{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T02:30:19Z","timestamp":1768789819500,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["955606, 101033975"],"award-info":[{"award-number":["955606, 101033975"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,7]]},"DOI":"10.1145\/3605573.3605616","type":"proceedings-article","created":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T16:21:16Z","timestamp":1694622076000},"page":"295-305","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Impact of Cache Coherence on the Performance of Shared-Memory based MPI Primitives: A Case Study for Broadcast on Intel Xeon Scalable Processors"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5874-3569","authenticated-orcid":false,"given":"George","family":"Katevenis","sequence":"first","affiliation":[{"name":"Institute of Computer Science (ICS), Foundation for Research and Technology - Hellas (FORTH), Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2173-062X","authenticated-orcid":false,"given":"Manolis","family":"Ploumidis","sequence":"additional","affiliation":[{"name":"Institute of Computer Science (ICS), Foundation for Research and Technology - Hellas (FORTH), Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4768-3289","authenticated-orcid":false,"given":"Manolis","family":"Marazakis","sequence":"additional","affiliation":[{"name":"Institute of Computer Science (ICS), Foundation for Research and Technology - Hellas (FORTH), Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,9,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126954"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00014"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2009.22"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2787123"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/173682.165146"},{"key":"e_1_3_2_2_6_1","volume-title":"MPI: A Message-Passing Interface Standard. https:\/\/dl.acm.org\/doi\/10.5555\/898758","author":"Passing\u00a0Interface Forum Message","year":"1994","unstructured":"Message Passing\u00a0Interface Forum. 1994. MPI: A Message-Passing Interface Standard. https:\/\/dl.acm.org\/doi\/10.5555\/898758"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00038"},{"key":"e_1_3_2_2_8_1","volume-title":"Goodman and Hhj Hum","author":"R.","year":"2004","unstructured":"James\u00a0R. Goodman and Hhj Hum. 2004. MESIF: A Two-Hop Cache Coherency Protocol for Point-to-Point Interconnects."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2011.42"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3604-8_9"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669165"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00111"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2019.00055"},{"key":"e_1_3_2_2_14_1","volume-title":"An Analysis of Core- and Chip-Level Architectural Features in Four Generations of Intel Server Processors","author":"Hofmann Johannes","unstructured":"Johannes Hofmann, Georg Hager, Gerhard Wellein, and Dietmar Fey. 2017. An Analysis of Core- and Chip-Level Architectural Features in Four Generations of Intel Server Processors. In High Performance Computing, Julian\u00a0M. Kunkel, Rio Yokota, Pavan Balaji, and David Keyes (Eds.). Springer International Publishing, Cham, 294\u2013314."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317808"},{"key":"e_1_3_2_2_16_1","unstructured":"Intel. 2017. Intel Xeon Processor Scalable Family Technical Overview. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/xeon-processor-scalable-family-technical-overview.html"},{"key":"e_1_3_2_2_17_1","unstructured":"Intel. 2021. 3rd Gen Intel\u00ae Xeon\u00ae Processor Scalable Family Codename Ice Lake Uncore Performance Monitoring Reference Manual. https:\/\/www.intel.com\/content\/www\/us\/en\/content-details\/639778\/3rd-gen-intel-xeon-processor-scalable-family-codename-ice-lake-uncore-performance-monitoring-reference-manual.html Document ID 639778 rev. 1.0."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00032"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056045"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER51413.2022.00024"},{"key":"e_1_3_2_2_21_1","unstructured":"George Katevenis Manolis Ploumidis and Manolis Marazakis. 2023. Cache_eng: Replication & profiling of shared-memory communication patterns. https:\/\/github.com\/CARV-ICS-FORTH\/XHC-OpenMPI\/tree\/icpp-23\/cache_eng"},{"key":"e_1_3_2_2_22_1","volume-title":"US 2013\/000737","author":"Kottapalli Sailesh","year":"2013","unstructured":"Sailesh Kottapalli, Vedaraman Geetha, Henk\u00a0G. Neefs, and Youngsoo Choi. 2013. Opportunistic snoop broadcast (osb) in directory enabled home snoopy systems. https:\/\/patents.google.com\/patent\/US20130007376 Patent No. US 2013\/000737.6 A1, Filed Jul. 1st., 2011, Issued Jan. 3rd., 2013."},{"key":"e_1_3_2_2_23_1","unstructured":"Network-Based\u00a0Computing Laboratory. 2022. OSU Micro-Benchmarks. Ohio State University. https:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00013"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2011.29"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2011.30"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00021"},{"key":"e_1_3_2_2_29_1","volume-title":"Filed Sep. 25th.","author":"Moga C.","year":"2010","unstructured":"Adrian\u00a0C. Moga, Malcolm Mandviwalla, Vedaraman Geetha, and Herbert\u00a0H. Hum. 2013. Allocation and write policy for a glueless area-efficient directory cache for hotly contested cache lines. https:\/\/patents.google.com\/patent\/US8392665B2 Patent No. US 8,392.665 B2, Filed Sep. 25th., 2010, Issued Mar. 5th., 2013."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2015.83"},{"key":"e_1_3_2_2_31_1","volume-title":"Filed Sep. 26th.","author":"Pal Rahul","year":"2014","unstructured":"Rahul Pal, Ishwar AGARWAL, Yen-Cheng Liu, Joseph Nuzman, Ashok Jagannathan, Bahaa Fahim, and Nithiyanandan Bashyam. 2017. Method and apparatus for distributed snoop filtering. https:\/\/patents.google.com\/patent\/US9727475B2 Patent No. US 9,727.475 B2, Filed Sep. 26th., 2014, Issued Aug. 8th., 2017."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2516540"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.30"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2017.08.004"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.24"},{"key":"e_1_3_2_2_36_1","volume-title":"Designing Non-blocking Personalized Collectives with Near Perfect Overlap for RDMA-Enabled Clusters","author":"Subramoni Hari","unstructured":"Hari Subramoni, Ammar\u00a0Ahmad Awan, Khaled Hamidouche, Dmitry Pekurovsky, Akshay Venkatesh, Sourav Chakraborty, Karen Tomko, and Dhabaleswar\u00a0K. Panda. 2015. Designing Non-blocking Personalized Collectives with Near Perfect Overlap for RDMA-Enabled Clusters. In High Performance Computing, Julian\u00a0M. Kunkel and Thomas Ludwig (Eds.). Springer International Publishing, Cham, 434\u2013453."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2616498.2616532"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00004"}],"event":{"name":"ICPP 2023: 52nd International Conference on Parallel Processing","location":"Salt Lake City UT USA","acronym":"ICPP 2023"},"container-title":["Proceedings of the 52nd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605573.3605616","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605573.3605616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:04Z","timestamp":1750182544000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605573.3605616"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":37,"alternative-id":["10.1145\/3605573.3605616","10.1145\/3605573"],"URL":"https:\/\/doi.org\/10.1145\/3605573.3605616","relation":{},"subject":[],"published":{"date-parts":[[2023,8,7]]},"assertion":[{"value":"2023-09-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}