{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:47:12Z","timestamp":1782546432998,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"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":["2326894"],"award-info":[{"award-number":["2326894"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2425655"],"award-info":[{"award-number":["2425655"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Texas Advanced Computing Center","award":["ASC24080"],"award-info":[{"award-number":["ASC24080"]}]},{"DOI":"10.13039\/100007065","name":"Nvidia","doi-asserted-by":"publisher","award":["Applied Research Accelerator Program Grant"],"award-info":[{"award-number":["Applied Research Accelerator Program Grant"]}],"id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,19]]},"DOI":"10.1145\/3801487.3801834","type":"proceedings-article","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:05:47Z","timestamp":1782543947000},"page":"201-209","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HMix : An Efficient Hardware Accelerator for Quantized MLP-Mixer Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1565-1787","authenticated-orcid":false,"given":"Dhananjay Rao","family":"Thallikar Shyam","sequence":"first","affiliation":[{"name":"Indian Institute of Science, Bangalore, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3619-6066","authenticated-orcid":false,"given":"Shashank","family":"Nag","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, Austin, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8747-5214","authenticated-orcid":false,"given":"Lizy K.","family":"John","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, Austin, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,27]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"Zynq UltraScale+ MPSoC ZCU106 Evaluation Kit User Guide, UG1244","year":"2019","unstructured":"AMD (formerly Xilinx) 2019. Zynq UltraScale+ MPSoC ZCU106 Evaluation Kit User Guide, UG1244. AMD (formerly Xilinx). https:\/\/docs.amd.com\/v\/u\/en-US\/ug1244-zcu106-eval-bd"},{"key":"e_1_3_3_1_3_2","volume-title":"Vivado Design Suite","author":"Xilinx AMD","year":"2022","unstructured":"AMD Xilinx. 2022. Vivado Design Suite. https:\/\/www.amd.com\/en\/products\/software\/adaptive-socs-and-fpgas\/vivado.html Version 2022.1."},{"key":"e_1_3_3_1_4_2","unstructured":"Jimmy\u00a0Lei Ba Jamie\u00a0Ryan Kiros and Geoffrey\u00a0E. Hinton. 2016. Layer Normalization. arxiv:https:\/\/arXiv.org\/abs\/1607.06450\u00a0[stat.ML] https:\/\/arxiv.org\/abs\/1607.06450"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD46524.2019.00028"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","unstructured":"Yu-Hsin Chen Tushar Krishna Joel\u00a0S. Emer and Vivienne Sze. 2017. Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks. IEEE Journal of Solid-State Circuits 52 1 (2017) 127\u2013138. 10.1109\/JSSC.2016.2616357","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","unstructured":"Yu-Hsin Chen Tien-Ju Yang Joel Emer and Vivienne Sze. 2019. Eyeriss v2: A Flexible Accelerator for Emerging Deep Neural Networks on Mobile Devices. IEEE Journal on Emerging and Selected Topics in Circuits and Systems 9 2 (2019) 292\u2013308. 10.1109\/JETCAS.2019.2910232","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"e_1_3_3_1_8_2","volume-title":"Prime Numbers: A Computational Perspective","author":"Crandall R.","year":"2005","unstructured":"R. Crandall and C. Pomerance. 2005. Prime Numbers: A Computational Perspective. Springer. https:\/\/books.google.co.in\/books?id=RbEz-_D7sAUC"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Dana Diaconu Xue Lin Michaela Blott and Miriam Leeser. 2025. A Survey of FPGA-based 3D CNN Accelerators and Hardware-aware Algorithmic Optimizations. ACM Comput. Surv. 58 6 Article 155 (Dec. 2025) 35\u00a0pages. 10.1145\/3777366","DOI":"10.1145\/3777366"},{"key":"e_1_3_3_1_10_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arxiv:https:\/\/arXiv.org\/abs\/2010.11929\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Zidong Du Robert Fasthuber Tianshi Chen Paolo Ienne Ling Li Tao Luo Xiaobing Feng Yunji Chen and Olivier Temam. 2015. ShiDianNao: shifting vision processing closer to the sensor. SIGARCH Comput. Archit. News 43 3S (June 2015) 92\u2013104. 10.1145\/2872887.2750389","DOI":"10.1145\/2872887.2750389"},{"key":"e_1_3_3_1_12_2","series-title":"Proceedings of Machine Learning Research","first-page":"597","volume-title":"Proceedings of The 34th International Conference on Algorithmic Learning Theory","volume":"201","author":"Duman\u00a0Keles Feyza","year":"2023","unstructured":"Feyza Duman\u00a0Keles, Pruthuvi\u00a0Mahesakya Wijewardena, and Chinmay Hegde. 2023. On The Computational Complexity of Self-Attention. In Proceedings of The 34th International Conference on Algorithmic Learning Theory(Proceedings of Machine Learning Research, Vol.\u00a0201), Shipra Agrawal and Francesco Orabona (Eds.). PMLR, 597\u2013619. https:\/\/proceedings.mlr.press\/v201\/duman-keles23a.html"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00452"},{"key":"e_1_3_3_1_14_2","unstructured":"Amir Gholami Sehoon Kim Zhen Dong Zhewei Yao Michael\u00a0W. Mahoney and Kurt Keutzer. 2021. A Survey of Quantization Methods for Efficient Neural Network Inference. arxiv:https:\/\/arXiv.org\/abs\/2103.13630\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2103.13630"},{"key":"e_1_3_3_1_15_2","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. arxiv:https:\/\/arXiv.org\/abs\/1512.03385\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1512.03385"},{"key":"e_1_3_3_1_16_2","unstructured":"Dan Hendrycks and Kevin Gimpel. 2023. Gaussian Error Linear Units (GELUs). arxiv:https:\/\/arXiv.org\/abs\/1606.08415\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1606.08415"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Seyed\u00a0Hani Hozhabr and Roberto Giorgi. 2025. A Survey on Real-Time Object Detection on FPGAs. IEEE Access 13 (2025) 38195\u201338238. 10.1109\/ACCESS.2025.3544515","DOI":"10.1109\/ACCESS.2025.3544515"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"Kung H.T.1982. Why systolic architectures? Computer 15 1 (1982) 37\u201346. 10.1109\/MC.1982.1653825","DOI":"10.1109\/MC.1982.1653825"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Mingqiang Huang Junyi Luo Chenchen Ding Zikun Wei Sixiao Huang and Hao Yu. 2023. An Integer-Only and Group-Vector Systolic Accelerator for Efficiently Mapping Vision Transformer on Edge. IEEE Transactions on Circuits and Systems I: Regular Papers 70 12 (2023) 5289\u20135301. 10.1109\/TCSI.2023.3312775","DOI":"10.1109\/TCSI.2023.3312775"},{"key":"e_1_3_3_1_20_2","unstructured":"Benoit Jacob Skirmantas Kligys Bo Chen Menglong Zhu Matthew Tang Andrew Howard Hartwig Adam and Dmitry Kalenichenko. 2017. Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference. arxiv:https:\/\/arXiv.org\/abs\/1712.05877\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1712.05877"},{"key":"e_1_3_3_1_21_2","unstructured":"Junye Jiang Yaan Zhou Yuanhao Gong Haoxuan Yuan and Shuanglong Liu. 2025. FPGA-based Acceleration for Convolutional Neural Networks: A Comprehensive Review. arxiv:https:\/\/arXiv.org\/abs\/2505.13461\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2505.13461"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Norman\u00a0P. Jouppi George Kurian Sheng Li Peter Ma Rahul Nagarajan Lifeng Nai Nishant Patil Suvinay Subramanian Andy Swing Brian Towles Cliff Young Xiang Zhou Zongwei Zhou and David Patterson. 2023. TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings. arxiv:https:\/\/arXiv.org\/abs\/2304.01433\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/2304.01433","DOI":"10.1145\/3579371.3589350"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","unstructured":"Md\u00a0Mohsin Kabir Ashifur Rahman Md\u00a0Nahid Hasan and M.F. Mridha. 2025. Computer vision algorithms in healthcare: Recent advancements and future challenges. Computers in Biology and Medicine 185 (2025) 109531. 10.1016\/j.compbiomed.2024.109531","DOI":"10.1016\/j.compbiomed.2024.109531"},{"key":"e_1_3_3_1_24_2","unstructured":"Sehoon Kim Amir Gholami Zhewei Yao Michael\u00a0W. Mahoney and Kurt Keutzer. 2021. I-BERT: Integer-only BERT Quantization. arxiv:https:\/\/arXiv.org\/abs\/2101.01321\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2101.01321"},{"key":"e_1_3_3_1_25_2","volume-title":"Advances in Neural Information Processing Systems","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey\u00a0E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems , F.\u00a0Pereira, C.J. Burges, L.\u00a0Bottou, and K.Q. Weinberger (Eds.), Vol.\u00a025. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2012\/file\/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf"},{"key":"e_1_3_3_1_26_2","unstructured":"Zhikai Li and Qingyi Gu. 2023. I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference. arxiv:https:\/\/arXiv.org\/abs\/2207.01405\u00a0[cs.CV]"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/FPL57034.2022.00027"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Ze Liu Yutong Lin Yue Cao Han Hu Yixuan Wei Zheng Zhang Stephen Lin and Baining Guo. 2021. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. arxiv:https:\/\/arXiv.org\/abs\/2103.14030\u00a0[cs.CV]","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC58850.2023.00039"},{"key":"e_1_3_3_1_30_2","unstructured":"Shashank Nag Alan T.\u00a0L. Bacellar Zachary Susskind Anshul Jha Logan Liberty Aishwarya Sivakumar Eugene\u00a0B. John Krishnan Kailas Priscila M.\u00a0V. Lima Neeraja\u00a0J. Yadwadkar Felipe M.\u00a0G. Franca and Lizy\u00a0K. John. 2025. LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons. arxiv:https:\/\/arXiv.org\/abs\/2511.00812\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2511.00812"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10181988"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","unstructured":"Anouar Nechi Lukas Groth Saleh Mulhem Farhad Merchant Rainer Buchty and Mladen Berekovic. 2023. FPGA-based Deep Learning Inference Accelerators: Where Are We Standing? ACM Trans. Reconfigurable Technol. Syst. 16 4 Article 60 (Oct. 2023) 32\u00a0pages. 10.1145\/3613963","DOI":"10.1145\/3613963"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein Alexander\u00a0C Berg and Li Fei-Fei. 2015. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision 115 3 (2015) 211\u2013252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_3_1_34_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. arxiv:https:\/\/arXiv.org\/abs\/1409.1556\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","unstructured":"Qingzeng Song Yao Dai Hao Lu and Guanghao Jin. 2024. High-throughput systolic array-based accelerator for hybrid transformer-CNN networks. Journal of King Saud University - Computer and Information Sciences 36 8 (2024) 102194. 10.1016\/j.jksuci.2024.102194","DOI":"10.1016\/j.jksuci.2024.102194"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34372-9"},{"key":"e_1_3_3_1_37_2","series-title":"(NIPS \u201921)","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"Tolstikhin Ilya\u00a0O.","year":"2021","unstructured":"Ilya\u00a0O. Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, Mario Lucic, and Alexey Dosovitskiy. 2021. MLP-Mixer: An all-MLP Architecture for Vision. In Proceedings of the 35th International Conference on Neural Information Processing Systems(NIPS \u201921). Curran Associates Inc., Red Hook, NY, USA, Article 1857, 12\u00a0pages."},{"key":"e_1_3_3_1_38_2","unstructured":"Hugo Touvron Matthieu Cord Matthijs Douze Francisco Massa Alexandre Sablayrolles and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. arxiv:https:\/\/arXiv.org\/abs\/2012.12877\u00a0[cs.CV]"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","unstructured":"Bo Wang Sheng Ma Guoyi Zhu Xiao Yi and Rui Xu. 2022. A novel systolic array processor with dynamic dataflows. Integration 85 (2022) 42\u201347. 10.1016\/j.vlsi.2022.03.002","DOI":"10.1016\/j.vlsi.2022.03.002"},{"key":"e_1_3_3_1_40_2","unstructured":"Hong-Yi Wang and Tian-Sheuan Chang. 2022. Row-wise Accelerator for Vision Transformer. arxiv:https:\/\/arXiv.org\/abs\/2205.03998\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/2205.03998"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","unstructured":"Teng Wang Lei Gong Chao Wang Yang Yang Yingxue Gao Xuehai Zhou and Huaping Chen. 2022. ViA: A Novel Vision-Transformer Accelerator Based on FPGA. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 41 11 (2022) 4088\u20134099. 10.1109\/TCAD.2022.3197489","DOI":"10.1109\/TCAD.2022.3197489"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","unstructured":"Zhongyu Zhao Rujian Cao Ka-Fai Un Wei-Han Yu Pui-In Mak and Rui\u00a0P. Martins. 2023. An FPGA-Based Transformer Accelerator Using Output Block Stationary Dataflow for Object Recognition Applications. IEEE Transactions on Circuits and Systems II: Express Briefs 70 1 (2023) 281\u2013285. 10.1109\/TCSII.2022.3196055","DOI":"10.1109\/TCSII.2022.3196055"}],"event":{"name":"CF '26: Proceedings of the 23rd ACM International Conference on Computing Frontiers","location":"Catania Italy","acronym":"CF '26","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 23rd ACM International Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3801487.3801834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:12:50Z","timestamp":1782544370000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3801487.3801834"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":41,"alternative-id":["10.1145\/3801487.3801834","10.1145\/3801487"],"URL":"https:\/\/doi.org\/10.1145\/3801487.3801834","relation":{},"subject":[],"published":{"date-parts":[[2026,5,19]]},"assertion":[{"value":"2026-06-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}