{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T04:41:05Z","timestamp":1789101665500,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T00:00:00Z","timestamp":1699660800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFB0300101"],"award-info":[{"award-number":["2021YFB0300101"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972408"],"award-info":[{"award-number":["61972408"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3581784.3607074","type":"proceedings-article","created":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T20:34:48Z","timestamp":1698698088000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Optimizing MPI Collectives on Shared Memory Multi-Cores"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3056-9391","authenticated-orcid":false,"given":"Jintao","family":"Peng","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3542-4869","authenticated-orcid":false,"given":"Jianbin","family":"Fang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3745-7541","authenticated-orcid":false,"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Chile"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3265-9772","authenticated-orcid":false,"given":"Min","family":"Xie","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9929-6459","authenticated-orcid":false,"given":"Yi","family":"Dai","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9035-1538","authenticated-orcid":false,"given":"Bo","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, ChangSha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7827-6304","authenticated-orcid":false,"given":"Shengguo","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6157-0662","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computing, University of Leeds, Leeds, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,11,11]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"[n. d.]. Build OpenMPI with UCX. https:\/\/openucx.readthedocs.io\/en\/master\/running.html"},{"key":"e_1_3_2_2_2_1","unstructured":"[n. d.]. Improve Performance and Stability with Intel\u00ae MPI Library on Infini-Band. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/improve-performance-and-stability-with-intel-mpi-library-on-infiniband.html"},{"key":"e_1_3_2_2_3_1","unstructured":"[n. d.]. MVAPICH2 2.3.7 User Guide. http:\/\/mvapich.cse.ohio-state.edu\/static\/media\/mvapich\/mvapich2-userguide.pdf"},{"key":"e_1_3_2_2_4_1","unstructured":"[n. d.]. NVIDIA: Enabling HCOLL in Open MPI. https:\/\/docs.nvidia.com\/networking\/display\/HPCXv29\/HCOLL"},{"key":"e_1_3_2_2_5_1","unstructured":"2023-01-02. Intel MPI. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/mpi-library.html"},{"key":"e_1_3_2_2_6_1","unstructured":"2023-01-02. MPICH. https:\/\/www.mpich.org\/"},{"key":"e_1_3_2_2_7_1","unstructured":"2023-01-02. MVAPICH Home. https:\/\/mvapich.cse.ohio-state.edu"},{"key":"e_1_3_2_2_8_1","unstructured":"2023-01-02. Open MPI. https:\/\/www.open-mpi.org\/"},{"key":"e_1_3_2_2_9_1","unstructured":"2023-01-02. OSU Micro-Benchmarks. https:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/"},{"key":"e_1_3_2_2_10_1","unstructured":"2023-03-14. Intel\u00ae 64 and IA-32 Architectures Software Developer Manuals. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/intel-sdm.html"},{"key":"e_1_3_2_2_11_1","unstructured":"2023-03-14. Intel\u00ae Xeon\u00ae Scalable Processor: The Foundation of Data Centre Innovation. https:\/\/simplecore-ger.intel.com\/swdevcon-uk\/wp-content\/uploads\/sites\/5\/2017\/10\/UK-Dev-Con_Toby-Smith-Track-A_1000.pdf"},{"key":"e_1_3_2_2_12_1","unstructured":"2023-y-02. Linux kernel v6.4.2. https:\/\/elixir.bootlin.com\/linux\/latest\/source\/mm\/process_vm_access.c"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126954"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00014"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ExaMPI49596.2019.00008"},{"key":"e_1_3_2_2_16_1","volume-title":"Designing High Performance and Scalable MPI Intra-node Communication Support for Clusters. In IEEE International Conference on Cluster Computing.","author":"Chai L.","unstructured":"L. Chai, A. Hartono, and D. K. Panda. 2006. Designing High Performance and Scalable MPI Intra-node Communication Support for Clusters. In IEEE International Conference on Cluster Computing."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.106"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00033"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00607-013-0327-z"},{"key":"e_1_3_2_2_20_1","volume-title":"VGG image annotator (VIA). URL: http:\/\/www.robots.ox.ac.uk\/vgg\/software\/via 2","author":"Dutta Abhishek","year":"2016","unstructured":"Abhishek Dutta, Ankush Gupta, and Andrew Zissermann. 2016. VGG image annotator (VIA). URL: http:\/\/www.robots.ox.ac.uk\/vgg\/software\/via 2 (2016)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42514-020-00039-4"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-020-0741-6"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503294"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517327.2442534"},{"key":"e_1_3_2_2_25_1","unstructured":"Juan Antonio Rico Gallego. 2016. t-Lop: Scalably and accurately modeling contention and mapping effects in multi-corec clusters. (2016)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2012.09.016"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87475-1_21"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45825-5_5"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00111"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2019.00055"},{"key":"e_1_3_2_2_32_1","volume-title":"Computer architecture: a quantitative approach","author":"Hennessy John L","unstructured":"John L Hennessy and David A Patterson. 2011. Computer architecture: a quantitative approach. Elsevier."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30695-7_16"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00032"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3488766.3488792"},{"key":"e_1_3_2_2_36_1","volume-title":"2005 International Conference on Parallel Processing (ICPP'05)","author":"Jin H-W","year":"2005","unstructured":"H-W Jin, Sayantan Sur, Lei Chai, and Dhabaleswar K Panda. 2005. Limic: Support for high-performance mpi intra-node communication on linux cluster. In 2005 International Conference on Parallel Processing (ICPP'05). IEEE, 184--191."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/173682.165154"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477113.3487264"},{"key":"e_1_3_2_2_39_1","volume-title":"Improved MPI collectives for MPI processes in shared address spaces. Cluster computing 17, 4","author":"Li Shigang","year":"2014","unstructured":"Shigang Li, Torsten Hoefler, Chungjin Hu, and Marc Snir. 2014. Improved MPI collectives for MPI processes in shared address spaces. Cluster computing 17, 4 (2014), 1139--1155."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2462902.2462903"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2768413"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2008.87"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/11846802_17"},{"key":"e_1_3_2_2_44_1","unstructured":"Benjamin S Parsons. 2015. Accelerating MPI collective communications through hierarchical algorithms with flexible inter-node communication and imbalance awareness. (2015)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2011.5764686"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.44"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751240"},{"key":"e_1_3_2_2_49_1","volume-title":"Resnet in resnet: Generalizing residual architectures. arXiv preprint arXiv:1603.08029","author":"Targ Sasha","year":"2016","unstructured":"Sasha Targ, Diogo Almeida, and Kevin Lyman. 2016. Resnet in resnet: Generalizing residual architectures. arXiv preprint arXiv:1603.08029 (2016)."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2003.1213188"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00037"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489525.3511689"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2616498.2616532"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2012.05.002"},{"key":"e_1_3_2_2_56_1","volume-title":"The SGI\u00ae AltixTM 3000 global shared-memory architecture. Silicon Graphics","author":"Woodacre Michael","year":"2005","unstructured":"Michael Woodacre, Derek Robb, Dean Roe, and Karl Feind. 2005. The SGI\u00ae AltixTM 3000 global shared-memory architecture. Silicon Graphics, Inc 44 (2005)."},{"key":"e_1_3_2_2_57_1","volume-title":"2005 International Conference on Parallel Processing (ICPP'05)","author":"Wu Meng-Shiou","year":"2005","unstructured":"Meng-Shiou Wu, Ricky A Kendall, and Kyle Wright. 2005. Optimizing collective communications on SMP clusters. In 2005 International Conference on Parallel Processing (ICPP'05). IEEE, 399--407."},{"key":"e_1_3_2_2_58_1","volume-title":"Hierarchical Roofline Analysis: How to Collect Data using Performance Tools on Intel CPUs and NVIDIA GPUs. CoRR abs\/2009.02449","author":"Yang Charlene","year":"2020","unstructured":"Charlene Yang. 2020. Hierarchical Roofline Analysis: How to Collect Data using Performance Tools on Intel CPUs and NVIDIA GPUs. CoRR abs\/2009.02449 (2020). arXiv:2009.02449 https:\/\/arxiv.org\/abs\/2009.02449"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2011.5749752"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3050748.3050765"},{"key":"e_1_3_2_2_61_1","volume-title":"Parallelized stochastic gradient descent. Advances in neural information processing systems 23","author":"Zinkevich Martin","year":"2010","unstructured":"Martin Zinkevich, Markus Weimer, Lihong Li, and Alex Smola. 2010. Parallelized stochastic gradient descent. Advances in neural information processing systems 23 (2010)."}],"event":{"name":"SC '23: International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Denver CO USA","acronym":"SC '23","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","IEEE CS"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3607074","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581784.3607074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:23Z","timestamp":1750178183000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3607074"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,11]]},"references-count":60,"alternative-id":["10.1145\/3581784.3607074","10.1145\/3581784"],"URL":"https:\/\/doi.org\/10.1145\/3581784.3607074","relation":{},"subject":[],"published":{"date-parts":[[2023,11,11]]},"assertion":[{"value":"2023-11-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}