{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T21:21:18Z","timestamp":1782854478171,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,26]]},"DOI":"10.1145\/3773656.3773680","type":"proceedings-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T10:22:11Z","timestamp":1767954131000},"page":"215-227","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["GPU Partitioning, Power, and Performance of the AMD MI300A"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0303-2871","authenticated-orcid":false,"given":"Amr","family":"Abouelmagd","sequence":"first","affiliation":[{"name":"Tennessee Technological University, Cookeville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4159-1519","authenticated-orcid":false,"given":"David","family":"Boehme","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1458-8453","authenticated-orcid":false,"given":"Stephanie","family":"Brink","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3036-0108","authenticated-orcid":false,"given":"Jason","family":"Burmark","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7201-5733","authenticated-orcid":false,"given":"Michael","family":"McKinsey","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5252-6600","authenticated-orcid":false,"given":"Anthony","family":"Skjellum","sequence":"additional","affiliation":[{"name":"Tennessee Technological University, Cookeville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1904-9627","authenticated-orcid":false,"given":"Olga","family":"Pearce","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,1,25]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Advanced Micro Devices Inc.[n. d.]. AMD Instinct MI300A APU: GPU Partitioning Overview. https:\/\/instinct.docs.amd.com\/projects\/amdgpu-docs\/en\/latest\/gpu-partitioning\/mi300a\/overview.html. Accessed: 2025-09-15."},{"key":"e_1_3_3_1_3_2","unstructured":"Advanced Micro Devices Inc.2023. AMD ROCprof v3: ROCm Profiling Tool. https:\/\/rocm.docs.amd.com\/projects\/rocprofiler\/en\/latest\/. Accessed: 2025-09-15."},{"key":"e_1_3_3_1_4_2","unstructured":"Advanced Micro Devices Inc.2023. AMD System Management Interface (AMD-SMI). https:\/\/www.amd.com\/en\/technologies\/amd-smi. Accessed: 2025-09-15."},{"key":"e_1_3_3_1_5_2","unstructured":"AMD. 2024. AMD CDNA3 Architecture. https:\/\/www.amd.com\/content\/dam\/am d\/en\/documents\/instinct-tech-docs\/white-papers\/amd-cdna-3-white-paper.pdf."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC49587.2019.00012"},{"key":"e_1_3_3_1_7_2","series-title":"(SC \u201916)","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Boehme David","year":"2016","unstructured":"David Boehme, Todd Gamblin, David Beckingsale, Peer-Timo Bremer, Alfredo Gimenez, Matthew LeGendre, Olga Pearce, and Martin Schulz. 2016. Caliper: Performance Introspection for HPC Software Stacks. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (Salt Lake City, Utah) (SC \u201916). IEEE Press, Article 47, 11\u00a0pages."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3588195.3592989"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"H. Carter Edwards Christian\u00a0R. Trott and Daniel Sunderland. 2014. Kokkos: Enabling manycore performance portability through polymorphic memory access patterns. J. Parallel Distributed Comput. 74 (2014) 3202\u20133216.","DOI":"10.1016\/j.jpdc.2014.07.003"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Jaeyoung Choi Jack\u00a0J. Dongarra L.\u00a0Susan Ostrouchov Antoine\u00a0P. Petitet David\u00a0W. Walker and R.\u00a0Clint Whaley. 1996. Design and Implementation of the ScaLAPACK LU QR and Cholesky Factorization Routines. Sci. Program. 5 3 (Aug. 1996) 173\u2013184. doi:10.1155\/1996\/483083","DOI":"10.1155\/1996\/483083"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Leonardo Dagum and Ram Menon. 1998. OpenMP: an industry standard API for shared-memory programming.","DOI":"10.1109\/99.660313"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Ra\u00fal de\u00a0la Cruz and Mauricio Araya\u00a0Polo. 2011. Towards a Multi-Level Cache Performance Model for 3D Stencil Computation. Procedia Computer Science 4. doi:10.1016\/j.procs.2011.04.235","DOI":"10.1016\/j.procs.2011.04.235"},{"key":"e_1_3_3_1_13_2","unstructured":"Hikmet Dursun Ken-ichi Nomura Weiqiang Wang Manaschai Kunaseth Liu Peng Richard Seymour Rajiv\u00a0K. Kalia Aiichiro Nakano and Priya Vashishta. 2009. In-Core Optimization of High-Order Stencil Computations.533\u2013538."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/1178597.1178605"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Baolin Li Viiay Gadepally Siddharth Samsi and Devesh Tiwari. 2022. Characterizing Multi-Instance GPU for Machine Learning Workloads. 2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) (2022) 724\u2013731. https:\/\/api.semanticscholar.org\/CorpusID:251324911","DOI":"10.1109\/IPDPSW55747.2022.00124"},{"key":"e_1_3_3_1_16_2","unstructured":"LLNL. 2016. RAJA Performance Portability Layer (C++). http:\/\/github.com\/LLNL\/raja."},{"key":"e_1_3_3_1_17_2","unstructured":"LLNL. 2017. Caliper. https:\/\/github.com\/llnl\/caliper."},{"key":"e_1_3_3_1_18_2","unstructured":"LLNL. 2023. Benchpark. https:\/\/github.com\/LLNL\/benchpark."},{"key":"e_1_3_3_1_19_2","unstructured":"LLNL. 2023. Thicket. https:\/\/github.com\/llnl\/thicket."},{"key":"e_1_3_3_1_20_2","unstructured":"NVIDIA. 2025. Multi-Process Service. https:\/\/docs.nvidia.com\/deploy\/mps\/index.html."},{"key":"e_1_3_3_1_21_2","unstructured":"NVIDIA. 2025. NVIDIA Multi-Instance GPU. https:\/\/www.nvidia.com\/en-us\/technologies\/multi-instance-gpu\/."},{"key":"e_1_3_3_1_22_2","unstructured":"Muhammed Osama Ryan Swann Karthik Sangaiah Sonali Singh Ganesh Dasika and Rajneesh Bhardwaj. 2025. Deep dive into the MI300 compute and memory partition modes. https:\/\/rocm.blogs.amd.com\/software-tools-optimization\/compute-memory-modes\/README.html."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Olga Pearce Gregory Becker Stephanie Brink Nathan Hanford Dewi Yokelson August Knox and Barry Rountree. 2025. HPC Benchmarking: Repeat Replicate Reproduce. ACM Conference on Reproducibility and Replicability.","DOI":"10.1145\/3736731.3746150"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00162"},{"key":"e_1_3_3_1_25_2","unstructured":"Sivasankaran Rajamanickam Seher Acer Luc Berger-Vergiat Vinh Dang Nathan Ellingwood Evan Harvey Brian Kelley Christian\u00a0R. Trott Jeremiah Wilke and Ichitaro Yamazaki. 2021. Kokkos Kernels: Performance Portable Sparse\/Dense Linear Algebra and Graph Kernels. ArXiv abs\/2103.11991 (2021)."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00068"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Christian\u00a0R. Trott Damien Lebrun-Grandi\u00e9 Daniel Arndt Jan Ciesko Vinh Dang Nathan Ellingwood Rahulkumar Gayatri Evan Harvey Daisy\u00a0S. Hollman Dan Ibanez Nevin Liber Jonathan Madsen Jeff Miles David Poliakoff Amy Powell Sivasankaran Rajamanickam Mikael Simberg Dan Sunderland Bruno Turcksin and Jeremiah Wilke. 2022. Kokkos 3: Programming Model Extensions for the Exascale Era. IEEE Transactions on Parallel and Distributed Systems 33 (2022) 805\u2013817.","DOI":"10.1109\/TPDS.2021.3097283"},{"key":"e_1_3_3_1_28_2","unstructured":"Tirth Vamja Kaustabha Ray Felix George and UmaMaheswari\u00a0C Devi. 2025. On the Partitioning of GPU Power among Multi-Instances. ArXiv abs\/2501.17752 (2025). https:\/\/api.semanticscholar.org\/CorpusID:275954225"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3754598.3754668"}],"event":{"name":"SCA\/HPCAsia 2026: Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","location":"Osaka Japan","acronym":"SCA\/HPCAsia 2026"},"container-title":["Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region"],"original-title":[],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T10:23:08Z","timestamp":1767954188000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773656.3773680"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,25]]},"references-count":28,"alternative-id":["10.1145\/3773656.3773680","10.1145\/3773656"],"URL":"https:\/\/doi.org\/10.1145\/3773656.3773680","relation":{},"subject":[],"published":{"date-parts":[[2026,1,25]]},"assertion":[{"value":"2026-01-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}