{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:00:14Z","timestamp":1776931214948,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-NA0003966, 9233218CNA000001"],"award-info":[{"award-number":["DE-NA0003966, 9233218CNA000001"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767520","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:18:44Z","timestamp":1762532324000},"page":"1611-1623","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Scalable, High-Fidelity Monitoring of Application Communication Patterns in Vernier"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7021-3077","authenticated-orcid":false,"given":"Jered","family":"Dominguez-Trujillo","sequence":"first","affiliation":[{"name":"University of New Mexico, Albuquerque, New Mexico, USA and Los Alamos National Laboratory, Los Alamos, New Mexico, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8438-5144","authenticated-orcid":false,"given":"Derek","family":"Schafer","sequence":"additional","affiliation":[{"name":"University of New Mexico, Albuquerque, New Mexico, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7486-7542","authenticated-orcid":false,"given":"Riley","family":"Shipley","sequence":"additional","affiliation":[{"name":"Tennessee Tech University, Cookeville, Tennessee, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3741-7196","authenticated-orcid":false,"given":"Ryan","family":"Marshall","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, New Mexico, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7536-9630","authenticated-orcid":false,"given":"Nicholas","family":"Bacon","sequence":"additional","affiliation":[{"name":"University of New Mexico, Albuquerque, New Mexico, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7213-089X","authenticated-orcid":false,"given":"Maxim","family":"Moraru","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, New Mexico, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6297-2145","authenticated-orcid":false,"given":"Galen","family":"Shipman","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, New Mexico, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5252-6600","authenticated-orcid":false,"given":"Anthony","family":"Skjellum","sequence":"additional","affiliation":[{"name":"Tennessee Tech University, Cookeville, Tennessee, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4801-0390","authenticated-orcid":false,"given":"Patrick","family":"Bridges","sequence":"additional","affiliation":[{"name":"University of New Mexico, Albuquerque, New Mexico, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Sandia National Laboratories. 2020. Sandia MPI Microbenchmark Suite. https:\/\/github.com\/sandialabs\/SMB"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS49563.2019.00016"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"L. Adhianto S. Banerjee M. Fagan M. Krentel G. Marin J. Mellor\u2010Crummey and N.\u00a0R. Tallent. 2010. HPCToolkit : tools for performance analysis of optimized parallel programs. Concurrency and Computation: Practice and Experience 22 6 (April 2010) 685\u2013701. 10.1002\/cpe.1553","DOI":"10.1002\/cpe.1553"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654101"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/215399.215427"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3236367.3236381"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"C.G. Baker and M.A. Heroux. 2012. Tpetra and the Use of Generic Programming in Scientific Computing. Scientific Programming 20 2 (2012) 693861. arXiv:https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.3233\/SPR-2012-034910.3233\/SPR-2012-0349","DOI":"10.3233\/SPR-2012-0349"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370223"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2009.5289198"},{"key":"e_1_3_3_2_11_2","unstructured":"Scott Beamer Krste Asanovi\u0107 and David Patterson. 2017. The GAP Benchmark Suite. arxiv:https:\/\/arXiv.org\/abs\/1508.03619\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/1508.03619"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.46"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/181014.181756"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3185768.3185771"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2009.5289150"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9774494"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624111"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575724"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"David\u00a0E Culler Richard\u00a0M Karp David Patterson Abhijit Sahay Eunice\u00a0E Santos Klaus\u00a0Erik Schauser Ramesh Subramonian and Thorsten Von\u00a0Eicken. 1996. LogP: A practical model of parallel computation. Commun. ACM 39 11 (1996) 78\u201385.","DOI":"10.1145\/240455.240477"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Tom Deakin James Price Matt Martineau and Simon McIntosh-Smith. 2018. Evaluating attainable memory bandwidth of parallel programming models via BabelStream. International Journal of Computational Science and Engineering 17 3 (2018) 247\u2013262.","DOI":"10.1504\/IJCSE.2018.095847"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2016.84"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3635035.3635036"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-92040-5_15"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC62374.2024.00023"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433746"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","unstructured":"Michael Gittings Robert Weaver Michael Clover Thomas Betlach Nelson Byrne Robert Coker Edward Dendy Robert Hueckstaedt Kim New W\u00a0Rob Oakes Dale Ranta and Ryan Stefan. 2008. The RAGE radiation-hydrodynamic code. Computational Science & Discovery 1 1 (11 2008) 015005. 10.1088\/1749-4699\/1\/1\/015005","DOI":"10.1088\/1749-4699\/1\/1\/015005"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Philipp Grete Joshua\u00a0C Dolence Jonah\u00a0M Miller Joshua Brown Ben Ryan Andrew Gaspar Forrest Glines Sriram Swaminarayan Jonas Lippuner Clell\u00a0J Solomon et\u00a0al. 2023. Parthenon\u2014a performance portable block-structured adaptive mesh refinement framework. The International Journal of High Performance Computing Applications 37 5 (2023) 465\u2013486.","DOI":"10.1177\/10943420221143775"},{"key":"e_1_3_3_2_28_2","volume-title":"Mantevo 3.0 Overview.","author":"Heroux Michael\u00a0Allen","year":"2015","unstructured":"Michael\u00a0Allen Heroux. 2015. Mantevo 3.0 Overview. Technical Report. Sandia National Lab.(SNL-NM), Albuquerque, NM (United States)."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370856"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/1851476.1851564"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Torsten Hoefler Christian Siebert and Andrew Lumsdaine. 2010. Scalable communication protocols for dynamic sparse data exchange. ACM Sigplan Notices 45 5 (2010) 159\u2013168.","DOI":"10.1145\/1837853.1693476"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3526063.3535353"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00036"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS.2018.8641622"},{"key":"e_1_3_3_2_35_2","unstructured":"Intel. 2025. Intel\u00ae VTune\u2122 Profiler. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/vtune-profiler.html. Accessed: 2025-08-08."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2013.6557149"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00037"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","unstructured":"John Kim Wiliam\u00a0J. Dally Steve Scott and Dennis Abts. 2008. Technology-Driven Highly-Scalable Dragonfly Topology. SIGARCH Comput. Archit. News 36 3 (June 2008) 77\u201388. 10.1145\/1394608.1382129","DOI":"10.1145\/1394608.1382129"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2008.19"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31476-6_7"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3422575.3422794"},{"key":"e_1_3_3_2_42_2","volume-title":"AMG2023","author":"Li Ruipeng","year":"2023","unstructured":"Ruipeng Li and Ulrike\u00a0M Yang. 2023. AMG2023. Technical Report. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)."},{"key":"e_1_3_3_2_43_2","unstructured":"Los Alamos National Laboratory. 2022. The CELL Adaptive mesh Refinement (CELLAR). https:\/\/github.com\/lanl\/CELLAR\/tree\/main"},{"key":"e_1_3_3_2_44_2","unstructured":"Los Alamos National Laboratory. 2024. ATS-5 Benchmarks Project. https:\/\/lanl.github.io\/benchmarks\/index.html Accessed: 2025-08-08."},{"key":"e_1_3_3_2_45_2","unstructured":"Andrew Mallinson David\u00a0A Beckingsale Wayne Gaudin J Herdman John Levesque and Stephen\u00a0A Jarvis. 2013. Cloverleaf: Preparing hydrodynamics codes for exascale. The Cray User Group 2013 (2013)."},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2008.87"},{"key":"e_1_3_3_2_47_2","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 (Dec. 1995) 19\u201325."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.105"},{"key":"e_1_3_3_2_49_2","volume-title":"MPI: A Message-Passing Interface Standard Version 5.0","author":"Forum Message Passing Interface","year":"2025","unstructured":"Message Passing Interface Forum. 2025. MPI: A Message-Passing Interface Standard Version 5.0. https:\/\/www.mpi-forum.org\/docs\/mpi-5.0\/mpi50-report.pdf Section 19.1.5, page 793."},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"crossref","unstructured":"Grace Nansamba Evelyn Namugwanya David Boehme Dewi Yokelson Riley Shipley Derek Schafer Michael McKinsey Olga Pearce and Anthony Skjellum. 2025. Leveraging Caliper and Benchpark to Analyze MPI Communication Patterns: Insights from AMG2023 Kripke and Laghos. arxiv:https:\/\/arXiv.org\/abs\/2507.22372\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2507.22372","DOI":"10.1109\/HPEC67600.2025.11196105"},{"key":"e_1_3_3_2_51_2","unstructured":"OSU 2025. OSU Micro-Benchmarks 7.5.1. https:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Jelena Pje\u0161ivac-Grbovi\u0107 George Bosilca Graham\u00a0E Fagg Thara Angskun and Jack\u00a0J Dongarra. 2007. MPI collective algorithm selection and quadtree encoding. Parallel Comput. 33 9 (2007) 613\u2013623.","DOI":"10.1016\/j.parco.2007.06.005"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0056559"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"crossref","unstructured":"Arun\u00a0F Rodrigues K\u00a0Scott Hemmert Brian\u00a0W Barrett Chad Kersey Ron Oldfield Marlo Weston Rolf Risen Jeanine Cook Paul Rosenfeld Elliot Cooper-Balis et\u00a0al. 2011. The structural simulation toolkit. ACM SIGMETRICS Performance Evaluation Review 38 4 (2011) 37\u201342.","DOI":"10.1145\/1964218.1964225"},{"key":"e_1_3_3_2_55_2","unstructured":"Aparna Sasidharan and Marc Snir. 2016. Miniamr-a miniapp for adaptive mesh refinement. (2016)."},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Sameer\u00a0S Shende and Allen\u00a0D Malony. 2006. The TAU parallel performance system. The International Journal of High Performance Computing Applications 20 2 (2006) 287\u2013311.","DOI":"10.1177\/1094342006064482"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"crossref","unstructured":"Cloyce\u00a0D Spradling. 2007. SPEC CPU2006 benchmark tools. ACM SIGARCH Computer Architecture News 35 1 (2007) 130\u2013134.","DOI":"10.1145\/1241601.1241625"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00066"},{"key":"e_1_3_3_2_59_2","unstructured":"Jeffrey Vetter and Chris Chambreau. 2005. mpip: Lightweight scalable mpi profiling. (2005)."},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/379539.379590"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid59990.2024.00065"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","unstructured":"Junchao Zhang Jed Brown Satish Balay Jacob Faibussowitsch Matthew Knepley Oana Marin Richard\u00a0Tran Mills Todd Munson Barry\u00a0F. Smith and Stefano Zampini. 2022. The PetscSF Scalable Communication Layer. IEEE Transactions on Parallel and Distributed Systems 33 4 (2022) 842\u2013853. 10.1109\/TPDS.2021.3084070","DOI":"10.1109\/TPDS.2021.3084070"}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3731599.3767520","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767520","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:32:48Z","timestamp":1767987168000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767520"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":61,"alternative-id":["10.1145\/3731599.3767520","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767520","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}