{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:02:24Z","timestamp":1766268144793,"version":"3.37.3"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T00:00:00Z","timestamp":1734480000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T00:00:00Z","timestamp":1734480000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1818253,1854828,2018627,2311830,2312927"],"award-info":[{"award-number":["1818253,1854828,2018627,2311830,2312927"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,18]]},"DOI":"10.1109\/hipc62374.2024.00022","type":"proceedings-article","created":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T20:05:39Z","timestamp":1740081939000},"page":"122-131","source":"Crossref","is-referenced-by-count":2,"title":["Design and Implementation of Kernel-based MPI Reduction Operations for Intel GPU s"],"prefix":"10.1109","author":[{"given":"Chen-Chun","family":"Chen","sequence":"first","affiliation":[{"name":"The Ohio State University,Columbus,Ohio,USA"}]},{"given":"Goutham Kalikrishna","family":"Reddy Kuncham","sequence":"additional","affiliation":[{"name":"The Ohio State University,Columbus,Ohio,USA"}]},{"given":"Hari","family":"Subramoni","sequence":"additional","affiliation":[{"name":"The Ohio State University,Columbus,Ohio,USA"}]},{"given":"Dhabaleswar K.","family":"Panda","sequence":"additional","affiliation":[{"name":"The Ohio State University,Columbus,Ohio,USA"}]}],"member":"263","reference":[{"article-title":"TOP 500 Supercomputer Sites","volume-title":"http:\/\/www.top500.org, 1993","author":"Strohmaier","key":"ref1"},{"year":"2004","key":"ref2","article-title":"Open MPI: Open Source High Performance Computing"},{"volume-title":"MVAPICH2: MPI over InfiniBand, 10GigE\/iWARP and RoCE","year":"2001","key":"ref3"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1145\/3569951.3597553","article-title":"Optimizing amber for device-to-device gpu communication","volume-title":"Practice and Experience in Advanced Research Computing, ser. PEARC \u201823","author":"Khuvis","year":"2023"},{"year":"2022","key":"ref5","article-title":"SYCL 2020 Specification Revision 5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50371-0_19"},{"year":"2024","key":"ref7","article-title":"Intel extension for tensorflow"},{"year":"2024","key":"ref8","article-title":"Intel Extension for PyTorch"},{"year":"2024","key":"ref9","article-title":"Intel optimization for horovod"},{"author":"Coporation","key":"ref10","article-title":"Intel MPI Library"},{"volume-title":"MPICH2: High Performance portable MPI implementation","key":"ref11"},{"year":"2022","key":"ref12","article-title":"Intel oneAPI"},{"key":"ref13","article-title":"Intel data center gpu max series overview"},{"volume-title":"MPI: A Message-Passing Interface Standard Version 4.1","year":"2023","author":"Passing","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33518-1_16"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s00450-011-0171-3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.222"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2514\/6.2010-522"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.17"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58667-0_18"},{"key":"ref21","article-title":"Per-formance Evaluation of MPI Libraries on GPU -enabled OpenPOWER Architectures: Early Experiences","volume-title":"International Workshop on Open-POWER for HPC (IWOPH 19) at the 2019 ISC High Performance Conference","author":"Khorassani","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00014"},{"issue":"17","key":"ref23","first-page":"e4667","article-title":"Design considerations for gpu-aware collective communications in mpi","volume-title":"Concurrency and Computation: Practice and Experience","volume":"30","author":"Faraji","year":"2018"},{"key":"ref24","first-page":"45","article-title":"Gpu-aware intranode mpi_allreduce","volume-title":"Proceedings of the 21st European MPI Users\u2019 Group Meeting","author":"Iman","year":"2014"},{"key":"ref25","first-page":"726","article-title":"Cuda kernel based collective reduction operations on large-scale gpu clusters","volume-title":"Proceedings of the 16th IEEEIACM International Symposium on Cluster, Cloud, and Grid Computing, ser. CCGRID \u201816","author":"Chu","year":"2016"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1145\/3392717.3392771","article-title":"Nv-group: link-efficient reduction for distributed deep learning on modern dense gpu systems","volume-title":"Proceedings of the 34th ACM International Conference on Supercomputing, ser. ICS \u201820","author":"Chu","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36592-9_11"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/10943420211008288"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78713-4_7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid57682.2023.00022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00074"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3388333.3388643"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PADW.2016.19"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622813"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC49587.2019.00008"}],"event":{"name":"2024 IEEE 31st International Conference on High Performance Computing, Data, and Analytics (HiPC)","start":{"date-parts":[[2024,12,18]]},"location":"Bangalore, India","end":{"date-parts":[[2024,12,21]]}},"container-title":["2024 IEEE 31st International Conference on High Performance Computing, Data, and Analytics (HiPC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10883940\/10884090\/10884146.pdf?arnumber=10884146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T06:56:44Z","timestamp":1740121004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10884146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,18]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/hipc62374.2024.00022","relation":{},"subject":[],"published":{"date-parts":[[2024,12,18]]}}}