{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:53:44Z","timestamp":1781794424733,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":25,"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":["2340949"],"award-info":[{"award-number":["2340949"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2419880"],"award-info":[{"award-number":["2419880"]}],"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\/3787109.3815216","type":"proceedings-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:17:19Z","timestamp":1781792239000},"page":"693-700","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Control-Flow Collapse: Exploiting Gating Logic in MoE Accelerators via Instruction-Level Fault Injection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9623-6522","authenticated-orcid":false,"given":"Weimin","family":"Fu","sequence":"first","affiliation":[{"name":"Mike Wiegers Department of Electrical and Computer Engineering, Kansas State University, Manhattan,, KS, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2968-641X","authenticated-orcid":false,"given":"Zelin","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6759-8949","authenticated-orcid":false,"given":"Gang","family":"Qu","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9896-9407","authenticated-orcid":false,"given":"Xiaolong","family":"Guo","sequence":"additional","affiliation":[{"name":"Kansas State University, Manhattan, KS, 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":"Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry Quoc Le et\u00a0al. 2021. Program synthesis with large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.07732 (2021)."},{"key":"e_1_3_3_1_3_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique\u00a0Ponde de Oliveira\u00a0Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman Alex Ray Raul Puri Gretchen Krueger Michael Petrov Heidy Khlaaf Girish Sastry Pamela Mishkin Brooke Chan Scott Gray Nick Ryder Mikhail Pavlov Alethea Power Lukasz Kaiser Mohammad Bavarian Clemens Winter Philippe Tillet Felipe\u00a0Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William\u00a0Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew\u00a0N. Carr Jan Leike Josh Achiam Vedant Misra Evan Morikawa Alec Radford Matthew Knight Miles Brundage Mira Murati Katie Mayer Peter Welinder Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever and Wojciech Zaremba. 2021. Evaluating Large Language Models Trained on Code. (2021). arxiv:https:\/\/arXiv.org\/abs\/2107.03374\u00a0[cs.LG]"},{"key":"e_1_3_3_1_4_2","unstructured":"William Fedus Barret Zoph and Noam Shazeer. 2022. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. J. Mach. Learn. Res. 23 (2022) 120:1\u2013120:39. https:\/\/jmlr.org\/papers\/v23\/21-0998.html"},{"key":"e_1_3_3_1_5_2","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, NeurIPS 2021","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. Measuring Mathematical Problem Solving With the MATH Dataset. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, NeurIPS 2021."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","unstructured":"Albert\u00a0Q. Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra\u00a0Singh Chaplot Diego de Las\u00a0Casas Emma\u00a0Bou Hanna Florian Bressand Gianna Lengyel Guillaume Bour Guillaume Lample L\u00e9lio\u00a0Renard Lavaud Lucile Saulnier Marie-Anne Lachaux Pierre Stock Sandeep Subramanian Sophia Yang Szymon Antoniak Teven\u00a0Le Scao Th\u00e9ophile Gervet Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William\u00a0El Sayed. 2024. Mixtral of Experts. CoRR abs\/2401.04088 (2024). arXiv:https:\/\/arXiv.org\/abs\/2401.0408810.48550\/ARXIV.2401.04088","DOI":"10.48550\/ARXIV.2401.04088"},{"key":"e_1_3_3_1_7_2","unstructured":"Dhiraj Kalamkar Dheevatsa Mudigere Naveen Mellempudi Dipankar Das Kunal Banerjee Sasikanth Avancha Dharma\u00a0Teja Vooturi Nataraj Jammalamadaka Jianyu Huang Hector Yuen et\u00a0al. 2019. A study of BFLOAT16 for deep learning training. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1905.12322 (2019)."},{"key":"e_1_3_3_1_8_2","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Lepikhin Dmitry","year":"2021","unstructured":"Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, and Zhifeng Chen. 2021. GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=qrwe7XHTmYb"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.671"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586262"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.154"},{"key":"e_1_3_3_1_13_2","unstructured":"NVIDIA Corporation. 2025. NVIDIA H200 Tensor Core GPU. https:\/\/www.nvidia.com\/en-us\/data-center\/h200\/. Data Center Product Page accessed 2025\u201108\u201101."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Bowen Pan Yikang Shen Haokun Liu Mayank Mishra Gaoyuan Zhang Aude Oliva Colin Raffel and Rameswar Panda. 2024. Dense Training Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models. CoRR abs\/2404.05567 (2024). arXiv:https:\/\/arXiv.org\/abs\/2404.0556710.48550\/ARXIV.2404.05567","DOI":"10.48550\/ARXIV.2404.05567"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.165"},{"key":"e_1_3_3_1_16_2","unstructured":"David Rein Betty\u00a0Li Hou Asa\u00a0Cooper Stickland Jackson Petty Richard\u00a0Yuanzhe Pang Julien Dirani Julian Michael and Samuel\u00a0R. Bowman. 2023. GPQA: A Graduate-Level Google-Proof Q&A Benchmark. arxiv:https:\/\/arXiv.org\/abs\/2311.12022\u00a0[cs.AI]"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6399"},{"key":"e_1_3_3_1_18_2","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Sprague Zayne","year":"2024","unstructured":"Zayne Sprague, Xi Ye, Kaj Bostrom, Swarat Chaudhuri, and Greg Durrett. 2024. MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning. In The Twelfth International Conference on Learning Representations, ICLR 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=jenyYQzue1"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.824"},{"key":"e_1_3_3_1_20_2","unstructured":"Qwen Team. 2024. Qwen1.5-MoE: Matching 7B Model Performance with 1\/3 Activated Parameters. https:\/\/qwenlm.github.io\/blog\/qwen-moe\/"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN48987.2021.00041"},{"key":"e_1_3_3_1_22_2","unstructured":"Shibo Wang and Pankaj Kanwar. 2019. BFloat16: The secret to high performance on Cloud TPUs. Google Cloud Blog 4 1 (2019)."},{"key":"e_1_3_3_1_23_2","volume-title":"Advances in Neural Information Processing Systems 38, NeurIPS 2024","author":"Wang Yubo","year":"2024","unstructured":"Yubo Wang, Xueguang Ma, Ge Zhang, Yuansheng Ni, Abhranil Chandra, Shiguang Guo, Weiming Ren, Aaran Arulraj, Xuan He, Ziyan Jiang, Tianle Li, Max Ku, Kai Wang, Alex Zhuang, Rongqi Fan, Xiang Yue, and Wenhu Chen. 2024. MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark. In Advances in Neural Information Processing Systems 38, NeurIPS 2024."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"e_1_3_3_1_25_2","unstructured":"Jeffrey Zhou Tianjian Lu Swaroop Mishra Siddhartha Brahma Sujoy Basu Yi Luan Denny Zhou and Le Hou. 2023. Instruction-Following Evaluation for Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.07911 (2023)."},{"key":"e_1_3_3_1_26_2","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Zuo Simiao","year":"2022","unstructured":"Simiao Zuo, Xiaodong Liu, Jian Jiao, Young\u00a0Jin Kim, Hany Hassan, Ruofei Zhang, Jianfeng Gao, and Tuo Zhao. 2022. Taming Sparsely Activated Transformer with Stochastic Experts. In The Tenth International Conference on Learning Representations, ICLR 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=B72HXs80q4"}],"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":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3787109.3815216","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:19:52Z","timestamp":1781792392000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3787109.3815216"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":25,"alternative-id":["10.1145\/3787109.3815216","10.1145\/3787109"],"URL":"https:\/\/doi.org\/10.1145\/3787109.3815216","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"}}]}}