{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T02:14:26Z","timestamp":1782958466030,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","funder":[{"name":"European High Performance Computing Joint Undertaking","award":["101093261"],"award-info":[{"award-number":["101093261"]}]},{"name":"Swedish Research Council","award":["2022.03062"],"award-info":[{"award-number":["2022.03062"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,6]]},"DOI":"10.1145\/3767110.3767130","type":"proceedings-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T04:36:01Z","timestamp":1769747761000},"page":"238-250","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Inter-APU Communication on AMD MI300A Systems via Infinity Fabric: A Deep Dive"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6504-7109","authenticated-orcid":false,"given":"Gabin","family":"Schieffer","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1669-7714","authenticated-orcid":false,"given":"Jacob","family":"Wahlgren","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4387-367X","authenticated-orcid":false,"given":"Ruimin","family":"Shi","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5805-9046","authenticated-orcid":false,"given":"Edgar A","family":"Leon","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6449-6568","authenticated-orcid":false,"given":"Roger","family":"Pearce","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4229-5735","authenticated-orcid":false,"given":"Maya","family":"Gokhale","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4158-3583","authenticated-orcid":false,"given":"Ivy","family":"Peng","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,1,29]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"2001. OSU Micro-Benchmarks. http:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/"},{"key":"e_1_3_3_1_3_2","unstructured":"AMD. 2024. Compute Language Runtimes (clr) implementation hipMemcpy implementation. https:\/\/github.com\/ROCm\/clr\/blob\/rocm-6.2.1\/hipamd\/src\/hip_memory.cpp."},{"key":"e_1_3_3_1_4_2","unstructured":"AMD. 2024. Heterogeneous-computing Interface for Portability (HIP) Documentation. https:\/\/rocm.docs.amd.com\/projects\/HIP\/en\/docs-6.2.1\/index.html."},{"key":"e_1_3_3_1_5_2","unstructured":"AMD. 2024. Heterogeneous System Architecture (HSA) Documentation. https:\/\/rocm.docs.amd.com\/projects\/ROCR-Runtime\/en\/docs-6.2.1\/."},{"key":"e_1_3_3_1_6_2","unstructured":"AMD. 2024. MI300A System Optimization Guide. https:\/\/instinct.docs.amd.com\/projects\/amdgpu-docs\/en\/latest\/system-optimization\/mi300a.html."},{"key":"e_1_3_3_1_7_2","unstructured":"AMD. 2024. ROCm documentation GPU Memory. https:\/\/rocm.docs.amd.com\/en\/docs-6.2.1\/conceptual\/gpu-memory.html."},{"key":"e_1_3_3_1_8_2","unstructured":"AMD. 2024. ROCr runtime source code. https:\/\/github.com\/ROCm\/ROCR-Runtime\/blob\/rocm-6.2.1\/src\/core\/runtime\/blit_shaders\/blit_copyAligned.s."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607089"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00183"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456233"},{"key":"e_1_3_3_1_12_2","first-page":"625","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Choi Sangjin","year":"2022","unstructured":"Sangjin Choi, Taeksoo Kim, Jinwoo Jeong, Rachata Ausavarungnirun, Myeongjae Jeon, Youngjin Kwon, and Jeongseob Ahn. 2022. Memory harvesting in Multi-GPU systems with hierarchical unified virtual memory. In 2022 USENIX Annual Technical Conference (USENIX ATC 22). 625\u2013638."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00039"},{"key":"e_1_3_3_1_14_2","unstructured":"Luigi Fusco Mikhail Khalilov Marcin Chrapek Giridhar Chukkapalli Thomas Schulthess and Torsten Hoefler. 2024. Understanding data movement in tightly coupled heterogeneous systems: A case study with the Grace Hopper superchip. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.11556 (2024)."},{"key":"e_1_3_3_1_15_2","unstructured":"Google. 2016. Google Benchmark library. https:\/\/github.com\/google\/benchmark."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656591"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Kawthar\u00a0Shafie Khorassani Chen-Chun Chen Bharath Ramesh Aamir Shafi Hari Subramoni and Dhabaleswar\u00a0K Panda. 2023. High performance mpi over the slingshot interconnect. Journal of Computer Science and Technology 38 1 (2023) 128\u2013145.","DOI":"10.1007\/s11390-023-2907-5"},{"key":"e_1_3_3_1_18_2","unstructured":"Lawrence Livermore\u00a0National Laboratory. 2017. https:\/\/asc.llnl.gov\/codes\/proxy-apps\/quicksilver."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573483"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589349"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389705"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-07518-1_4"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Krzysztof\u00a0M Ocetkiewicz Cezary Czaplewski Henryk Krawczyk Agnieszka\u00a0G Lipska Adam Liwo Jerzy Proficz Adam\u00a0K Sieradzan and Pawe\u0142 Czarnul. 2024. Multi-GPU UNRES for scalable coarse-grained simulations of very large protein systems. Computer Physics Communications 298 (2024) 109112.","DOI":"10.1016\/j.cpc.2024.109112"},{"key":"e_1_3_3_1_24_2","unstructured":"Carl Pearson. 2023. Interconnect Bandwidth Heterogeneity on AMD MI250x and Infinity Fabric. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.14827 (2023)."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-02465-9_32"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS61541.2024.00022"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00079"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673110"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/DASC\/PiCom\/DataCom\/CyberSciTec.2018.000-4"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624203"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00068"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-72971-8_1"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.23919\/ISC.2024.10528925"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.42"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC66894.2025.00038"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00035"}],"event":{"name":"MemSys '25: International Symposium on Memory Systems","location":"Washington USA","acronym":"MemSys '25"},"container-title":["Proceedings of the International Symposium on Memory Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3767110.3767130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T04:37:01Z","timestamp":1769747821000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767110.3767130"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,6]]},"references-count":35,"alternative-id":["10.1145\/3767110.3767130","10.1145\/3767110"],"URL":"https:\/\/doi.org\/10.1145\/3767110.3767130","relation":{},"subject":[],"published":{"date-parts":[[2025,10,6]]},"assertion":[{"value":"2026-01-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}