smart Networks","author":"Alex Horany, Morad and Margolin,","year":"2021","unstructured":"Horany, Morad and Margolin, Alex. 2021. Remote Programmability Model for SmartNICs in HPC Workloads. In OpenSHMEM and Related Technologies. OpenSHMEM in the Era of Exascale and Smart Networks(Lecture Notes in Computer Science, Vol.\u00a013159), Poole, Stephen and Hernandez, Oscar and Baker, Matthew and Curtis, Tony (Ed.). Springer."},{"key":"e_1_3_3_1_11_2","series-title":"Lecture Notes in Computer Science","volume-title":"OpenSHMEM and Related Technologies. OpenSHMEM in the Era of Exascale and Smart Networks","author":"Akhil Langer,","year":"2021","unstructured":"Langer, Akhil. 2021. Dynamic Heap Allocation in NVSHMEM. In OpenSHMEM and Related Technologies. OpenSHMEM in the Era of Exascale and Smart Networks(Lecture Notes in Computer Science, Vol.\u00a013159), Poole, Stephen and Hernandez, Oscar and Baker, Matthew and Curtis, Tony (Ed.). Springer."},{"key":"e_1_3_3_1_12_2","series-title":"(SC \u201923)","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Xiaoyi Li, Yuke and Guo, Yanfei and Lu,","year":"2023","unstructured":"Li, Yuke and Guo, Yanfei and Lu, Xiaoyi. 2023. Characterizing One-\/Two-sided Designs in OpenSHMEM Collectives. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (Denver, Colorado, 12-17) (SC \u201923). Association for Computing Machinery, New York, NY, USA. Research Poster Paper."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER51413.2022.00017"},{"key":"e_1_3_3_1_14_2","unstructured":"Michael Beebe. [n. d.]. shmembench: Benchmarking suite for OpenSHMEM implementations adhering to either the v1.4 or v1.5 specification.https:\/\/github.com\/michael-beebe\/shmembench"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC62374.2024.00012"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3569951.3593595"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI59126.2023.00020"},{"key":"e_1_3_3_1_18_2","unstructured":"Network-Based Computing Laboratory Ohio State University. 2024. OSU Micro-Benchmarks 7.5. Available at: https:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/."},{"key":"e_1_3_3_1_19_2","unstructured":"NVIDIA. 2022. NVIDIA BlueField-3 DPU Data Sheet. https:\/\/resources.nvidia.com\/en-us-accelerated-networking-resource-library\/datasheet-nvidia-bluefield?lx=LbHvpR&topic=networking-cloud"},{"key":"e_1_3_3_1_20_2","unstructured":"Oak Ridge National Laboratory. [n. d.]. Oak Ridge OpenSHMEM Benchmarks. https:\/\/github.com\/ornl-languages\/osb"},{"key":"e_1_3_3_1_21_2","unstructured":"OSSS. [n. d.]. OSSS-UCX: Reference Implementation of OpenSHMEM over UCX. https:\/\/github.com\/openshmem-org\/osss-ucx"},{"key":"e_1_3_3_1_22_2","unstructured":"Ray Ryan Saptarshi and Ray Utpal Kumar and Anand Ashish and Bhaumik Parama. 2016. Distributed Shared Memory \u2013 A Survey and Implementation Using Openshmem. International Journal of Engineering Research and Applications 6 2 (2016) 49\u201352."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2017.23"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-04888-3_3"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00022"},{"key":"e_1_3_3_1_26_2","unstructured":"Tibbetts Nathan. 2025. A Survey on Heterogeneous Computing Using SmartNICs and Emerging Data Processing Units. (2025). arXiv:https:\/\/arXiv.org\/abs\/2504.03653\u00a0[cs.DC]"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.2172\/1814738"}],"event":{"name":"PEARC '25: Practice and Experience in Advanced Research Computing","location":"Columbus Ohio USA","acronym":"PEARC '25","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Practice and Experience in Advanced Research Computing 2025: The Power of Collaboration"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3708035.3736109","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3708035.3736109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T12:31:37Z","timestamp":1752841897000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708035.3736109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":26,"alternative-id":["10.1145\/3708035.3736109","10.1145\/3708035"],"URL":"https:\/\/doi.org\/10.1145\/3708035.3736109","relation":{},"subject":[],"published":{"date-parts":[[2025,7,18]]},"assertion":[{"value":"2025-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}