{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T20:35:01Z","timestamp":1775421301579,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":106,"publisher":"ACM","funder":[{"name":"United States - Department of Energy","award":["DE-SC0011925, DE-FOA-0002705"],"award-info":[{"award-number":["DE-SC0011925, DE-FOA-0002705"]}]},{"name":"United States - National Science Foundation","award":["PHY240298, PHY2117997"],"award-info":[{"award-number":["PHY240298, PHY2117997"]}]},{"name":"United Kingdom - EPSRC","award":["UKRI256, EP\/V028251\/1, EP\/N031768\/1, EP\/S030069\/1, EP\/X036006\/1"],"award-info":[{"award-number":["UKRI256, EP\/V028251\/1, EP\/N031768\/1, EP\/S030069\/1, EP\/X036006\/1"]}]},{"name":"Switzerland - National Science Foundation","award":["PZ00P2_201594"],"award-info":[{"award-number":["PZ00P2_201594"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,2,22]]},"DOI":"10.1145\/3748173.3779200","type":"proceedings-article","created":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T21:17:35Z","timestamp":1770326255000},"page":"79-91","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2774-175X","authenticated-orcid":false,"given":"Chang","family":"Sun","sequence":"first","affiliation":[{"name":"California Institute of Technology, Pasadena, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9263-6529","authenticated-orcid":false,"given":"Zhiqiang","family":"Que","sequence":"additional","affiliation":[{"name":"Imperial Collage London, London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7671-243X","authenticated-orcid":false,"given":"Thea","family":"Aarrestad","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3651-0232","authenticated-orcid":false,"given":"Vladimir","family":"Loncar","sequence":"additional","affiliation":[{"name":"Institute of Physics Belgrade, Belgrade, Serbia and CERN, Geneva, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0055-2935","authenticated-orcid":false,"given":"Jennifer","family":"Ngadiuba","sequence":"additional","affiliation":[{"name":"FermiLab, Batavia, Illinois, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6750-927X","authenticated-orcid":false,"given":"Wayne","family":"Luk","sequence":"additional","affiliation":[{"name":"Imperial College London, London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8172-7081","authenticated-orcid":false,"given":"Maria","family":"Spiropulu","sequence":"additional","affiliation":[{"name":"California Institute of Technology, Pasadena, California, USA"}]}],"member":"320","published-online":{"date-parts":[[2026,2,21]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. Level-1 Trigger Calorimeter Image Convolutional Anomaly Detection Algorithm. (2023). https:\/\/cds.cern.ch\/record\/2879816"},{"key":"e_1_3_2_1_2_1","unstructured":"2024. 2024 Data Collected with AXOL1TL Anomaly Detection at the CMS Level-1 Trigger. (2024). https:\/\/cds.cern.ch\/record\/2904695"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac0ea1"},{"key":"e_1_3_2_1_4_1","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dandelion Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https:\/\/www.tensorflow.org\/ Software available from tensorflow.org."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"Alessandro Giuseppe Franco Nick Fraser and Yaman Umuroglu. 2021. Xilinx\/ brevitas: Release version 0.2.1. doi:10.5281\/zenodo.4507794","DOI":"10.5281\/zenodo.4507794"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL64840.2024.00028"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM62733.2025.00077"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2025.3586311"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEC.1961.5219227"},{"key":"e_1_3_2_1_10_1","volume-title":"Differentiable Weightless Neural Networks. In Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"2295","author":"Leibel Bacellar Alan Tendler","unstructured":"Alan Tendler Leibel Bacellar, Zachary Susskind, Mauricio Breternitz Jr, Eugene John, Lizy Kurian John, Priscila Machado Vieira Lima, and Felipe M.G. Fran\u00e7a. 2024. Differentiable Weightless Neural Networks. In Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 235), Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR, 2277-2295. https:\/\/proceedings.mlr.press\/v235\/bacellar24a.html"},{"key":"e_1_3_2_1_11_1","volume-title":"ONNX: Open Neural Network Exchange. https:\/\/github.com\/onnx\/onnx.","author":"Bai Junjie","year":"2019","unstructured":"Junjie Bai, Fang Lu, Ke Zhang, et al. 2019. ONNX: Open Neural Network Exchange. https:\/\/github.com\/onnx\/onnx."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3444943"},{"key":"e_1_3_2_1_13_1","volume-title":"Courville","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Nicholas L\u00e9onard, and Aaron C. Courville. 2013. Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation. CoRR abs\/1308.3432 (2013). arXiv:1308.3432 http:\/\/arxiv.org\/abs\/1308.3432"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242897"},{"key":"e_1_3_2_1_15_1","volume-title":"Chris Leary, Dougal Maclaurin, George Necula, Adam Paszke, Jake VanderPlas, Skye Wanderman-Milne, and Qiao Zhang.","author":"Bradbury James","year":"2018","unstructured":"James Bradbury, Roy Frostig, Peter Hawkins, Matthew James Johnson, Chris Leary, Dougal Maclaurin, George Necula, Adam Paszke, Jake VanderPlas, Skye Wanderman-Milne, and Qiao Zhang. 2018. JAX: composable transformations of PythonNumPy programs. http:\/\/github.com\/google\/jax"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706628.3708823"},{"key":"e_1_3_2_1_17_1","unstructured":"CERN Collaboration. 2025. CERNBox LHC Jets Dataset. https:\/\/cernbox.cern.ch\/index.php\/s\/jvFd5MoWhGs1l5v\/download Accessed: 2025-09-15."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00027"},{"key":"e_1_3_2_1_19_1","volume-title":"Zhuo Wang, Swagath Venkataramani, Vijayalakshmi Srinivasan, and Kailash Gopalakrishnan.","author":"Choi Jungwook","year":"2018","unstructured":"Jungwook Choi, Pierce I-Jen Chuang, Zhuo Wang, Swagath Venkataramani, Vijayalakshmi Srinivasan, and Kailash Gopalakrishnan. 2018. Bridging the Accuracy Gap for 2-bit Quantized Neural Networks (QNN). CoRR abs\/1807.06964 (2018). arXiv:1807.06964 http:\/\/arxiv.org\/abs\/1807.06964"},{"key":"e_1_3_2_1_20_1","unstructured":"Fran\u00e7ois Chollet et al. 2015. Keras. https:\/\/keras.io."},{"key":"e_1_3_2_1_21_1","volume-title":"Holger Voos, and Jose Luis Sanchez-Lopez.","author":"Cimarelli Claudio","year":"2025","unstructured":"Claudio Cimarelli, Jose Andres Millan-Romera, Holger Voos, and Jose Luis Sanchez-Lopez. 2025. Hardware, Algorithms, and Applications of the Neuromorphic Vision Sensor: a Review. arXiv:2504.08588 [cs.CV] https:\/\/arxiv.org\/abs\/2504.08588"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00356-5"},{"key":"e_1_3_2_1_23_1","volume-title":"Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=mbx2pLK5Eq","author":"Colbert Ian","year":"2024","unstructured":"Ian Colbert, Alessandro Pappalardo, Jakoba Petri-Koenig, and Yaman Umuroglu. 2024. A2Q: Improving Accumulator-Aware Weight Quantization. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=mbx2pLK5Eq"},{"key":"e_1_3_2_1_24_1","unstructured":"OpenML Contributors and LHC Jets HLF Curators. 2020. hls4ml LHC Jets HLF (OpenML Dataset 42468). https:\/\/www.openml.org\/d\/42468 Accessed: 2025-09-15."},{"key":"e_1_3_2_1_25_1","volume-title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations. CoRR abs\/1511.00363","author":"Courbariaux Matthieu","year":"2015","unstructured":"Matthieu Courbariaux, Yoshua Bengio, and Jean-Pierre David. 2015. BinaryConnect: Training Deep Neural Networks with binary weights during propagations. CoRR abs\/1511.00363 (2015). arXiv:1511.00363 http:\/\/arxiv.org\/abs\/1511.00363"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTC.2010.5750334"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","unstructured":"Allison McCarn Deiana Nhan Tran Joshua Agar Michaela Blott Giuseppe Di Guglielmo Javier Duarte Philip Harris Scott Hauck Mia Liu Mark S. Neubauer Jennifer Ngadiuba Seda Ogrenci-Memik Maurizio Pierini Thea Aarrestad Steffen B\u00e4hr J\u00fcrgen Becker Anne-Sophie Berthold Richard J. Bonventre Tom\u00e1s E. M\u00fcller Bravo Markus Diefenthaler Zhen Dong Nick Fritzsche Amir Gholami Ekaterina Govorkova Dongning Guo Kyle J. Hazelwood Christian Herwig Babar Khan Sehoon Kim Thomas Klijnsma Yaling Liu Kin Ho Lo Tri Nguyen Gianantonio Pezzullo Seyedramin Rasoulinezhad Ryan A. Rivera Kate Scholberg Justin Selig Sougata Sen Dmitri Strukov William Tang Savannah Thais Kai Lukas Unger Ricardo Vilalta Belina von Krosigk Shen Wang and Thomas K. Warburton. 2022. Applications and Techniques for Fast Machine Learning in Science. Frontiers in Big Data 5 (April 2022). doi:10.3389\/fdata.2022.787421","DOI":"10.3389\/fdata.2022.787421"},{"key":"e_1_3_2_1_28_1","volume-title":"9th International Conference on Learning Representations, ICLR","author":"Dettmers Tim","year":"2022","unstructured":"Tim Dettmers, Mike Lewis, Sam Shleifer, and Luke Zettlemoyer. 2022. 8-bit Optimizers via Block-wise Quantization. 9th International Conference on Learning Representations, ICLR (2022)."},{"key":"e_1_3_2_1_29_1","unstructured":"Tim Dettmers Ruslan Svirschevski Vage Egiazarian Denis Kuznedelev Elias Frantar Saleh Ashkboos Alexander Borzunov Torsten Hoefler and Dan Alistarh. 2023. SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression. arXiv:2306.03078 [cs.CL]"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Giuseppe Di Guglielmo et al. 2025. End-to-end workflow for machine learningbased qubit readout with QICK and hls4ml. (1 2025). arXiv:2501.14663 [quant-ph]","DOI":"10.1109\/TQE.2025.3604712"},{"key":"e_1_3_2_1_31_1","volume-title":"HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks. CoRR abs\/1911.03852","author":"Dong Zhen","year":"2019","unstructured":"Zhen Dong, Zhewei Yao, Yaohui Cai, Daiyaan Arfeen, Amir Gholami, MichaelW. Mahoney, and Kurt Keutzer. 2019. HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks. CoRR abs\/1911.03852 (2019). arXiv:1911.03852 http:\/\/arxiv.org\/abs\/1911.03852"},{"key":"e_1_3_2_1_32_1","volume-title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed- Precision. CoRR abs\/1905.03696","author":"Dong Zhen","year":"2019","unstructured":"Zhen Dong, Zhewei Yao, Amir Gholami, MichaelW. Mahoney, and Kurt Keutzer. 2019. HAWQ: Hessian AWare Quantization of Neural Networks with Mixed- Precision. CoRR abs\/1905.03696 (2019). arXiv:1905.03696 http:\/\/arxiv.org\/abs\/1905.03696"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/13\/07\/P07027"},{"key":"e_1_3_2_1_34_1","unstructured":"Alexandre D\u00e9fossez Yossi Adi and Gabriel Synnaeve. 2022. Differentiable Model Compression via Pseudo Quantization Noise. arXiv:2104.09987 [stat.ML] https:\/\/arxiv.org\/abs\/2104.09987"},{"key":"e_1_3_2_1_35_1","volume-title":"Modha","author":"Esser Steven K.","year":"2020","unstructured":"Steven K. Esser, Jeffrey L. McKinstry, Deepika Bablani, Rathinakumar Appuswamy, and Dharmendra S. Modha. 2020. Learned Step Size Quantization. arXiv:1902.08153 [cs.LG] https:\/\/arxiv.org\/abs\/1902.08153"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems (","author":"Frantar Elias","year":"2024","unstructured":"Elias Frantar, Sidak Pal Singh, and Dan Alistarh. 2024. Optimal brain compression: a framework for accurate post-training quantization and pruning. In Proceedings of the 36th International Conference on Neural Information Processing Systems (, New Orleans, LA, USA,) (NIPS '22). Curran Associates Inc., Red Hook, NY, USA, Article 323, 14 pages."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC47756.2020.9045268"},{"key":"e_1_3_2_1_38_1","volume-title":"Network Sketching: Exploiting Binary Structure in Deep CNNs. CoRR abs\/1706.02021","author":"Guo Yiwen","year":"2017","unstructured":"Yiwen Guo, Anbang Yao, Hao Zhao, and Yurong Chen. 2017. Network Sketching: Exploiting Binary Structure in Deep CNNs. CoRR abs\/1706.02021 (2017). arXiv:1706.02021 http:\/\/arxiv.org\/abs\/1706.02021"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560551"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/VLSI-DAT54769.2022.9768065"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706628.3708877"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2017.2788865"},{"key":"e_1_3_2_1_44_1","volume-title":"SqueezeLLM: Dense-and-Sparse Quantization. arXiv","author":"Kim Sehoon","year":"2023","unstructured":"Sehoon Kim, Coleman Hooper, Amir Gholami, Zhen Dong, Xiuyu Li, Sheng Shen, Michael Mahoney, and Kurt Keutzer. 2023. SqueezeLLM: Dense-and-Sparse Quantization. arXiv (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. CoRR abs\/1412.6980 (2015)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/15\/06\/C06063"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"e_1_3_2_1_48_1","unstructured":"Fengfu Li Bin Liu Xiaoxing Wang Bo Zhang and Junchi Yan. 2022. Ternary Weight Networks. arXiv:1605.04711 [cs.CV]"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.3390\/computers12030060"},{"key":"e_1_3_2_1_50_1","volume-title":"Garnett (Eds.)","volume":"30","author":"Lin Xiaofan","year":"2017","unstructured":"Xiaofan Lin, Cong Zhao, and Wei Pan. 2017. Towards Accurate Binary Convolutional Neural Network. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H.Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/b1a59b315fc9a3002ce38bbe070ec3f5-Paper.pdf"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2941282"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2518038"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL64840.2024.00029"},{"key":"e_1_3_2_1_54_1","volume-title":"AutoQ: Automated Kernel-Wise Neural Network Quantization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rygfnn4twS","author":"Lou Qian","year":"2020","unstructured":"Qian Lou, Feng Guo, Minje Kim, Lantao Liu, and Lei Jiang. 2020. AutoQ: Automated Kernel-Wise Neural Network Quantization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rygfnn4twS"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3578938"},{"key":"e_1_3_2_1_56_1","unstructured":"Etienne Mercuriali. 2025. The need for speed. https:\/\/www.globaltrading.net\/the-need-for-speed\/"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2006.4380833"},{"key":"e_1_3_2_1_58_1","volume-title":"NIPS Workshop on Deep Learning and Unsupervised Feature Learning","author":"Netzer Yuval","year":"2011","unstructured":"Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y Ng. 2011. Reading digits in natural images with unsupervised feature learning. NIPS Workshop on Deep Learning and Unsupervised Feature Learning (2011)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/608\/1\/012052"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3089687"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad5f10"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_36"},{"key":"e_1_3_2_1_63_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, Hanna M. Wallach, Author PictureHugo Larochelle, Author PictureAlina Beygelzimer, Author PictureFlorence d'Alch\u00e9 Buc, and Author PictureEmily B. Fox (Eds.). Curran Associates Inc., Red Hook, NY, USA, Article 721, 12 pages."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.3602260"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00801"},{"key":"e_1_3_2_1_66_1","volume-title":"MetaML-Pro: Cross-Stage Design Flow Automation for Efficient Deep Learning Acceleration. ACM Transactions on Reconfigurable Technology and Systems","author":"Que Zhiqiang","year":"2026","unstructured":"Zhiqiang Que, Jose G. F. Coutinho, Ce Guo, Hongxiang Fan, and Wayne Luk. 2026. MetaML-Pro: Cross-Stage Design Flow Automation for Efficient Deep Learning Acceleration. ACM Transactions on Reconfigurable Technology and Systems (2026)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640464"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL60245.2023.00042"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL57034.2022.00057"},{"key":"e_1_3_2_1_70_1","volume-title":"JEDI-linear: Fast and Efficient Graph Neural Networks for Jet Tagging on FPGAs. In 2025 International Conference on Field Programmable Technology (FPT). IEEE.","author":"Que Zhiqiang","year":"2025","unstructured":"Zhiqiang Que, Chang Sun, Sudarshan Paramesvaran, Emyr Clement, Katerina Karakoulaki, Christopher Brown, Lauri Laatu, Arianna Cox, Alexander Tapper, Wayne Luk, and Maria Spiropulu. 2025. JEDI-linear: Fast and Efficient Graph Neural Networks for Jet Tagging on FPGAs. In 2025 International Conference on Field Programmable Technology (FPT). IEEE."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP52443.2021.00025"},{"key":"e_1_3_2_1_72_1","unstructured":"Benjamin Ramhorst George A. Constantinides and Vladimir Loncar. 2023. FPGA Resource-aware Structured Pruning for Real-Time Neural Networks. arXiv:2308.05170v1 [cs.AR] https:\/\/arxiv.org\/abs\/2308.05170v1"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00409"},{"key":"e_1_3_2_1_75_1","unstructured":"Jan-Frederik Schulte Benjamin Ramhorst Chang Sun Jovan Mitrevski Nicol\u00f2 Ghielmetti Enrico Lupi Dimitrios Danopoulos Vladimir Loncar Javier Duarte David Burnette Lauri Laatu Stylianos Tzelepis Konstantinos Axiotis Quentin Berthet HaoyanWang Paul White Suleyman Demirsoy Marco Colombo Thea Aarrestad Sioni Summers Maurizio Pierini Giuseppe Di Guglielmo Jennifer Ngadiuba Javier Campos Ben Hawks Abhijith Gandrakota Farah Fahim Nhan Tran George Constantinides Zhiqiang Que Wayne Luk Alexander Tapper Duc Hoang Noah Paladino Philip Harris Bo-Cheng Lai Manuel Valentin Ryan Forelli Seda Ogrenci Lino Gerlach Rian Flynn Mia Liu Daniel Diaz Elham Khoda Melissa Quinnan Russell Solares Santosh Parajuli Mark Neubauer Christian Herwig Ho Fung Tsoi Dylan Rankin Shih-Chieh Hsu and Scott Hauck. 2026. hls4ml: A Flexible Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware. ACM Transactions on Reconfigurable Technology and Systems (2026)."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.02.004"},{"key":"e_1_3_2_1_77_1","unstructured":"Wilson Snyder Paul Wasson Duane Galbi and et al. 2025. Verilator. https:\/\/verilator.org If you use this software please cite it using the metadata from this file.."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.nima.2022.167546"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/adf596"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3777387"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490422.3502364"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","unstructured":"Ole Tange. 2023. GNU Parallel 20240122 ('Frederik X'). doi:10.5281\/zenodo. 10558745 GNU Parallel is a general parallelizer to run multiple serial command line programs in parallel without changing them..","DOI":"10.5281\/zenodo"},{"key":"e_1_3_2_1_83_1","unstructured":"The ATLAS Collaboration. 2017. Technical Design Report for the Phase-II Upgrade of the ATLAS TDAQ System. Technical Report. CERN Geneva. doi:10.17181\/CERN.2LBB.4IAL"},{"key":"e_1_3_2_1_84_1","unstructured":"The Belle II Collaboration. 2010. Belle II Technical Design Report. arXiv:1011.0352 [physics.ins-det] https:\/\/arxiv.org\/abs\/1011.0352"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1093\/ptep\/ptz106"},{"key":"e_1_3_2_1_86_1","volume-title":"The Phase-2 Upgrade of the CMS Level-1 Trigger","author":"Collaboration The CMS","unstructured":"The CMS Collaboration. 2020. The Phase-2 Upgrade of the CMS Level-1 Trigger. Technical Report. CERN, Geneva. https:\/\/cds.cern.clh\/record\/2714892 Final version."},{"key":"e_1_3_2_1_87_1","unstructured":"The LHC Study Group. 1995. The Large Hadron Collider Conceptual Design. Technical Report. CERN\/AC\/95-05 (LHC) Geneva."},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359983"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/adaad8"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL50879.2020.00055"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","unstructured":"Yaman Umuroglu Hendrik Borras Vladimir Loncar Sioni Summers and Javier Duarte. 2024. QONNX. doi:10.5281\/zenodo.14537023","DOI":"10.5281\/zenodo.14537023"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021744"},{"key":"e_1_3_2_1_93_1","volume-title":"CoRR abs\/1706.03762","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. CoRR abs\/1706.03762 (2017). arXiv:1706.03762 http:\/\/arxiv.org\/abs\/1706.03762"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2978817"},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01339-6"},{"key":"e_1_3_2_1_96_1","volume-title":"Linformer: Self-Attention with Linear Complexity. arXiv:2006.04768 [cs.LG] https:\/\/arxiv.org\/abs\/2006.04768","author":"Wang Sinong","year":"2020","unstructured":"Sinong Wang, Belinda Z. Li, Madian Khabsa, Han Fang, and Hao Ma. 2020. Linformer: Self-Attention with Linear Complexity. arXiv:2006.04768 [cs.LG] https:\/\/arxiv.org\/abs\/2006.04768"},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"crossref","unstructured":"Jason Weitz Dmitri Demler Luke McDermott Nhan Tran and Javier Duarte. 2025. Neural Architecture Codesign for Fast Physics Applications. arXiv:2501.05515 [cs.LG] https:\/\/arxiv.org\/abs\/2501.05515","DOI":"10.1088\/2632-2153\/adede1"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706628.3708874"},{"key":"e_1_3_2_1_99_1","volume-title":"Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search. CoRR abs\/1812.00090","author":"Wu Bichen","year":"2018","unstructured":"Bichen Wu, Yanghan Wang, Peizhao Zhang, Yuandong Tian, Peter Vajda, and Kurt Keutzer. 2018. Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search. CoRR abs\/1812.00090 (2018). arXiv:1812.00090 http:\/\/arxiv.org\/abs\/1812.00090"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.3390\/s24030889"},{"key":"e_1_3_2_1_101_1","volume-title":"Alternating Multi-bit Quantization for Recurrent Neural Networks. CoRR abs\/1802.00150","author":"Xu Chen","year":"2018","unstructured":"Chen Xu, Jianqiang Yao, Zhouchen Lin,Wenwu Ou, Yuanbin Cao, ZhirongWang, and Hongbin Zha. 2018. Alternating Multi-bit Quantization for Recurrent Neural Networks. CoRR abs\/1802.00150 (2018). arXiv:1802.00150 http:\/\/arxiv.org\/abs\/1802.00150"},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446863"},{"key":"e_1_3_2_1_103_1","first-page":"581","volume-title":"PyHessian: Neural Networks Through the Lens of the Hessian. 2020 IEEE International Conference on Big Data (Big Data) (2019","author":"Yao Zhewei","year":"2093","unstructured":"Zhewei Yao, Amir Gholami, Kurt Keutzer, and Michael W. Mahoney. 2019. PyHessian: Neural Networks Through the Lens of the Hessian. 2020 IEEE International Conference on Big Data (Big Data) (2019), 581-590. https:\/\/api.semanticscholar.org\/CorpusID:209376531"},{"key":"e_1_3_2_1_104_1","volume-title":"LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks. CoRR abs\/1807.10029","author":"Zhang Dongqing","year":"2018","unstructured":"Dongqing Zhang, Jiaolong Yang, Dongqiangzi Ye, and Gang Hua. 2018. LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks. CoRR abs\/1807.10029 (2018). arXiv:1807.10029 http:\/\/arxiv.org\/abs\/1807.10029"},{"key":"e_1_3_2_1_105_1","volume-title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients. CoRR abs\/1606.06160","author":"Zhou Shuchang","year":"2016","unstructured":"Shuchang Zhou, Zekun Ni, Xinyu Zhou, He Wen, Yuxin Wu, and Yuheng Zou. 2016. DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients. CoRR abs\/1606.06160 (2016). arXiv:1606.06160 http:\/\/arxiv.org\/abs\/1606.06160"},{"key":"e_1_3_2_1_106_1","volume-title":"Dally","author":"Zhu Chenzhuo","year":"2017","unstructured":"Chenzhuo Zhu, Song Han, Huizi Mao, and William J. Dally. 2017. Trained Ternary Quantization. arXiv:1612.01064 [cs.LG]"}],"event":{"name":"FPGA '26:The 2026 ACM\/SIGDA International Symposium on Field Programmable Gate Arrays","location":"Seaside CA USA","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the 2026 ACM\/SIGDA International Symposium on Field Programmable Gate Arrays"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3748173.3779200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:56:24Z","timestamp":1773154584000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3748173.3779200"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":106,"alternative-id":["10.1145\/3748173.3779200","10.1145\/3748173"],"URL":"https:\/\/doi.org\/10.1145\/3748173.3779200","relation":{},"subject":[],"published":{"date-parts":[[2026,2,21]]},"assertion":[{"value":"2026-02-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}