{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T17:09:19Z","timestamp":1773248959625,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T00:00:00Z","timestamp":1750377600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["2112562"],"award-info":[{"award-number":["2112562"]}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2328805"],"award-info":[{"award-number":["2328805"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-23-2-0224"],"award-info":[{"award-number":["W911NF-23-2-0224"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,21]]},"DOI":"10.1145\/3695053.3731035","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T16:43:11Z","timestamp":1750437791000},"page":"930-943","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Phi: Leveraging Pattern-based Hierarchical Sparsity for High-Efficiency Spiking Neural Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8815-7948","authenticated-orcid":false,"given":"Chiyue","family":"Wei","sequence":"first","affiliation":[{"name":"Duke University, Durham, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9085-5025","authenticated-orcid":false,"given":"Bowen","family":"Duan","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4479-5525","authenticated-orcid":false,"given":"Cong","family":"Guo","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9771-5111","authenticated-orcid":false,"given":"Jingyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7705-9354","authenticated-orcid":false,"given":"Qingyue","family":"Song","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3228-6544","authenticated-orcid":false,"given":"Hai","family":"Li","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1486-8412","authenticated-orcid":false,"given":"Yiran","family":"Chen","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"2017. IEEE Standard for SystemVerilog: Unified Hardware Design Specification and Verification Language. 10.1109\/IEEESTD.2018.8299595","DOI":"10.1109\/IEEESTD.2018.8299595"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Amogh Agrawal Akhilesh Jaiswal Deboleena Roy Bing Han Gopalakrishnan Srinivasan Aayush Ankit and Kaushik Roy. 2019. Xcel-RAM: Accelerating Binary Neural Networks in High-Throughput SRAM Compute Arrays. IEEE Transactions on Circuits and Systems I: Regular Papers 66 8 (2019) 3064\u20133076.","DOI":"10.1109\/TCSI.2019.2907488"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123982"},{"key":"e_1_3_3_1_5_2","unstructured":"Saleh Ashkboos Amirkeivan Mohtashami Maximilian Croci Bo Li Pashmina Cameron Martin Jaggi Dan Alistarh Torsten Hoefler and James Hensman. 2024. Quarot: Outlier-free 4-bit inference in rotated llms. Advances in Neural Information Processing Systems 37 (2024) 100213\u2013100240."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28975"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"A.\u00a0N. Burkitt. 2006. A Review of the Integrate-and-Fire Neuron Model: I. Homogeneous Synaptic Input. Biological Cybernetics 95 1 (2006) 1\u201319.","DOI":"10.1007\/s00422-006-0068-6"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Tianshi Chen Zidong Du Ninghui Sun Jia Wang Chengyong Wu Yunji Chen and Olivier Temam. 2014. Diannao: A small-footprint high-throughput accelerator for ubiquitous machine-learning. ACM SIGARCH Computer Architecture News 42 1 (2014) 269\u2013284.","DOI":"10.1145\/2654822.2541967"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00048"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Yu-Hsin Chen Tushar Krishna Joel\u00a0S Emer and Vivienne Sze. 2016. Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE journal of solid-state circuits 52 1 (2016) 127\u2013138.","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/378239.379048"},{"key":"e_1_3_3_1_12_2","unstructured":"Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.11929 (2020)."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00075"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304014"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107447615"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Samanwoy Ghosh-Dastidar and Hojjat Adeli. 2009. Spiking neural networks. International journal of neural systems 19 04 (2009) 295\u2013308.","DOI":"10.1142\/S0129065709002002"},{"key":"e_1_3_3_1_17_2","first-page":"249","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249\u2013256."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Cong Guo Feng Cheng Zhixu Du James Kiessling Jonathan Ku Shiyu Li Ziru Li Mingyuan Ma Tergel Molom-Ochir Benjamin Morris et\u00a0al. 2025. A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models. IEEE Circuits and Systems Magazine 25 1 (2025) 35\u201357.","DOI":"10.1109\/MCAS.2024.3476008"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433722"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Cong Guo Chiyue Wei Jiaming Tang Bowen Duan Song Han Hai Li and Yiran Chen. 2025. Transitive Array: An Efficient GEMM Accelerator with Result Reuse. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.16339 (2025).","DOI":"10.1145\/3695053.3731043"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Cong Guo Fengchen Xue Jingwen Leng Yuxian Qiu Yue Guan Weihao Cui Quan Chen and Minyi Guo. 2024. Accelerating sparse dnns based on tiled gemm. IEEE Trans. Comput. (2024).","DOI":"10.1109\/TC.2024.3365942"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00095"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"M. Hassaballah Saleh Omran and Youssef\u00a0B. Mahdy. 2008. A Review of SIMD Multimedia Extensions and their Usage in Scientific and Engineering Applications. Comput. J. 51 6 (2008) 630\u2013649.","DOI":"10.1093\/comjnl\/bxm099"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00086"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358283"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Sagar Imambi Kolla\u00a0Bhanu Prakash and GR Kanagachidambaresan. 2021. PyTorch. Programming with TensorFlow: solution for edge computing applications (2021) 87\u2013104.","DOI":"10.1007\/978-3-030-57077-4_10"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Eugene\u00a0M Izhikevich. 2003. Simple model of spiking neurons. IEEE Transactions on neural networks 14 6 (2003) 1569\u20131572.","DOI":"10.1109\/TNN.2003.820440"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Herve J\u00e9gou Matthijs Douze and Cordelia Schmid. 2011. Product Quantization for Nearest Neighbor Search. IEEE Transactions on Pattern Analysis and Machine Intelligence 33 1 (2011) 117\u2013128.","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439283"},{"key":"e_1_3_3_1_33_2","unstructured":"Alex Krizhevsky Geoffrey Hinton et\u00a0al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Yann LeCun Yoshua Bengio and Geoffrey Hinton. 2015. Deep learning. nature 521 7553 (2015) 436\u2013444.","DOI":"10.1038\/nature14539"},{"key":"e_1_3_3_1_35_2","unstructured":"Jaehoon Lee Yasaman Bahri Roman Novak Samuel\u00a0S Schoenholz Jeffrey Pennington and Jascha Sohl-Dickstein. 2017. Deep neural networks as gaussian processes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1711.00165 (2017)."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00031"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Hongmin Li Hanchao Liu Xiangyang Ji Guoqi Li and Luping Shi. 2017. Cifar10-dvs: an event-stream dataset for object classification. Frontiers in neuroscience 11 (2017) 309.","DOI":"10.3389\/fnins.2017.00309"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Shang Li Zhiyuan Yang Dhiraj Reddy Ankur Srivastava and Bruce Jacob. 2020. DRAMsim3: A cycle-accurate thermal-capable DRAM simulator. IEEE Computer Architecture Letters 19 2 (2020) 106\u2013109.","DOI":"10.1109\/LCA.2020.2973991"},{"key":"e_1_3_3_1_39_2","unstructured":"Ji Lin Jiaming Tang Haotian Tang Shang Yang Wei-Ming Chen Wei-Chen Wang Guangxuan Xiao Xingyu Dang Chuang Gan and Song Han. 2024. Awq: Activation-aware weight quantization for on-device llm compression and acceleration. Proceedings of Machine Learning and Systems 6 (2024) 87\u2013100."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530592"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480123"},{"key":"e_1_3_3_1_42_2","unstructured":"Changze Lv Tianlong Li Jianhan Xu Chenxi Gu Zixuan Ling Cenyuan Zhang Xiaoqing Zheng and Xuanjing Huang. 2023. Spikebert: A language spikformer trained with two-stage knowledge distillation from bert. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.15122 (2023)."},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00023"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"crossref","unstructured":"Naveen Muralimanohar Rajeev Balasubramonian and Norman\u00a0P Jouppi. 2009. CACTI 6.0: A tool to model large caches. HP laboratories 27 (2009) 28.","DOI":"10.1109\/MM.2008.2"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00038"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Martin\u00a0J. Pearson A.\u00a0G. Pipe B. Mitchinson K. Gurney C. Melhuish I. Gilhespy and M. Nibouche. 2007. Implementing Spiking Neural Networks for Real-Time Signal-Processing and Control Applications: A Model-Validated FPGA Approach. IEEE Transactions on Neural Networks 18 5 (2007) 1472\u20131487.","DOI":"10.1109\/TNN.2007.891203"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"crossref","unstructured":"David\u00a0E Rumelhart Geoffrey\u00a0E Hinton and Ronald\u00a0J Williams. 1986. Learning representations by back-propagating errors. nature 323 6088 (1986) 533\u2013536.","DOI":"10.1038\/323533a0"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00062"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"crossref","unstructured":"Ajay Shrestha and Ausif Mahmood. 2019. Review of Deep Learning Algorithms and Architectures. IEEE Access 7 (2019) 53040\u201353065.","DOI":"10.1109\/ACCESS.2019.2912200"},{"key":"e_1_3_3_1_52_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1409.1556 (2014)."},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"crossref","unstructured":"Christoph St\u00f6ckl and Wolfgang Maass. 2021. Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes. Nature Machine Intelligence 3 3 (2021) 230\u2013238.","DOI":"10.1038\/s42256-021-00311-4"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"crossref","unstructured":"Vivienne Sze Yu-Hsin Chen Tien-Ju Yang and Joel\u00a0S. Emer. 2017. Efficient Processing of Deep Neural Networks: A Tutorial and Survey. Proc. IEEE 105 12 (2017) 2295\u20132329.","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"crossref","unstructured":"Amirhossein Tavanaei Masoud Ghodrati Saeed\u00a0Reza Kheradpisheh Timoth\u00e9e Masquelier and Anthony Maida. 2019. Deep learning in spiking neural networks. Neural networks 111 (2019) 47\u201363.","DOI":"10.1016\/j.neunet.2018.12.002"},{"key":"e_1_3_3_1_57_2","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9 11 (2008)."},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"crossref","unstructured":"Gregory\u00a0K Wallace. 1991. The JPEG still picture compression standard. Commun. ACM 34 4 (1991) 30\u201344.","DOI":"10.1145\/103085.103089"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00088"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00066"},{"key":"e_1_3_3_1_62_2","unstructured":"Adina Williams Nikita Nangia and Samuel\u00a0R Bowman. 2017. A broad-coverage challenge corpus for sentence understanding through inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1704.05426 (2017)."},{"key":"e_1_3_3_1_63_2","unstructured":"Xingrun Xing Zheng Zhang Ziyi Ni Shitao Xiao Yiming Ju Siqi Fan Yequan Wang Jiajun Zhang and Guoqi Li. 2024. SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.03287 (2024)."},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"crossref","unstructured":"Yue Yang Xumeng Zhang Pei Chen Lingli Cheng Yanting Ding Chao Li Jie Yu and Qi Liu. 2024. Fully Integrated Memristive Hodgkin-Huxley Neurons With Homeostatic Plasticity. IEEE Electron Device Letters 45 11 (2024) 2225\u20132228.","DOI":"10.1109\/LED.2024.3456816"},{"key":"e_1_3_3_1_65_2","unstructured":"Man Yao Jiakui Hu Zhaokun Zhou Li Yuan Yonghong Tian Bo Xu and Guoqi Li. 2024. Spike-driven transformer. Advances in neural information processing systems 36 (2024)."},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_3_3_1_67_2","unstructured":"Zhaokun Zhou Yuesheng Zhu Chao He Yaowei Wang Shuicheng Yan Yonghong Tian and Li Yuan. 2022. Spikformer: When spiking neural network meets transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.15425 (2022)."},{"key":"e_1_3_3_1_68_2","unstructured":"Rui-Jie Zhu Malu Zhang Qihang Zhao Haoyu Deng Yule Duan and Liang-Jian Deng. 2024. TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networks. IEEE Transactions on Neural Networks and Learning Systems (2024) 1\u201314."}],"event":{"name":"ISCA '25: Proceedings of the 52nd Annual International Symposium on Computer Architecture","location":"Tokyo Japan","acronym":"SIGARCH '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 52nd Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731035","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T10:59:18Z","timestamp":1750503558000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731035"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":67,"alternative-id":["10.1145\/3695053.3731035","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731035","relation":{},"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"2025-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}