{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T09:19:30Z","timestamp":1773825570924,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T00:00:00Z","timestamp":1748908800000},"content-version":"vor","delay-in-days":369,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Department of Energy","award":["17-SC-20-SC"],"award-info":[{"award-number":["17-SC-20-SC"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3650200.3656591","type":"proceedings-article","created":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T14:11:54Z","timestamp":1717423914000},"page":"426-436","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["CommBench: Micro-Benchmarking Hierarchical Networks with Multi-GPU, Multi-NIC Nodes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9276-5075","authenticated-orcid":false,"given":"Mert","family":"Hidayetoglu","sequence":"first","affiliation":[{"name":"Stanford University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5699-1793","authenticated-orcid":false,"given":"Simon Garcia","family":"De Gonzalo","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9725-1305","authenticated-orcid":false,"given":"Elliott","family":"Slaughter","sequence":"additional","affiliation":[{"name":"SLAC National Accelerator Laboratory, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4962-2913","authenticated-orcid":false,"given":"Yu","family":"Li","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5054-4354","authenticated-orcid":false,"given":"Christopher","family":"Zimmer","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8428-5159","authenticated-orcid":false,"given":"Tekin","family":"Bicer","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4116-5237","authenticated-orcid":false,"given":"Bin","family":"Ren","sequence":"additional","affiliation":[{"name":"William & Mary, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2905-3029","authenticated-orcid":false,"given":"William","family":"Gropp","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2532-5349","authenticated-orcid":false,"given":"Wen-Mei","family":"Hwu","sequence":"additional","affiliation":[{"name":"Nvidia Research, USA and University of Illinois at Urbana-Champaign, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3723-9555","authenticated-orcid":false,"given":"Alex","family":"Aiken","sequence":"additional","affiliation":[{"name":"Stanford University, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,6,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[1] [n. d.]. https:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2009.5289198"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342020925535"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622742"},{"key":"e_1_3_2_1_5_1","unstructured":"National Energy Research Scientific\u00a0Computing Center. 2022. Perlmutter Architecture. https:\/\/docs.nersc.gov\/systems\/perlmutter\/architecture\/"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356215"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433747"},{"key":"e_1_3_2_1_8_1","unstructured":"Argonne Leadership\u00a0Computing Facility. 2022. Aurora. https:\/\/www.alcf.anl.gov\/support-center\/aurora-sunspot"},{"key":"e_1_3_2_1_9_1","unstructured":"Oak Ridge Leadership\u00a0Computing Facility. 2022. Frontier User Guide - System Overview. https:\/\/docs.olcf.ornl.gov\/systems\/frontier_user_guide.html#id2"},{"key":"e_1_3_2_1_10_1","unstructured":"National\u00a0Center for Supercomputing\u00a0Applications. 2022. Delta. https:\/\/www.ncsa.illinois.edu\/research\/project-highlights\/delta\/"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.006"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"William Gropp and Ewing Lusk. 1996. User\u2019s Guide for MPICH a Portable Implementation of MPI.","DOI":"10.2172\/378911"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2966884.2966919"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2019.01.001"},{"key":"e_1_3_2_1_16_1","volume-title":"SC20: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, 1\u201313","author":"Hidayeto\u011flu Mert","year":"2020","unstructured":"Mert Hidayeto\u011flu, Tekin Bicer, Simon\u00a0Garcia De\u00a0Gonzalo, Bin Ren, Vincent De\u00a0Andrade, 2020. Petascale XCT: 3D image reconstruction with hierarchical communications on multi-GPU nodes. In SC20: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, 1\u201313."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3128032"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75444-2_62"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS.2005.32"},{"key":"e_1_3_2_1_20_1","unstructured":"IBM. 2017. IBM Spectrum MPI - Overview. https:\/\/www.ibm.com\/products\/spectrum-mpi"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/3014904.3014923"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1394608.1382129"},{"key":"e_1_3_2_1_23_1","volume-title":"Performance analysis and optimal node-aware communication for enlarged conjugate gradient methods. ACM Transactions on Parallel Computing","author":"Lockhart Shelby","year":"2022","unstructured":"Shelby Lockhart, Amanda Bienz, William Gropp, and Luke Olson. 2022. Performance analysis and optimal node-aware communication for enlarged conjugate gradient methods. ACM Transactions on Parallel Computing (2022)."},{"key":"e_1_3_2_1_24_1","volume-title":"Characterizing the Performance of Node-Aware Strategies for Irregular Point-to-Point Communication on Heterogeneous Architectures. arXiv:2209.06141","author":"Lockhart Shelby","year":"2022","unstructured":"Shelby Lockhart, Amanda Bienz, William\u00a0D Gropp, and Luke\u00a0N Olson. 2022. Characterizing the Performance of Node-Aware Strategies for Irregular Point-to-Point Communication on Heterogeneous Architectures. arXiv:2209.06141 (2022)."},{"key":"e_1_3_2_1_25_1","volume-title":"Contention-free routing for shift-based communication in MPI applications on large-scale InfiniBand clusters","author":"Moody Adam","unstructured":"Adam Moody. 2009. Contention-free routing for shift-based communication in MPI applications on large-scale InfiniBand clusters. Technical Report. Lawrence Livermore National Lab.(LLNL), Livermore, CA (United States)."},{"key":"e_1_3_2_1_26_1","unstructured":"Samuel\u00a0K. Moore. 2022. Behind Intel\u2019s HPC chip that will break the exascale barrier. https:\/\/spectrum.ieee.org\/intel-s-exascale-supercomputer-chip-is-a-master-class-in-3d-integration"},{"key":"e_1_3_2_1_27_1","unstructured":"NVIDIA. 2016. NVIDIA Collective Communications Library (NCCL). https:\/\/developer.nvidia.com\/nccl"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2007.1065"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2020.101208"},{"key":"e_1_3_2_1_30_1","volume-title":"Interconnect Bandwidth Heterogeneity on AMD MI250x and Infinity Fabric. arXiv:2302.14827","author":"Pearson Carl","year":"2023","unstructured":"Carl Pearson. 2023. Interconnect Bandwidth Heterogeneity on AMD MI250x and Infinity Fabric. arXiv:2302.14827 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297663.3310299"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1155\/2002\/202839"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330357"},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Supercomputing, Vol.\u00a02000","author":"Shroff Mohak","year":"1999","unstructured":"Mohak Shroff and Robert\u00a0A Van De\u00a0Geijn. 1999. CollMark: MPI collective communication benchmark. In International Conference on Supercomputing, Vol.\u00a02000. 10."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624203"},{"key":"e_1_3_2_1_36_1","volume-title":"Euro-Par 2021: Parallel Processing Workshops: Euro-Par 2021 International Workshops","author":"Soyt\u00fcrk Muhammet\u00a0Abdullah","year":"2021","unstructured":"Muhammet\u00a0Abdullah Soyt\u00fcrk, Palwisha Akhtar, Erhan Tezcan, and Didem Unat. 2022. Monitoring collective communication among GPUs. In Euro-Par 2021: Parallel Processing Workshops: Euro-Par 2021 International Workshops, Lisbon, Portugal, August 30-31, 2021, Revised Selected Papers. Springer, 41\u201352."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00055"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356166"}],"event":{"name":"ICS '24: 2024 International Conference on Supercomputing","location":"Kyoto Japan","acronym":"ICS '24","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 38th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650200.3656591","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3650200.3656591","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3650200.3656591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:24:57Z","timestamp":1755876297000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650200.3656591"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":38,"alternative-id":["10.1145\/3650200.3656591","10.1145\/3650200"],"URL":"https:\/\/doi.org\/10.1145\/3650200.3656591","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}