{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:04:46Z","timestamp":1772867086023,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T00:00:00Z","timestamp":1699660800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3581784.3607066","type":"proceedings-article","created":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T20:34:48Z","timestamp":1698698088000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Optimizing High-Performance Linpack for Exascale Accelerated Architectures"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1293-7525","authenticated-orcid":false,"given":"Noel","family":"Chalmers","sequence":"first","affiliation":[{"name":"Advanced Micro Devices, Inc, Austin, TX, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9697-0145","authenticated-orcid":false,"given":"Jakub","family":"Kurzak","sequence":"additional","affiliation":[{"name":"Advanced Micro Devices, Inc, Oak Ridge, TN, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5865-9322","authenticated-orcid":false,"given":"Damon","family":"Mcdougall","sequence":"additional","affiliation":[{"name":"Advanced Micro Devices, Inc, Austin, TX, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3513-8264","authenticated-orcid":false,"given":"Paul","family":"Bauman","sequence":"additional","affiliation":[{"name":"Advanced Micro Devices, Inc, Austin, TX, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,11,11]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1837853.1693484"},{"key":"e_1_3_2_2_2_1","volume-title":"rocHPL - High Performance Linpack for Next-Generation AMD HPC Accelerators version 6.0","author":"Rel SW","year":"2022","unstructured":"[SW Rel.] N. Chalmers, rocHPL - High Performance Linpack for Next-Generation AMD HPC Accelerators version 6.0, 2022. Advanced Micro Devices Inc. url: https:\/\/github.com\/ROCmSoftwarePlatform\/rocHPL."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"J. J. Dongarra P. Luszczek and A. Petitet. 2003. The LINPACK benchmark: past present and future. Concurrency and Computation: practice and experience 15 9 803--820.","DOI":"10.1002\/cpe.728"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3110"},{"key":"e_1_3_2_2_5_1","volume-title":"2008 IEEE International Symposium on Parallel and Distributed Processing. IEEE, 1--10","author":"Endo T.","unstructured":"T. Endo and S. Matsuoka. 2008. Massive supercomputing coping with heterogeneity of modern accelerators. In 2008 IEEE International Symposium on Parallel and Distributed Processing. IEEE, 1--10."},{"key":"e_1_3_2_2_6_1","volume-title":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS). IEEE, 1--8.","author":"Endo T.","unstructured":"T. Endo, S. Matsuoka, A. Nukada, and N. Maruyama. 2010. Linpack evaluation on a supercomputer with heterogeneous accelerators. In 2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS). IEEE, 1--8."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1513895.1513901"},{"key":"e_1_3_2_2_8_1","volume-title":"2013 IEEE 27th International Symposium on Parallel and Distributed Processing. IEEE, 126--137","author":"Heinecke A.","unstructured":"A. Heinecke, K. Vaidyanathan, M. Smelyanskiy, A. Kobotov, R. Dubtsov, G. Henry, A. G. Shet, G. Chrysos, and P. Dubey. 2013. Design and implementation of the Linpack benchmark for single and multi-node systems based on Intel\u00ae Xeon Phi coprocessor. In 2013 IEEE 27th International Symposium on Parallel and Distributed Processing. IEEE, 126--137."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2321742"},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of the 36th ACM International Conference on Supercomputing, 1--12","author":"Kim J.","unstructured":"J. Kim, H. Kwon, J. Kang, J. Park, S. Lee, and J. Lee. 2022. SnuHPL: high performance LINPACK for heterogeneous GPUs. In Proceedings of the 36th ACM International Conference on Supercomputing, 1--12."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1594835.1504212"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29400-7_35"},{"key":"e_1_3_2_2_13_1","volume-title":"Crusher Quick-Start Guide. Retrieved","author":"Leadership Computing Facility Oak Ridge","year":"2023","unstructured":"Oak Ridge Leadership Computing Facility. 2023. Crusher Quick-Start Guide. Retrieved Mar. 1, 2023 from https:\/\/docs.olcf.ornl.gov\/systems\/crusher_quick_start_guide.html."},{"key":"e_1_3_2_2_14_1","volume-title":"HPL - A Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers version 2.3","author":"Rel SW","year":"2018","unstructured":"[SW Rel.] A. Petitet, R. C. Whaley, J. Dongarra, and A. Cleary, HPL - A Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers version 2.3, 2018. Innovative Compute Laboratory. url: https:\/\/netlib.org\/benchmark\/hpl\/."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.66"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3067731"},{"key":"e_1_3_2_2_17_1","volume-title":"June Top500 list. Retrieved","year":"2022","unstructured":"Top500.org. 2022. June Top500 list. Retrieved June 1, 2022 from https:\/\/www.top500.org\/lists\/top500\/2022\/06\/."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-011-0184-1"}],"event":{"name":"SC '23: International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Denver CO USA","acronym":"SC '23","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","IEEE CS"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3607066","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581784.3607066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:23Z","timestamp":1750178183000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3607066"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,11]]},"references-count":18,"alternative-id":["10.1145\/3581784.3607066","10.1145\/3581784"],"URL":"https:\/\/doi.org\/10.1145\/3581784.3607066","relation":{},"subject":[],"published":{"date-parts":[[2023,11,11]]},"assertion":[{"value":"2023-11-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}