{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T02:26:35Z","timestamp":1768011995195,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":29,"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\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2323116"],"award-info":[{"award-number":["2323116"]}],"id":[{"id":"10.13039\/100000001","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\/3731599.3767704","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:20:02Z","timestamp":1762532402000},"page":"1442-1451","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Peak Performance Model for All-to-all on Hierarchical Systems and Its Applications"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0583-6109","authenticated-orcid":false,"given":"Rohini","family":"Uma-Vaideswaran","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1358-5565","authenticated-orcid":false,"given":"Joshua","family":"Romero","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation, Santa Clara, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6209-809X","authenticated-orcid":false,"given":"Daniel L.","family":"Dotson","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1433-9198","authenticated-orcid":false,"given":"David","family":"Appelhans","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation, Westminster, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6278-6032","authenticated-orcid":false,"given":"P. K.","family":"Yeung","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/215399.215427"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607089"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2003.1213106"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS.2016.007"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Pedro Costa. 2018. A FFT-based finite-difference solver for massively-parallel direct numerical simulations of turbulent flows. Computers and Mathematics with Applications 76 8 (2018) 1853\u20131862. 10.1016\/j.camwa.2018.07.034","DOI":"10.1016\/j.camwa.2018.07.034"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/155332.155333"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00039"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Roger\u00a0W Hockney. 1994. The communication challenge for MPP: Intel Paragon and Meiko CS-2. Parallel computing 20 3 (1994) 389\u2013398.","DOI":"10.1016\/S0167-8191(06)80021-9"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15646-5_3"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Torsten Hoefler Timo Schneider and Andrew Lumsdaine. 2009. Loggp in theory and practice\u2013an in-depth analysis of modern interconnection networks and benchmarking methods for collective operations. Simulation Modelling Practice and Theory 17 9 (2009) 1511\u20131521.","DOI":"10.1016\/j.simpat.2009.06.007"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.13"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45591-4_162"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/301104.301116"},{"key":"e_1_3_3_2_15_2","unstructured":"NVIDIA. 2025. Blackwell Datasheet [Online]. Available: https:\/\/nvdam.widen.net\/s\/wwnsxrhm2w\/blackwell-datasheet-3384703. (Accessed: 11 August 2025)."},{"key":"e_1_3_3_2_16_2","unstructured":"NVIDIA. 2025. High Performance Computing HPC SDK Online]. Available: https:\/\/developer.nvidia.com\/hpc-sdk. (Accessed: 11 August 2025)."},{"key":"e_1_3_3_2_17_2","unstructured":"NVIDIA. 2025. NVIDIA Collective Communications Library (NCCL) [Online]. Available: https:\/\/developer.nvidia.com\/nccl. (Accessed: 11 August 2025)."},{"key":"e_1_3_3_2_18_2","unstructured":"NVIDIA. 2025. NVSHMEM [Online]. Available: https:\/\/developer.nvidia.com\/nvshmem. (Accessed: 11 August 2025)."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Dhabaleswar\u00a0Kumar Panda Hari Subramoni Ching-Hsiang Chu and Mohammadreza Bayatpour. 2021. The MVAPICH project: Transforming research into high-performance MPI library for HPC community. Journal of Computational Science 52 (2021) 101208. 10.1016\/j.jocs.2020.101208Case Studies in Translational Computer Science.","DOI":"10.1016\/j.jocs.2020.101208"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Jelena Pje\u0161ivac-Grbovi\u0107 Thara Angskun George Bosilca Graham\u00a0E Fagg Edgar Gabriel and Jack\u00a0J Dongarra. 2007. Performance analysis of MPI collective operations. Cluster Computing 10 2 (2007) 127\u2013143.","DOI":"10.1007\/s10586-007-0012-0"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356209"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Juan\u00a0A Rico-Gallego Juan\u00a0C D\u00edaz-Mart\u00edn Ravi\u00a0Reddy Manumachu and Alexey\u00a0L Lastovetsky. 2019. A survey of communication performance models for high-performance computing. ACM Computing Surveys (CSUR) 51 6 (2019) 1\u201336.","DOI":"10.1145\/3284358"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"A. Roccon L. Enzenberger D. Zaza and A. Soldati. 2025. MHIT36: A Phase-Field Code for Gpu Simulations of Multiphase Homogeneous Isotropic Turbulence. Computer Physics Communications (in press) (2025). 10.2139\/ssrn.5264052","DOI":"10.2139\/ssrn.5264052"},{"key":"e_1_3_3_2_24_2","volume-title":"Numerical experiments in homogeneous turbulence","author":"Rogallo R.\u00a0S.","year":"1981","unstructured":"R.\u00a0S. Rogallo. 1981. Numerical experiments in homogeneous turbulence. NASA TM 81315. NASA Ames Research Center, Moffett Field, CA."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539781.3539797"},{"key":"e_1_3_3_2_26_2","unstructured":"Swiss National Supercomputing Centre. 2025. User Guides [Online]. Available: https:\/\/confluence.cscs.ch\/spaces\/KB\/pages\/847908761\/User+Guides. (Accessed: 11 August 2025)."},{"key":"e_1_3_3_2_27_2","unstructured":"Texas Advanced Computing Center. 2025. Vista User Guide [Online]. Available: https:\/\/docs.tacc.utexas.edu\/hpc\/vista\/. (Accessed: 11 August 2025)."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-39924-7_38"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","unstructured":"Maochao Xiao Alessandro Ceci Pedro Costa Johan Larsson and Sergio Pirozzoli. 2025. CaLES: A GPU-accelerated solver for large-eddy simulation of wall-bounded flows. Computer Physics Communications 310 (2025) 109546. 10.1016\/j.cpc.2025.109546","DOI":"10.1016\/j.cpc.2025.109546"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"P.\u00a0K. Yeung Kiran Ravikumar Stephen Nichols and Rohini Uma-Vaideswaran. 2025. GPU-enabled extreme-scale turbulence simulations: Fourier pseudo-spectral algorithms at the exascale using OpenMP offloading. Computer Physics Communications 306:109364 (2025).","DOI":"10.1016\/j.cpc.2024.109364"}],"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\/3731599.3767704","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767704","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:35:31Z","timestamp":1767987331000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767704"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":29,"alternative-id":["10.1145\/3731599.3767704","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767704","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"}}]}}