{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T07:55:24Z","timestamp":1773820524206,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"vor","delay-in-days":366,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Department of Energy"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3624062.3624203","type":"proceedings-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T13:53:39Z","timestamp":1699624419000},"page":"1298-1305","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Latency and Bandwidth Microbenchmarks of US Department of Energy Systems in the June 2023 Top 500 List"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2116-125X","authenticated-orcid":false,"given":"Christopher M","family":"Siefert","sequence":"first","affiliation":[{"name":"Sandia National Laboratories, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6481-970X","authenticated-orcid":false,"given":"Carl","family":"Pearson","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6247-8980","authenticated-orcid":false,"given":"Stephen L.","family":"Olivier","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3616-5504","authenticated-orcid":false,"given":"Andrey","family":"Prokopenko","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4636-3619","authenticated-orcid":false,"given":"Jonathan","family":"Hu","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5781-626X","authenticated-orcid":false,"given":"Timothy J.","family":"Fuller","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,11,12]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2017. NVIDIA Tesla V100 GPU Architecture. https:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/volta-architecture-whitepaper.pdf"},{"key":"e_1_3_2_2_2_1","unstructured":"2018. HPL - A Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers. https:\/\/www.netlib.org\/benchmark\/hpl"},{"key":"e_1_3_2_2_3_1","unstructured":"2020. NVIDIA A100 Tensor Core GPU Architecture. https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf"},{"key":"e_1_3_2_2_4_1","unstructured":"2021. Introducing AMD CDNA 2 Architecture. https:\/\/www.amd.com\/system\/files\/documents\/amd-cdna2-white-paper.pdf"},{"key":"e_1_3_2_2_5_1","unstructured":"2021. mpi-benchmarks. https:\/\/github.com\/intel\/mpi-benchmarks"},{"key":"e_1_3_2_2_6_1","unstructured":"2022. BenchPress. https:\/\/github.com\/bienz2\/BenchPress"},{"key":"e_1_3_2_2_7_1","unstructured":"2022. HPCG Benchmark. https:\/\/www.hpcg-benchmark.org\/"},{"key":"e_1_3_2_2_8_1","unstructured":"2023. alcf-mpi-benchmarks. https:\/\/github.com\/argonne-lcf\/alcf-mpi-benchmarks"},{"key":"e_1_3_2_2_9_1","unstructured":"2023. AMD Instinct MI250X Accelerator. https:\/\/www.amd.com\/en\/products\/server-accelerators\/instinct-mi250x"},{"key":"e_1_3_2_2_10_1","unstructured":"2023. benchmark. http:\/\/github.com\/google\/benchmark"},{"key":"e_1_3_2_2_11_1","unstructured":"2023. Frontier User Guide. https:\/\/docs.olcf.ornl.gov\/systems\/frontier_user_guide.html"},{"key":"e_1_3_2_2_12_1","unstructured":"2023. Intel Xeon Gold 6154 Processor. https:\/\/ark.intel.com\/content\/www\/us\/en\/ark\/products\/120495\/intel-xeon-gold-6154-processor-24-75m-cache-3-00-ghz.html"},{"key":"e_1_3_2_2_13_1","unstructured":"2023. Intel Xeon Platinum 8268 Processor. https:\/\/ark.intel.com\/content\/www\/us\/en\/ark\/products\/192481\/intel-xeon-platinum-8268-processor-35-75m-cache-2-90-ghz.html"},{"key":"e_1_3_2_2_14_1","unstructured":"2023. OSU Micro-benchmarks. http:\/\/mvapich.cse.ohio- state.edu\/benchmarks\/"},{"key":"e_1_3_2_2_15_1","unstructured":"2023. Perlmutter Architecture. https:\/\/docs.nersc.gov\/systems\/perlmutter\/architecture\/"},{"key":"e_1_3_2_2_16_1","unstructured":"2023. Summit User Guide. https:\/\/docs.olcf.ornl.gov\/systems\/summit_user_guide.html"},{"key":"e_1_3_2_2_17_1","unstructured":"2023. TOP500 June 2023. https:\/\/www.top500.org\/lists\/top500\/2023\/06\/"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/125826.125925"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2003.1213106"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503247"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33518-1_16"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Paul\u00a0Stewart Crozier Heidi\u00a0K Thornquist Robert\u00a0W Numrich Alan\u00a0B Williams Harold\u00a0Carter Edwards Eric\u00a0Richard Keiter Mahesh Rajan James\u00a0M Willenbring Douglas\u00a0W Doerfler and Michael\u00a0Allen Heroux. 2009. Improving Performance via Mini-Applications.Technical Report SAND2009-5574. Sandia National Laboratories. https:\/\/www.osti.gov\/biblo\/993908.","DOI":"10.2172\/993908"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1504\/IJCSE.2018.095847"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2018.05.006"},{"key":"e_1_3_2_2_25_1","volume-title":"Efficient Intranode Communication in GPU-accelerated Systems. In 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops. IEEE","author":"Ji Feng","year":"2012","unstructured":"Feng Ji, Ashwin\u00a0M Aji, James Dinan, Darius Buntinas, Pavan Balaji, Wu-chun Feng, and Xiaosong Ma. 2012. Efficient Intranode Communication in GPU-accelerated Systems. In 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops. IEEE, 1838\u20131847."},{"key":"e_1_3_2_2_26_1","volume-title":"Performance Evaluation of MPI Libraries on GPU-enabled OpenPOWER Architectures: Early Experiences. In High Performance Computing: ISC High Performance 2019 International Workshops","author":"Khorassani Kawthar\u00a0Shafie","year":"2019","unstructured":"Kawthar\u00a0Shafie Khorassani, Ching-Hsiang Chu, Hari Subramoni, and Dhabaleswar\u00a0K Panda. 2019. Performance Evaluation of MPI Libraries on GPU-enabled OpenPOWER Architectures: Early Experiences. In High Performance Computing: ISC High Performance 2019 International Workshops, Frankfurt, Germany, June 16-20, 2019, Revised Selected Papers 34. Springer, 361\u2013378."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573483"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2004.1268994"},{"key":"e_1_3_2_2_30_1","unstructured":"John\u00a0D McCalpin. 1995. Sustainable Memory Bandwidth in Current High Performance Computers. (1995). https:\/\/www.cs.virginia.edu\/\u00a0mccalpin\/papers\/bandwidth\/bandwidth.html"},{"key":"e_1_3_2_2_31_1","first-page":"19","article-title":". Memory Bandwidth and Machine Balance in Current High Performance Computers","volume":"2","author":"McCalpin D","year":"1995","unstructured":"John\u00a0D McCalpin 1995. Memory Bandwidth and Machine Balance in Current High Performance Computers. IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter 2, 19-25 (1995).","journal-title":"IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297663.3310299"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Mahesh Rajan Doug Doerfler and Simon Hammond. 2015. Trinity Benchmarks on Intel Xeon Phi (Knights Corner). Technical Report SAND2015-0454C. Sandia National Laboratories. https:\/\/www.osti.gov\/biblo\/1504115.","DOI":"10.2172\/1504115"},{"key":"e_1_3_2_2_34_1","volume-title":"Knights landing: Second-generation intel xeon phi product. Ieee micro 36, 2","author":"Sodani Avinash","year":"2016","unstructured":"Avinash Sodani, Roger Gramunt, Jesus Corbal, Ho-Seop Kim, Krishna Vinod, Sundaram Chinthamani, Steven Hutsell, Rajat Agarwal, and Yen-Chen Liu. 2016. Knights landing: Second-generation intel xeon phi product. Ieee micro 36, 2 (2016), 34\u201346."},{"key":"e_1_3_2_2_35_1","unstructured":"N Wichmann C Nuss P Carrier R Olson S Anderson M Davis R Baker E Draeger S Domino A Agelastos and M Rajan. 2015. Performance on Trinity (a Cray XC40) with Acceptance-Applications and Benchmarks. Technical Report SAND2016-3635C. Sandia National Laboratories. https:\/\/www.osti.gov\/biblio\/1365199."}],"event":{"name":"SC-W 2023: Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis","location":"Denver CO USA","acronym":"SC-W 2023"},"container-title":["Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624203","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624062.3624203","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624062.3624203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T03:05:11Z","timestamp":1755745511000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624203"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,12]]},"references-count":35,"alternative-id":["10.1145\/3624062.3624203","10.1145\/3624062"],"URL":"https:\/\/doi.org\/10.1145\/3624062.3624203","relation":{},"subject":[],"published":{"date-parts":[[2023,11,12]]},"assertion":[{"value":"2023-11-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}