{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:44:22Z","timestamp":1768031062140,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":20,"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":["2311830, 2312927, 2323116, 2415201, 2504944"],"award-info":[{"award-number":["2311830, 2312927, 2323116, 2415201, 2504944"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006227","name":"Lawrence Livermore National Laboratory","doi-asserted-by":"publisher","award":["B668423"],"award-info":[{"award-number":["B668423"]}],"id":[{"id":"10.13039\/100006227","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004720","name":"NCR","doi-asserted-by":"publisher","award":["NCR-130002"],"award-info":[{"award-number":["NCR-130002"]}],"id":[{"id":"10.13039\/100004720","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\/3731599.3767462","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:13:44Z","timestamp":1762532024000},"page":"977-984","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["MPI Communication Performance on AMD MI300A: Microbenchmarks and Applications"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2112-4769","authenticated-orcid":false,"given":"Goutham Kalikrishna Reddy","family":"Kuncham","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Ohio State University, Columbus, Ohio, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6888-7793","authenticated-orcid":false,"given":"Siyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Ohio State University, Columbus, Ohio, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9723-4396","authenticated-orcid":false,"given":"Shoaib","family":"Mohammad","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Ohio State University, Columbus, Ohio, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7471-7552","authenticated-orcid":false,"given":"Chen-Chun","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Ohio State University, Columbus, Ohio, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0356-1781","authenticated-orcid":false,"given":"Dhabaleswar K.","family":"Panda","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Ohio State University, Columbus, Ohio, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","volume-title":"Introducing AMD CDNA\u2122 3 Architecture","author":"Inc. Advanced Micro Devices,","year":"2023","unstructured":"Advanced Micro Devices, Inc.2023. Introducing AMD CDNA\u2122 3 Architecture. White Paper. Advanced Micro Devices, Inc.https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/instinct-tech-docs\/white-papers\/amd-cdna-3-white-paper.pdf Accessed: 2025-07-04."},{"key":"e_1_3_3_2_3_2","volume-title":"AMD Instinct\u2122 MI300A APU Data Sheet","author":"Inc. Advanced Micro Devices,","year":"2025","unstructured":"Advanced Micro Devices, Inc.2025. AMD Instinct\u2122 MI300A APU Data Sheet. Data Sheet. Advanced Micro Devices, Inc.https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/instinct-tech-docs\/data-sheets\/amd-instinct-mi300a-data-sheet.pdf Accessed: 2025-07-04."},{"key":"e_1_3_3_2_4_2","unstructured":"AMD. 2025. AMD Instinct MI250 GPU Architecture \u2014 ROCm Documentation. https:\/\/rocm.docs.amd.com\/en\/latest\/conceptual\/gpu-arch\/mi250.html."},{"key":"e_1_3_3_2_5_2","unstructured":"Argonne National Laboratory. [n. d.]. MPICH: High-Performance Portable MPI. https:\/\/www.mpich.org\/. Accessed: August 16 2025."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Carlo Bertolli Thorsten Blass Lynd Stringer Nicole Aschenbrenner Jan-Patrick Lehr Doru Bercea Dhruva Chakrabarti Lawrence Meadows and Ron Lieberman. 2024. Performance Analysis of Runtime Handling of Zero-Copy for OpenMP Programs on MI300A APUs. SC24-W: Workshops of the International Conference for High Performance Computing Networking Storage and Analysis (2024).","DOI":"10.1109\/SCW63240.2024.00183"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"e_1_3_3_2_8_2","unstructured":"Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe Charles Foster Jason Phang Horace He Anish Thite Noa Nabeshima Shawn Presser and Connor Leahy. 2020. The Pile: An 800GB Dataset of Diverse Text for Language Modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2101.00027 (2020)."},{"key":"e_1_3_3_2_9_2","unstructured":"HPE Cray Inc.2025. Cray MPICH: High-Performance MPI Implementation for Cray Systems. https:\/\/docs.nersc.gov\/development\/programming-models\/mpi\/cray-mpich\/. Accessed: 2025-08-16."},{"key":"e_1_3_3_2_10_2","unstructured":"Intel. 2025. Level-Zero. https:\/\/github.com\/oneapi-src\/level-zero."},{"key":"e_1_3_3_2_11_2","unstructured":"Andrej Karpathy. 2022. NanoGPT. https:\/\/github.com\/karpathy\/nanoGPT."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34356-9_28"},{"key":"e_1_3_3_2_13_2","unstructured":"MVAPICH2: MPI over InfiniBand 10GigE\/iWARP and RoCE. [n. d.]. https:\/\/mvapich.cse.ohio-state.edu\/."},{"key":"e_1_3_3_2_14_2","unstructured":"NVIDIA. 2025. CUDA Interprocess Communication. https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html."},{"key":"e_1_3_3_2_15_2","unstructured":"NVIDIA. 2025. NVIDIA NVLink and NVSwitch. https:\/\/www.nvidia.com\/en-us\/data-center\/nvlink\/."},{"key":"e_1_3_3_2_16_2","unstructured":"OSU Micro-benchmarks. [n. d.]. http:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/."},{"key":"e_1_3_3_2_17_2","unstructured":"Quentin Anthony. 2024. nanoGPT. https:\/\/github.com\/Quentin-Anthony\/nanoGPT\/tree\/qanthony\/fsdp."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00079"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Igor Sfiligoi. 2025. Comparing CPU and GPU compute of PERMANOVA on MI300A. (2025). https:\/\/api.semanticscholar.org\/CorpusID:278368042","DOI":"10.1145\/3708035.3736040"},{"key":"e_1_3_3_2_20_2","unstructured":"The OpenFOAM Foundation. [n. d.]. https:\/\/openfoam.org\/."},{"key":"e_1_3_3_2_21_2","unstructured":"The OpenFOAM Foundation. 2025. OpenFOAM: Open Source Computational Fluid Dynamics Software. https:\/\/openfoam.org\/. Version 13."}],"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\/pdf\/10.1145\/3731599.3767462","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:28:20Z","timestamp":1767986900000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767462"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":20,"alternative-id":["10.1145\/3731599.3767462","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767462","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"}}]}}