{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:55:05Z","timestamp":1781794505393,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2441694"],"award-info":[{"award-number":["2441694"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,22]]},"DOI":"10.1145\/3787109.3815290","type":"proceedings-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:17:19Z","timestamp":1781792239000},"page":"502-508","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MRAM-MoE: Efficient Inference of Mixture-of-Experts LLMs with MRAM Chiplet-based Accelerators"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9107-0336","authenticated-orcid":false,"given":"Md Tanjimur","family":"Rahman","sequence":"first","affiliation":[{"name":"Electrical and computer Engineering, Auburn University, Auburn, AL, Auburn, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7325-3134","authenticated-orcid":false,"given":"Md","family":"Asef","sequence":"additional","affiliation":[{"name":"Electrical and computer Engineering, Auburn University, Auburn, AL, Auburn, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0468-7810","authenticated-orcid":false,"given":"Mehdi","family":"Sadi","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, Auburn University, Auburn, AL, Auburn, AL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Samira Abnar et\u00a0al. 2025. Parameters vs flops: Scaling laws for optimal sparsity for mixture-of-experts language models 2025. arXiv:https:\/\/arXiv.org\/abs\/2501.12370 12370 (2025)."},{"key":"e_1_3_3_1_3_2","unstructured":"Muhammad Adnan et\u00a0al. 2024. Keyformer: Kv cache reduction through key tokens selection for efficient generative inference. Proceedings of Machine Learning and Systems 6 (2024) 114\u2013127."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD66269.2025.11240867"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Julian B\u00fcchel et\u00a0al. 2025. Efficient scaling of large language models with mixture of experts and 3D analog in-memory computing. Nature Computational Science 5 1 (2025) 13\u201326.","DOI":"10.1038\/s43588-024-00753-x"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00022"},{"key":"e_1_3_3_1_7_2","volume-title":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","author":"Cao Shiyi","year":"2025","unstructured":"Shiyi Cao et\u00a0al. 2025. Moe-lightning: High-throughput moe inference on memory-constrained gpus. In Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3731599.3767706"},{"key":"e_1_3_3_1_9_2","unstructured":"Etienne\u00a0Goffinet Daria\u00a0Soboleva. 2025. MoE Math Demystified: What Does 8x7B Actually Mean?https:\/\/www.cerebras.ai\/blog\/moe-guide-calculator"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Zhitao Diao et\u00a0al. 2007. Spin-transfer torque switching in magnetic tunnel junctions and spin-transfer torque random access memory. Journal of Physics: Condensed Matter 19 16 (2007) 165209.","DOI":"10.1088\/0953-8984\/19\/16\/165209"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716261"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC63849.2025.11132870"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC63849.2025.11133023"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM19573.2019.8993604"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"AV Khvalkovskiy et\u00a0al. 2013. Basic principles of STT-MRAM cell operation in memory arrays. Journal of Physics D: Applied Physics 46 7 (2013) 074001.","DOI":"10.1088\/0022-3727\/46\/7\/074001"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00066"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITSA60681.2024.10546457"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Kaniz Mishty and Mehdi Sadi. 2021. Designing efficient and high-performance AI accelerators with customized STT-MRAM. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 29 10 (2021) 1730\u20131742.","DOI":"10.1109\/TVLSI.2021.3105958"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Kaniz Mishty and Mehdi Sadi. 2024. Chiplet-gym: Optimizing chiplet-based ai accelerator design with reinforcement learning. IEEE Trans. Comput. 74 1 (2024) 43\u201356.","DOI":"10.1109\/TC.2024.3457740"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Kaniz Mishty and Mehdi Sadi. 2024. System and Design Technology Co-Optimization of SOT-MRAM for High-Performance AI Accelerator Memory System. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 43 4 (2024) 1065\u20131078. 10.1109\/TCAD.2023.3333754","DOI":"10.1109\/TCAD.2023.3333754"},{"key":"e_1_3_3_1_21_2","unstructured":"NVIDIA Corporation. 2022. Floating-Point 8: An Introduction to Efficient Lower-Precision AI Training. https:\/\/developer.nvidia.com\/blog\/floating-point-8-an-introduction-to-efficient-lower-precision-ai-training\/. Accessed: 2026-03-16."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3725843.3756043"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Yue Pan et\u00a0al. 2025. Stratum: System-Hardware Co-Design with Tiered Monolithic 3D-Stackable DRAM for Efficient MoE Serving. Proceedings of the 58th IEEE\/ACM International Symposium on Microarchitecture (2025).","DOI":"10.1145\/3725843.3756043"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.7873\/DATE.2015.0733"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD66269.2025.11240872"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.2009.5424242"},{"key":"e_1_3_3_1_27_2","unstructured":"Luohe Shi Hongyi Zhang Yao Yao Zuchao Li and Hai Zhao. 2024. Keep the cost down: A review on methods to optimize LLM\u2019s KV-cache consumption. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.18003 (2024)."}],"event":{"name":"GLSVLSI '26: Great Lakes Symposium on VLSI 2026","location":"Canandaigua , NY , USA","acronym":"GLSVLSI '26","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CEDA"]},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2026"],"original-title":[],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:29:31Z","timestamp":1781792971000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3787109.3815290"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":26,"alternative-id":["10.1145\/3787109.3815290","10.1145\/3787109"],"URL":"https:\/\/doi.org\/10.1145\/3787109.3815290","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"2026-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}