{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:38:04Z","timestamp":1781887084866,"version":"3.54.5"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"name":"IDT Young Doctoral Innovation Program","award":["S203.2.01.23.001"],"award-info":[{"award-number":["S203.2.01.23.001"]}]},{"name":"Ningbo NSF","award":["2024J237"],"award-info":[{"award-number":["2024J237"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Reconfigurable Technol. Syst."],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:p>\n            Transformer-based models have achieved extensive success with increasingly large numbers of parameters and computations, for which many multi-core accelerators have been developed. Nevertheless, they suffer from limited throughput due to either low operating frequency or high communication overhead between cores. This article proposes an FPGA-based multi-core overlay processor, named MCoreOPU, to optimize intra-core computation and inter-core communication. First, we boost the operating frequency of the processing element (PE) array to double the rest of the processor to improve the intra-core throughput. Second, we develop on-chip synchronization routers to reduce off-chip memory traffic, where only the partial sum and maximum are communicated between cores rather than entire vectors for layer normalization and softmax. Moreover, we pipeline synchronization to reduce synchronization latency and develop a bypass of the interconnect bus to reduce the off-chip memory access latency. Finally, we optimize the multi-core model allocation and scheduling to minimize the inter-core communications and maximize the intra-core computation efficiency. The MCoreOPU is implemented in 8-bit fixed-point precision with four cores and four DDRs on the Xilinx U200 FPGA, where the PE array runs at 600 MHz while the rest runs at 300 MHz. Experimental results show that the throughput per MAC of MCoreOPU for BERT, ViT, GPT-2, and LLaMA inference is 1.31\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\times\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            \u20137.18\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\times\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            higher than other FPGA-based accelerators. Compared with the A100 GPU, the throughput per equivalent MAC efficiency is improved by 22.52\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\times\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            \u201327.12\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\times\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            .\n          <\/jats:p>","DOI":"10.1145\/3742437","type":"journal-article","created":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T09:10:21Z","timestamp":1748941821000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["MCoreOPU: An FPGA-based Multi-Core Overlay Processor for Transformer-based Models"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8624-8666","authenticated-orcid":false,"given":"Shaoqiang","family":"Lu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China and Eastern Institute of Technology, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5348-1715","authenticated-orcid":false,"given":"Tiandong","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5208-482X","authenticated-orcid":false,"given":"Ting-Jung","family":"Lin","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Ningbo, China and Eastern\u00a0Institute of Technology, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2617-2380","authenticated-orcid":false,"given":"Rumin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Ningbo, China and Eastern\u00a0Institute of Technology, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9939-8922","authenticated-orcid":false,"given":"Chen","family":"Wu","sequence":"additional","affiliation":[{"name":"Chiplet CAD and Manufacturing Engineering Research Center of Zhejiang Province, Ningbo, China, Ningbo Institute of Digital Twin, Ningbo, China and Eastern Institute of Technology, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5266-3805","authenticated-orcid":false,"given":"Lei","family":"He","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,18]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et al. 2023. GPT-4 technical report. arXiv:2303.08774. Retrieved from https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_1_3_2","unstructured":"Hicham Badri and Appu Shaji. 2023. Half-quadratic quantization of large machine learning models November 2023. Retrieved from https:\/\/mobiusml.github.io\/hqq_blog\/"},{"key":"e_1_3_1_4_2","volume-title":"IEEE\/ACM International Conference on Computer Aided Design (ICCAD)","author":"Bai Yueyin","year":"2023","unstructured":"Yueyin Bai, Hao Zhou, Keqing Zhao, Hongji Wang, Jianli Chen, Jun Yu, and Kun Wang. 2023. FET-OPU: A flexible and efficient FPGA-based overlay processor for transformer networks. In IEEE\/ACM International Conference on Computer Aided Design (ICCAD)."},{"key":"e_1_3_1_5_2","volume-title":"IEEE International Conference on Field-Programmable Logic and Applications (FPL)","author":"Bai Yueyin","year":"2023","unstructured":"Yueyin Bai, Hao Zhou, Keqing Zhao, Manting Zhang, Jianli Chen, Jun Yu, and Kun Wang. 2023. LTrans-OPU: A low-latency FPGA-based overlay processor for transformer networks. In IEEE International Conference on Field-Programmable Logic and Applications (FPL)."},{"key":"e_1_3_1_6_2","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems (NIPS)."},{"issue":"1","key":"e_1_3_1_7_2","first-page":"5","article-title":"Understanding the potential of FPGA-based spatial acceleration for large language model inference","volume":"18","author":"Chen Hongzheng","year":"2024","unstructured":"Hongzheng Chen, Jiahao Zhang, Yixiao Du, Shaojie Xiang, Zichao Yue, Niansong Zhang, Yaohui Cai, and Zhiru Zhang. 2024. Understanding the potential of FPGA-based spatial acceleration for large language model inference. ACM Transactions on Reconfigurable Technology and Systems 18, 1, Article 5 (March 2025), 29 pages.","journal-title":"ACM Transactions on Reconfigurable Technology and Systems"},{"key":"e_1_3_1_8_2","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1, 4171\u20134186.","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"},{"key":"e_1_3_1_9_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929. Retrieved from https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_1_10_2","volume-title":"The 11th International Conference on Learning Representations (ICLR)","author":"Frantar Elias","year":"2023","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2023. OPTQ: Accurate quantization for generative pre-trained transformers. In The 11th International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Cheng Gong Haoshuai Zheng Mengting Hu Zheng Lin Deng-Ping Fan Yuzhi Zhang and Tao Li. 2024. Minimise quantization output error with bias compensation. arXiv:2404.01892. Retrieved from https:\/\/arxiv.org\/abs\/2404.01892","DOI":"10.26599\/AIR.2024.9150036"},{"key":"e_1_3_1_12_2","volume-title":"IEEE International Conference on Field-Programmable Logic and Applications (FPL)","author":"Han Yuntao","year":"2023","unstructured":"Yuntao Han and Qiang Liu. 2023. HPTA: A high performance transformer accelerator based on FPGA. In IEEE International Conference on Field-Programmable Logic and Applications (FPL)."},{"key":"e_1_3_1_13_2","volume-title":"International Symposium of Electronics Design Automation (ISEDA)","author":"He Zicheng","year":"2024","unstructured":"Zicheng He, Tiandong Zhao, Siyuan Miao, Chen Wu, and Lei He. 2024. An FPGA-based efficient streaming vector processing engine for transformer-based models. In International Symposium of Electronics Design Automation (ISEDA)."},{"key":"e_1_3_1_14_2","volume-title":"IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Hong Seongmin","year":"2022","unstructured":"Seongmin Hong, Seungjae Moon, Junsoo Kim, Sungjae Lee, Minsub Kim, Dongsoo Lee, and Joo-Young Kim. 2022. DFX: A low-latency multi-FPGA appliance for accelerating transformer-based text generation. In IEEE\/ACM International Symposium on Microarchitecture (MICRO)."},{"issue":"1","key":"e_1_3_1_15_2","first-page":"11","article-title":"A fast and flexible FPGA-based accelerator for natural language processing neural networks","volume":"20","author":"Hur Suyeon","year":"2023","unstructured":"Suyeon Hur, Seongmin Na, Dongup Kwon, Joonsung Kim, Andrew Boutros, Eriko Nurvitadhi, and Jangwoo Kim. 2023. A fast and flexible FPGA-based accelerator for natural language processing neural networks. ACM Transactions on Architecture and Code Optimization 20, 1, Article 11 (March 2023), 24 pages.","journal-title":"ACM Transactions on Architecture and Code Optimization"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"e_1_3_1_17_2","volume-title":"ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA)","author":"Khan Hamza","year":"2021","unstructured":"Hamza Khan, Asma Khan, Zainab Khan, Lun Bin Huang, Kun Wang, and Lei He. 2021. NPE: An FPGA-based overlay processor for natural language processing. In ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA)."},{"key":"e_1_3_1_18_2","volume-title":"International Conference on Machine Learning (ICML)","author":"Kim Sehoon","year":"2021","unstructured":"Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, and Kurt Keutzer. 2021. I-BERT: Integer-only BERT quantization. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_1_19_2","volume-title":"ACM\/IEEE International Symposium on Low Power Electronics and Design (ISLPED)","author":"Li Bingbing","year":"2020","unstructured":"Bingbing Li, Santosh Pandey, Haowen Fang, Yanjun Lyv, Ji Li, Jieyang Chen, Mimi Xie, Lipeng Wan, Hang Liu, and Caiwen Ding. 2020. FTRANS: Energy-efficient acceleration of transformers using FPGA. In ACM\/IEEE International Symposium on Low Power Electronics and Design (ISLPED)."},{"key":"e_1_3_1_20_2","volume-title":"IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Li Zhikai","year":"2022","unstructured":"Zhikai Li and Qingyi Gu. 2022. I-ViT: Integer-only quantization for efficient vision transformer inference. In IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_1_21_2","volume-title":"IEEE International System-on-Chip Conference (SOCC)","author":"Lu Siyuan","year":"2020","unstructured":"Siyuan Lu, Meiqi Wang, Shuang Liang, Jun Lin, and Zhongfeng Wang. 2020. Hardware accelerator for multi-head attention and position-wise feed-forward in the transformer. In IEEE International System-on-Chip Conference (SOCC)."},{"key":"e_1_3_1_22_2","volume-title":"IEEE International Symposium of Electronics Design Automation (ISEDA)","author":"Lu Shaoqiang","year":"2024","unstructured":"Shaoqiang Lu, Tiandong Zhao, Rumin Zhang, Ting-Jung Lin, Chen Wu, and Lei He. 2024. An FPGA-based multi-core overlay processor for transformer-based models. In IEEE International Symposium of Electronics Design Automation (ISEDA)."},{"key":"e_1_3_1_23_2","unstructured":"Maxim Milakov and Natalia Gimelshein. 2018. Online normalizer calculation for softmax arXiv:1805.02867. Retrieved from https:\/\/arxiv.org\/abs\/1805.02867"},{"key":"e_1_3_1_24_2","volume-title":"IEEE International Symposium on Circuits and Systems (ISCAS)","author":"Nag Shashank","year":"2023","unstructured":"Shashank Nag, Gourav Datta, Souvik Kundu, Nitin Chandrachoodan, and Peter A. Beerel. 2023. ViTA: A vision transformer inference accelerator for edge applications. In IEEE International Symposium on Circuits and Systems (ISCAS)."},{"key":"e_1_3_1_25_2","unstructured":"NVIDIA. 2020. NVIDIA A100 tensor core GPU architecture. Retrieved from https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdfpage 24"},{"key":"e_1_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Minseop Park Jaeseong You Markus Nagel and Simyung Chang. 2022. Quadapter: Adapter for GPT-2 quantization. In Findings of the Association for Computational Linguistics (EMNLP).","DOI":"10.18653\/v1\/2022.findings-emnlp.185"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"e_1_3_1_28_2","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever. 2018.\u00a0Improving Language Understanding by Generative Pre-Training. Technical Report OpenAI. Retrieved from https:\/\/cdn.openai.com\/research-covers\/language-unsupervised\/language_understanding_paper.pdf"},{"key":"e_1_3_1_29_2","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever. 2019.\u00a0Language Models are Unsupervised Multitask Learners. Technical Report OpenAI. Retrieved from https:\/\/cdn.openai.com\/better-language-models\/language_models_are_unsupervised_multitask_learners.pdf"},{"key":"e_1_3_1_30_2","volume-title":"IEEE International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","author":"Rajbhandari Samyam","year":"2020","unstructured":"Samyam Rajbhandari, Jeff Rasley, Olatunji Ruwase, and Yuxiong He. 2020. ZeRo: Memory optimizations toward training trillion parameter models. In IEEE International Conference for High Performance Computing, Networking, Storage and Analysis (SC)."},{"key":"e_1_3_1_31_2","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2019. Megatron-LM: Training multi-billion parameter language models using model parallelism. arXiv:1909.08053. Retrieved from https:\/\/arxiv.org\/abs\/1909.08053"},{"key":"e_1_3_1_32_2","unstructured":"Sangeetha Siddegowda Marios Fournarakis Markus Nagel Tijmen Blankevoort Chirag Patel and Abhijit Khobare. 2022. Neural network quantization with AI model efficiency toolkit (AIMET). arXiv:2201.08442. Retrieved from https:\/\/arxiv.org\/abs\/2201.08442"},{"key":"e_1_3_1_33_2","unstructured":"Mengshu Sun Haoyu Ma Guoliang Kang Yifan Jiang Tianlong Chen Xiaolong Ma Zhangyang Wang and Yanzhi Wang. 2022. VAQF: Fully automatic software-hardware co-design framework for low-bit vision transformer. arXiv:2201.06618. Retrieved from https:\/\/arxiv.org\/abs\/2201.06618"},{"key":"e_1_3_1_34_2","volume-title":"IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Tambe Thierry","year":"2021","unstructured":"Thierry Tambe, Coleman Hooper, Lillian Pentecost, Tianyu Jia, En-Yu Yang, Marco Donato, Victor Sanh, Paul Whatmough, Alexander M. Rush, David Brooks, et al. 2021. Edgebert: Sentence-level energy optimizations for latency-aware multi-task nlp inference. In IEEE\/ACM International Symposium on Microarchitecture (MICRO)."},{"key":"e_1_3_1_35_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et al. 2023. LLaMA: Open and efficient foundation language models. arXiv:2302.13971. Retrieved from https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_1_36_2","volume-title":"The 38th Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Wang Changyuan","year":"2024","unstructured":"Changyuan Wang, Ziwei Wang, Xiuwei Xu, Yansong Tang, Jie Zhou, and Jiwen Lu. 2024. Q-VLM: Post-training quantization for large vision-language models. In The 38th Annual Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3197489"},{"issue":"1","key":"e_1_3_1_38_2","first-page":"6","article-title":"Low-precision floating-point arithmetic for high-performance FPGA-based CNN acceleration","volume":"15","author":"Wu Chen","year":"2022","unstructured":"Chen Wu, Mingyu Wang, Xinyuan Chu, Kun Wang, and Lei He. 2022. Low-precision floating-point arithmetic for high-performance FPGA-based CNN acceleration. ACM Transactions on Reconfigurable Technology and Systems 15, 1, Article 6 (March 2022), 21 pages.","journal-title":"ACM Transactions on Reconfigurable Technology and Systems"},{"key":"e_1_3_1_39_2","volume-title":"IEEE International Conference on Field-Programmable Logic and Applications (FPL)","author":"Wu Chen","year":"2021","unstructured":"Chen Wu, Jinming Zhuang, Kun Wang, and Lei He. 2021. MP-OPU: A mixed precision FPGA-based overlay processor for convolutional neural networks. In IEEE International Conference on Field-Programmable Logic and Applications (FPL)."},{"key":"e_1_3_1_40_2","volume-title":"International Conference on Machine Learning (ICLR)","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, and Song Han. 2023. SmoothQuant: Accurate and efficient post-training quantization for large language models. In International Conference on Machine Learning (ICLR)."},{"key":"e_1_3_1_41_2","unstructured":"Xilinx Inc. 2016.\u00a0UltraScale FPGA Product Selection Guide. Technical Report Xilinx. Retrieved from https:\/\/docs.amd.com\/v\/u\/en-US\/ultrascale-fpga-product-selection-guide"},{"key":"e_1_3_1_42_2","unstructured":"Xilinx Inc. 2017. Vivado Design Suite: AXI Reference Guide (UG1037). Technical Report Xilinx. Retrieved from https:\/\/docs.amd.com\/v\/u\/en-US\/ug1037-vivado-axi-reference-guide"},{"key":"e_1_3_1_43_2","unstructured":"Xilinx Inc. 2021. UltraFast Design Methodology Guide for Xilinx FPGAs and SoCs (UG949). Technical Report Xilinx. Retrieved from https:\/\/docs.amd.com\/r\/en-US\/ug949-vivado-design-methodology."},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2019.2939726"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.2995741"},{"key":"e_1_3_1_46_2","doi-asserted-by":"crossref","DOI":"10.1109\/EMC2-NIPS53020.2019.00016","article-title":"Q8BERT: Quantized 8Bit BERT","author":"Zafrir Ofir","year":"2019","unstructured":"Ofir Zafrir, Guy Boudoukh, Peter Izsak, and Moshe Wasserblat. 2019. Q8BERT: Quantized 8Bit BERT. In Energy Efficient Machine Learning and Cognitive Computing - NeurIPS Edition (EMC2-NIPS).","journal-title":"Energy Efficient Machine Learning and Cognitive Computing - NeurIPS Edition (EMC2-NIPS)"},{"key":"e_1_3_1_47_2","volume-title":"ACM\/SIGDA International Symposium on Field Programmable Gate Arrays (FPGA)","author":"Zeng Shulin","year":"2024","unstructured":"Shulin Zeng, Jun Liu, Guohao Dai, Xinhao Yang, Tianyu Fu, Hongyi Wang, Wenheng Ma, Hanbo Sun, Shiyao Li, Zixiao Huang, et al. 2024. FlightLLM: Efficient large language model inference with a complete mapping flow on FPGAs. In ACM\/SIGDA International Symposium on Field Programmable Gate Arrays (FPGA)."},{"key":"e_1_3_1_48_2","volume-title":"IEEE\/ACM International Conference on Computer-Aided Design (ICCAD)","author":"Zhao Tiandong","year":"2024","unstructured":"Tiandong Zhao, Shaoqiang Lu, Chen Wu, and Lei He. 2024. ChatOPU: An FPGA-based overlay processor for large language models with unstructured sparsity. In IEEE\/ACM International Conference on Computer-Aided Design (ICCAD)."},{"key":"e_1_3_1_49_2","volume-title":"IEEE International Conference on Field-Programmable Logic and Applications (FPL)","author":"Zhao Tiandong","year":"2023","unstructured":"Tiandong Zhao, Siyuan Miao, Shaoqiang Lu, Jialin Cao, Jun Qiu, Xiao Shi, Kun Wang, and Lei He. 2023. Token packing for transformers with variable-length inputs. In IEEE International Conference on Field-Programmable Logic and Applications (FPL)."},{"key":"e_1_3_1_50_2","volume-title":"ACM\/SIGDA International Symposium on Field Programmable Gate Arrays (FPGA)","author":"Zhuang Jinming","year":"2024","unstructured":"Jinming Zhuang, Zhuoping Yang, Shixin Ji, Heng Huang, Alex K. Jones, Jingtong Hu, Yiyu Shi, and Peipei Zhou. 2024. SSR: Spatial sequential hybrid architecture for latency throughput tradeoff in transformer acceleration. In ACM\/SIGDA International Symposium on Field Programmable Gate Arrays (FPGA)."}],"container-title":["ACM Transactions on Reconfigurable Technology and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3742437","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:22:35Z","timestamp":1755562955000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3742437"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,18]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,9,30]]}},"alternative-id":["10.1145\/3742437"],"URL":"https:\/\/doi.org\/10.1145\/3742437","relation":{},"ISSN":["1936-7406","1936-7414"],"issn-type":[{"value":"1936-7406","type":"print"},{"value":"1936-7414","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,18]]},"assertion":[{"value":"2024-03-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}