{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:55:26Z","timestamp":1776930926307,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":27,"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":[{"name":"DOE","award":[""],"award-info":[{"award-number":[""]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3712285.3759875","type":"proceedings-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T16:04:47Z","timestamp":1762963487000},"page":"397-410","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Insights from Optimizing HPL Performance on Exascale Systems: A Comparative Analysis of Panel Factorization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8941-870X","authenticated-orcid":false,"given":"Hao","family":"Lu","sequence":"first","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1512-5255","authenticated-orcid":false,"given":"Michael","family":"Matheson","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1293-7525","authenticated-orcid":false,"given":"Noel","family":"Chalmers","sequence":"additional","affiliation":[{"name":"Advanced Micro Devices, Inc. (AMD), Austin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2589-3792","authenticated-orcid":false,"given":"Aditya","family":"Kashi","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6259-7453","authenticated-orcid":false,"given":"Nicholas","family":"Malaya","sequence":"additional","affiliation":[{"name":"Advanced Micro Devices, Inc. (AMD), Austin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0099-1559","authenticated-orcid":false,"given":"Feiyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2025. TOP500 Supercomputer Sites. TOP500.org"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","unstructured":"Ahmad Abdelfattah Natalie Beams Robert Carson Pieter Ghysels Tzanio Kolev Thomas Stitt Arturo Vargas Stanimire Tomov and Jack Dongarra. 2024. MAGMA: Enabling exascale performance with accelerated BLAS and LAPACK for diverse GPU architectures. The International Journal of High Performance Computing Applications (2024-06 2024). 10.1177\/10943420241261960","DOI":"10.1177\/10943420241261960"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Ahmad Abdelfattah Azzam Haidar Stanimire Tomov and Jack Dongarra. 2018. Analysis and Design Techniques towards High-Performance and Energy-Efficient Dense Linear Solvers on GPUs. IEEE Transactions on Parallel and Distributed Systems 29 (2018-12 2018) 2700\u20132712. 10.1109\/TPDS.2018.2842785","DOI":"10.1109\/TPDS.2018.2842785"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607089"},{"key":"e_1_3_3_2_6_2","unstructured":"Linear\u00a0Solvers Basics. 2005. Intel\u00ae Math Kernel Library. (2005)."},{"key":"e_1_3_3_2_7_2","volume-title":"Introduction to AMD GPU Programming with HIP","author":"Bauman Paul","unstructured":"Paul Bauman and et al.[n. d.]. Introduction to AMD GPU Programming with HIP. https:\/\/www.olcf.ornl.gov\/calendar\/intro-to-amd-gpu-programming-with-hip\/"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607066"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Jaeyoung Choi James Demmel Inderjiit Dhillon Jack Dongarra Susan Ostrouchov Antoine Petitet Ken Stanley David Walker and R\u00a0Clinton Whaley. 1996. ScaLAPACK: A portable linear algebra library for distributed memory computers\u2014Design issues and performance. Computer Physics Communications 97 1-2 (1996) 1\u201315.","DOI":"10.1016\/0010-4655(96)00017-3"},{"key":"e_1_3_3_2_10_2","unstructured":"Intel Corporation. 2025. Intel Math Kernel Library (MKL). https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/oneapi-math-kernel-library.html Accessed: 2025-04-08."},{"key":"e_1_3_3_2_11_2","volume-title":"ROCm Communication Collectives Library","author":"Devices Advanced\u00a0Micro","year":"2022","unstructured":"Advanced\u00a0Micro Devices. 2022. ROCm Communication Collectives Library. https:\/\/github.com\/rocm\/rccl"},{"key":"e_1_3_3_2_12_2","unstructured":"\"Advanced\u00a0Micro Devices. 2025. AOCL-BLAS library. https:\/\/github.com\/amd\/blis Accessed: 2025-04-08."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.5555\/898688"},{"key":"e_1_3_3_2_14_2","volume-title":"Frontier User Guide","author":"Facility Oak Ridge Leadership\u00a0Computing","unstructured":"Oak Ridge Leadership\u00a0Computing Facility. [n. d.]. Frontier User Guide. https:\/\/docs.olcf.ornl.gov\/systems\/frontier_user_guide.html"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Mark Gates Ahmad Abdelfattah Kadir Akbudak Mohammed Al\u00a0Farhan Rabab Alomairy Daniel Bielich Treece Burgess Sebastien Cayrols Neil Lindquist Dalal Sukkari and Asim YarKhan. 2024. Evolution of the SLATE linear algebra library. The International Journal of High Performance Computing Applications (2024-09 2024). 10.1177\/10943420241286531","DOI":"10.1177\/10943420241286531"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532370"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Woody Lichtenstein and S.\u00a0Lennart Johnsson. 1993. Block-cyclic dense linear algebra. SIAM Journal of Scientific Computing 14 6 (1993) 1259\u20131288.","DOI":"10.1137\/0914075"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607030"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00083"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3615318.3615327"},{"key":"e_1_3_3_2_22_2","unstructured":"Rajib Nath Jack Dongarra Stanimire Tomov Hatem Ltaeif and Peng Du. 2009. Numerical Linear Algebra on Hybrid Architectures: Recent Developments in the MAGMA Project. (2009-11 2009)."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","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.","DOI":"10.1016\/j.jocs.2020.101208"},{"key":"e_1_3_3_2_24_2","volume-title":"HPL - A Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers","author":"Petitet A.","year":"2018","unstructured":"A. Petitet, R.\u00a0C. Whaley, J. Dongarra, and A. Cleary. 2018. HPL - A Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers. https:\/\/netlib.org\/benchmark\/hpl\/"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"Guangming Tan Chaoyang Shui Yinshan Wang and Yujin Yan. 2021. Optimizing the LINPACK algorithm for large-scale PCIe-based CPU-GPU heterogeneous systems. IEEE Transactions on Parallel and Distributed Systems 32 9 (2021). 10.1109\/TPDS.2021.3067731","DOI":"10.1109\/TPDS.2021.3067731"},{"key":"e_1_3_3_2_26_2","volume-title":"Towards Dense Linear Algebra for Hybrid GPU Accelerated Manycore Systems","author":"Tomov Stanimire","year":"2008","unstructured":"Stanimire Tomov, Jack Dongarra, and Marc Baboulin. 2008. Towards Dense Linear Algebra for Hybrid GPU Accelerated Manycore Systems. Technical Report."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Field\u00a0G Van\u00a0Zee and Robert\u00a0A Van De\u00a0Geijn. 2015. BLIS: A framework for rapidly instantiating BLAS functionality. ACM Transactions on Mathematical Software (TOMS) 41 3 (2015) 1\u201333.","DOI":"10.1145\/2764454"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503219"}],"event":{"name":"SC '25: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St. Louis MO USA","acronym":"SC '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3712285.3759875","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759875","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759875","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:50:32Z","timestamp":1773255032000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712285.3759875"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":27,"alternative-id":["10.1145\/3712285.3759875","10.1145\/3712285"],"URL":"https:\/\/doi.org\/10.1145\/3712285.3759875","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"}}]}}