{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T13:58:13Z","timestamp":1764251893413,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T00:00:00Z","timestamp":1721174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-23-1-0232"],"award-info":[{"award-number":["FA9550-23-1-0232"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1925764, 2112356"],"award-info":[{"award-number":["1925764, 2112356"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,17]]},"DOI":"10.1145\/3626203.3670540","type":"proceedings-article","created":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T20:12:20Z","timestamp":1721247140000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Impact of Memory Bandwidth on the Performance of Accelerators"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9518-5890","authenticated-orcid":false,"given":"Sambit","family":"Mishra","sequence":"first","affiliation":[{"name":"Department of Ocean Engineering, Texas A&M University, PhD candidate, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7739-3701","authenticated-orcid":false,"given":"Dhruva K.","family":"Chakravorty","sequence":"additional","affiliation":[{"name":"High Performance Research Computing, Texas A&M University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1176-1027","authenticated-orcid":false,"given":"Lisa M.","family":"Perez","sequence":"additional","affiliation":[{"name":"High Performance Research Computing, Texas A&M University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9494-7639","authenticated-orcid":false,"given":"Francis","family":"Dang","sequence":"additional","affiliation":[{"name":"High Performance Research Computing, Texas A&M University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2942-9014","authenticated-orcid":false,"given":"Honggao","family":"Liu","sequence":"additional","affiliation":[{"name":"High Performance Research Computing, Texas A&M University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2343-412X","authenticated-orcid":false,"given":"Freddie David","family":"Witherden","sequence":"additional","affiliation":[{"name":"Department of Ocean Engineering, Texas A&M University, Texas A&M University, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,7,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compfluid.2021.104935"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2021.108193"},{"key":"e_1_3_2_1_3_1","unstructured":"BabelSTREAM for benchmarking memory bandwidth 2024.. Retrieved March 8 2024 from https:\/\/github.com\/uob-hpc\/babelstream"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Wesley\u00a0A. Brashear Lisa\u00a0M. Perez Elizabeth Leake Sandra\u00a0B. Nite Marinus Pennings Sheri Stebenne Honggao Liu and Dhruva\u00a0K. Chakravorty.2024. Cultivating Cyberinfrastructure Careers through Student Engagement at Texas A&M University High Performance Research Computing.. In Practice and Experience in Advanced Research Computing(PEARC \u201924). ACM.","DOI":"10.1145\/3626203.3670544"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/mm.2023.3256796"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.2514\/6.2007-4079"},{"key":"e_1_3_2_1_7_1","unstructured":"Intel Data Center GPU MAX 1100 Specifications 2024.. Retrieved Feb 22 2024 from https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/232876\/intel-data-center-gpu-max-1100\/specifications.html"},{"key":"e_1_3_2_1_8_1","unstructured":"Intel Data Center GPU MAX Series 2024.. Retrieved March 8 2024 from https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/intel-data-center-gpu-max-series-overview.html"},{"key":"e_1_3_2_1_9_1","unstructured":"Intel Data Center GPU MAX Series Technical Overview 2024.. Retrieved March 5 2024 from https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/discrete-gpus\/data-center-gpu\/max-series.html"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Richard Lawrence Dhruva\u00a0K. Chakravorty Lisa\u00a0M. Perez Wesley\u00a0A. Brashear Zhenhua He and Joshua Winchell.2024. Container Adoption in Campus High Performance Computing.. In Practice and Experience in Advanced Research Computing(PEARC \u201924). ACM.","DOI":"10.1145\/3626203.3670550"},{"key":"e_1_3_2_1_11_1","unstructured":"Hieu\u00a0T. Le Zhenhua He Mai Le Dhruva\u00a0K. Chakravorty Akhil Chilumuru Yan Yao and Jiefu Chen. 2024. Performance Benchmarking and Lessons Learned from Porting AI\/ML Workloads to Intelligence Processing Units. In Practice and Experience in Advanced Research Computing(PEARC \u201924). ACM."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Sambit Mishra Freddie Witherden Dhruva Chakravorty Lisa Perez and Francis Dang. 2023. Scaling Study of Flow Simulations on Composable Cyberinfrastructure. In Practice and Experience in Advanced Research Computing(PEARC \u201923). ACM. https:\/\/doi.org\/10.1145\/3569951.3597565","DOI":"10.1145\/3569951.3597565"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"Abhinand Nasari Lujun Zhai Zhenhua He Hieu Le Suxia Cui Dhruva Chakravorty Jian Tao and Honggao Liu. 2023. Porting AI\/ML Models to Intelligence Processing Units (IPUs). In Practice and Experience in Advanced Research Computing(PEARC \u201923). ACM. https:\/\/doi.org\/10.1145\/3569951.3603632","DOI":"10.1145\/3569951.3603632"},{"key":"e_1_3_2_1_14_1","volume-title":"ACES - Accelerating Computing for Emerging Sciences","author":"NSF","year":"2024","unstructured":"NSF Category II: ACES - Accelerating Computing for Emerging Sciences 2024.. Retrieved March 6, 2024 from https:\/\/hprc.tamu.edu\/aces\/"},{"key":"e_1_3_2_1_15_1","volume-title":"Retrieved","author":"NVIDIA","year":"2024","unstructured":"NVIDIA cuBLASLt library user guide 2024.. Retrieved Feb 24, 2024 from https:\/\/docs.nvidia.com\/cuda\/cublas\/index.html#using-the-cublaslt-api"},{"key":"e_1_3_2_1_16_1","unstructured":"NVIDIA H100 Specifications 2024.. Retrieved Feb 16 2024 from https:\/\/resources.nvidia.com\/en-us-tensor-core"},{"key":"e_1_3_2_1_17_1","unstructured":"Paper data and results 2024.. Retrieved June 7 2024 from https:\/\/github.com\/sambitmishra98\/GiMMiK-profiling-on-GPU.git"},{"volume-title":"Retrieved","year":"2024","key":"e_1_3_2_1_18_1","unstructured":"PyFR branch with functionality to choose specific kernels 2024.. Retrieved Jun 12, 2024 from https:\/\/github.com\/sambitmishra98\/PyFR.git"},{"key":"e_1_3_2_1_19_1","unstructured":"Python scripts to create GMSH 2024.. Retrieved March 7 2024 from https:\/\/github.com\/WillTrojak\/basic_gmsh.git"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2020.107169"},{"key":"e_1_3_2_1_21_1","unstructured":"Single-GPU test scripts 2024.. Retrieved March 7 2024 from https:\/\/github.com\/sambitmishra98\/benchmark"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.1937.0036"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.1"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/fld.3767"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2014.07.011"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","unstructured":"F.D. Witherden B.C. Vermeire and P.E. Vincent. 2015. Heterogeneous computing on mixed unstructured grids with PyFR. Computers and Fluids 120 (Oct. 2015) 173\u2013186. https:\/\/doi.org\/10.1016\/j.compfluid.2015.07.016","DOI":"10.1016\/j.compfluid.2015.07.016"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/mcse.2021.3080126"}],"event":{"name":"PEARC '24: Practice and Experience in Advanced Research Computing","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"],"location":"Providence RI USA","acronym":"PEARC '24"},"container-title":["Practice and Experience in Advanced Research Computing 2024: Human Powered Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626203.3670540","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626203.3670540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:56:32Z","timestamp":1755867392000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626203.3670540"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,17]]},"references-count":27,"alternative-id":["10.1145\/3626203.3670540","10.1145\/3626203"],"URL":"https:\/\/doi.org\/10.1145\/3626203.3670540","relation":{},"subject":[],"published":{"date-parts":[[2024,7,17]]},"assertion":[{"value":"2024-07-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}