{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T02:14:26Z","timestamp":1782958466027,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T00:00:00Z","timestamp":1721174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"XRAC","award":["#NCR-130002"],"award-info":[{"award-number":["#NCR-130002"]}]},{"name":"NSF","award":["#1818253,#1854828,#2007991,#2018627,#2311830,#2312927"],"award-info":[{"award-number":["#1818253,#1854828,#2007991,#2018627,#2311830,#2312927"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,17]]},"DOI":"10.1145\/3626203.3670549","type":"proceedings-article","created":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T20:12:20Z","timestamp":1721247140000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Design and Implementation of an IPC-based Collective MPI Library for Intel GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7471-7552","authenticated-orcid":false,"given":"Chen-Chun","family":"Chen","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, The Ohio State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2112-4769","authenticated-orcid":false,"given":"Goutham Kalikrishna Reddy","family":"Kuncham","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, The Ohio State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7507-0940","authenticated-orcid":false,"given":"Pouya","family":"Kousha","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, The Ohio State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1200-2754","authenticated-orcid":false,"given":"Hari","family":"Subramoni","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, The Ohio State University, 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":"Computer Science and Engineering, The Ohio State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50371-0_19"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33518-1_16"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00014"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid57682.2023.00022"},{"key":"e_1_3_2_1_5_1","unstructured":"Intel. 2024. Intel Data Center GPU Max 1100. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/232876\/intel-data-center-gpu-max-1100\/specifications.html."},{"key":"e_1_3_2_1_6_1","unstructured":"Intel. 2024. Level-Zero. https:\/\/github.com\/oneapi-src\/level-zero."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Kawthar\u00a0Shafie Khorassani Ching-Hsiang Chu Hari Subramoni and Dhabaleswar\u00a0K. Panda. 2018. Performance Evaluation of MPI Libraries on GPU-enabled OpenPOWER Architectures: Early Experiences. In International Workshop on OpenPOWER for HPC (IWOPH 19) at the 2019 ISC High Performance Conference.","DOI":"10.1007\/978-3-030-34356-9_28"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1177\/10943420211008288"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622813"},{"key":"e_1_3_2_1_10_1","volume-title":"Porting CUDA-Based Molecular Dynamics Algorithms to AMD ROCm Platform Using HIP Framework: Performance Analysis","author":"Kuznetsov Evgeny","unstructured":"Evgeny Kuznetsov and Vladimir Stegailov. 2019. Porting CUDA-Based Molecular Dynamics Algorithms to AMD ROCm Platform Using HIP Framework: Performance Analysis. In Supercomputing, Vladimir Voevodin and Sergey Sobolev (Eds.). Springer International Publishing, Cham, 121\u2013130."},{"key":"e_1_3_2_1_11_1","unstructured":"NVIDIA. 2024. CUDA Interprocess Communication. https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.17"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC49587.2019.00008"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78713-4_7"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.222"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Hao Wang Sreeram Potluri Miao Luo Ashish\u00a0Kumar Singh Sayantan Sur and Dhabaleswar\u00a0K. Panda. 2011. MVAPICH2-GPU: Optimized GPU to GPU Communication for InfiniBand Clusters. Comput. Sci. (2011) 257\u2013266.","DOI":"10.1007\/s00450-011-0171-3"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00074"}],"event":{"name":"PEARC '24: Practice and Experience in Advanced Research Computing","location":"Providence RI USA","acronym":"PEARC '24","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 2024: Human Powered Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626203.3670549","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626203.3670549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:56:45Z","timestamp":1755867405000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626203.3670549"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,17]]},"references-count":17,"alternative-id":["10.1145\/3626203.3670549","10.1145\/3626203"],"URL":"https:\/\/doi.org\/10.1145\/3626203.3670549","relation":{},"subject":[],"published":{"date-parts":[[2024,7,17]]},"assertion":[{"value":"2024-07-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}