{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:42:56Z","timestamp":1787017376633,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T00:00:00Z","timestamp":1737331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFB4403103"],"award-info":[{"award-number":["2023YFB4403103"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,1,20]]},"DOI":"10.1145\/3658617.3697674","type":"proceedings-article","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T09:43:12Z","timestamp":1741081392000},"page":"700-705","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["SUArch: Accelerating Layer-wise N:M Sparse Pattern with a Unified Architecture for Deep-learning Edge Device"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3853-2398","authenticated-orcid":false,"given":"Xilong","family":"Kang","sequence":"first","affiliation":[{"name":"Southeast Univ., Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7047-7182","authenticated-orcid":false,"given":"Qingwen","family":"Wei","sequence":"additional","affiliation":[{"name":"Southeast Univ., Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4489-3767","authenticated-orcid":false,"given":"Ningyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Engineering Univ., Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9890-3567","authenticated-orcid":false,"given":"Xingyu","family":"Xu","sequence":"additional","affiliation":[{"name":"Southeast Univ., Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9251-0574","authenticated-orcid":false,"given":"Hao","family":"Cai","sequence":"additional","affiliation":[{"name":"Southeast Univ., Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0894-1054","authenticated-orcid":false,"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"Southeast Univ., Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,3,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"2023 IEEE International Solid-State Circuits Conference (ISSCC). 422--424","author":"Hyochan","unstructured":"Hyochan An et al. 2023. 29.3 An 8.09TOPS\/W Neural Engine Leveraging Bit-Sparsified Sign-Magnitude Multiplications and Dual Adder Trees. In 2023 IEEE International Solid-State Circuits Conference (ISSCC). 422--424."},{"key":"e_1_3_2_1_2_1","first-page":"27826","article-title":"Unsupervised Speech Recognition","volume":"34","author":"Alexei Baevski","year":"2021","unstructured":"Alexei Baevski et al. 2021. Unsupervised Speech Recognition. In Advances in Neural Information Processing Systems (NeuIPS), Vol. 34. 27826--27839.","journal-title":"Advances in Neural Information Processing Systems (NeuIPS)"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 357--366","author":"Chun-Fu","unstructured":"Chun-Fu Chen et al. 2021. CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 357--366."},{"key":"e_1_3_2_1_4_1","volume-title":"2021 IEEE International Solid-State Circuits Conference (ISSCC)","volume":"64","author":"Jack","unstructured":"Jack Choquette et al. 2021. 3.2 The A100 Datacenter GPU and Ampere Architecture. In 2021 IEEE International Solid-State Circuits Conference (ISSCC), Vol. 64. 48--50."},{"key":"e_1_3_2_1_5_1","first-page":"4271","article-title":"Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing","volume":"33","author":"Zihang Dai","year":"2020","unstructured":"Zihang Dai et al. 2020. Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing. In Advances in Neural Information Processing Systems (NeuIPS), Vol. 33. 4271--4282.","journal-title":"Advances in Neural Information Processing Systems (NeuIPS)"},{"key":"e_1_3_2_1_6_1","volume-title":"2024 IEEE Custom Integrated Circuits Conference (CICC). 1--2.","author":"Chaoming","unstructured":"Chaoming Fang et al. 2024. A 0.078 pJ\/SOP Unstructured Sparsity-Aware Spiking Attention\/Convolution Processor with 3D Compute Array. In 2024 IEEE Custom Integrated Circuits Conference (CICC). 1--2."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1109\/TCAD.2023.3317789","article-title":"Efficient N:M Sparse DNN Training Using Algorithm, Architecture, and Dataflow Co-Design","volume":"43","author":"Chao Fang","year":"2024","unstructured":"Chao Fang et al. 2024. Efficient N:M Sparse DNN Training Using Algorithm, Architecture, and Dataflow Co-Design. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) 43 (2024), 506--519.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD)"},{"key":"e_1_3_2_1_8_1","volume-title":"Eureka: Efficient Tensor Cores for One-sided Unstructured Sparsity in DNN Inference. In 2023 56th IEEE\/ACM International Symposium on Microarchitecture (MICRO). 324--337","author":"Ashish","unstructured":"Ashish Gondimalla et al. 2023. Eureka: Efficient Tensor Cores for One-sided Unstructured Sparsity in DNN Inference. In 2023 56th IEEE\/ACM International Symposium on Microarchitecture (MICRO). 324--337."},{"key":"e_1_3_2_1_9_1","volume-title":"2023 IEEE International Solid-State Circuits Conference (ISSCC). 250--252","author":"Shiwei","unstructured":"Shiwei Liu et al. 2023. 16.2 A 28nm 53.8TOPS\/W 8b Sparse Transformer Accelerator with In-Memory Butterfly Zero Skipper for Unstructured-Pruned NN and CIM-Based Local-Attention-Reusable Engine. In 2023 IEEE International Solid-State Circuits Conference (ISSCC). 250--252."},{"key":"e_1_3_2_1_10_1","volume-title":"Exploring the Granularity of Sparsity in Convolutional Neural Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 1927--1934","author":"Huizi","unstructured":"Huizi Mao et al. 2017. Exploring the Granularity of Sparsity in Convolutional Neural Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 1927--1934."},{"key":"e_1_3_2_1_11_1","volume-title":"2021 IEEE International Solid-State Circuits Conference (ISSCC)","volume":"64","author":"Jun-Seok","unstructured":"Jun-Seok Park et al. 2021. 9.5 A 6K-MAC Feature-Map-Sparsity-Aware Neural Processing Unit in 5nm Flagship Mobile SoC. In 2021 IEEE International Solid-State Circuits Conference (ISSCC), Vol. 64. 152--154."},{"key":"e_1_3_2_1_12_1","volume-title":"DSPIMM: A Fully Digital SParse In-Memory Matrix Vector Multiplier for Communication Applications. In 2023 60th ACM\/IEEE Design Automation Conference (DAC). 1--6.","author":"Amitesh","unstructured":"Amitesh Sridharan et al. 2023. DSPIMM: A Fully Digital SParse In-Memory Matrix Vector Multiplier for Communication Applications. In 2023 60th ACM\/IEEE Design Automation Conference (DAC). 1--6."},{"key":"e_1_3_2_1_13_1","first-page":"20721","article-title":"DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks","volume":"34","author":"Wei Sun","year":"2021","unstructured":"Wei Sun et al. 2021. DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks. In Advances in Neural Information Processing Systems (NeuIPS), Vol. 34. 20721--20732.","journal-title":"Advances in Neural Information Processing Systems (NeuIPS)"},{"key":"e_1_3_2_1_14_1","volume-title":"Compressing Deep Neural Networks for Efficient Speech Enhancement. In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 8358--8362","author":"Ke","unstructured":"Ke Tan et al. 2021. Compressing Deep Neural Networks for Efficient Speech Enhancement. In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 8358--8362."},{"key":"e_1_3_2_1_15_1","volume-title":"Dual-side Sparse Tensor Core. In 2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA). 1083--1095","author":"Yang","unstructured":"Yang Wang et al. 2021. Dual-side Sparse Tensor Core. In 2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA). 1083--1095."},{"key":"e_1_3_2_1_16_1","first-page":"4003","article-title":"An FPGA-Based Energy-Efficient Reconfigurable Depthwise Separable Convolution Accelerator for Image Recognition","volume":"69","author":"Lei Xuan","year":"2022","unstructured":"Lei Xuan et al. 2022. An FPGA-Based Energy-Efficient Reconfigurable Depthwise Separable Convolution Accelerator for Image Recognition. IEEE Transactions on Circuits and Systems II: Express Briefs (TCAS II) 69 (2022), 4003--4007.","journal-title":"IEEE Transactions on Circuits and Systems II: Express Briefs (TCAS II)"},{"key":"e_1_3_2_1_17_1","volume-title":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA). 273--286","author":"Haoran","unstructured":"Haoran You et al. 2023. ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design. In 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA). 273--286."},{"key":"e_1_3_2_1_18_1","first-page":"941","article-title":"Learning Best Combination for Efficient N:M Sparsity","volume":"35","author":"Yuxin Zhang","year":"2022","unstructured":"Yuxin Zhang et al. 2022. Learning Best Combination for Efficient N:M Sparsity. In Advances in Neural Information Processing Systems (NeuIPS), Vol. 35. 941--953.","journal-title":"Advances in Neural Information Processing Systems (NeuIPS)"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML)","volume":"202","author":"Yuxin","unstructured":"Yuxin Zhang et al. 2023. Bi-directional Masks for Efficient N:M Sparse Training. In Proceedings of the 40th International Conference on Machine Learning (ICML), Vol. 202. 41488--41497."},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Aojun","unstructured":"Aojun Zhou et al. 2021. Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_21_1","volume-title":"2021 58th ACM\/IEEE Design Automation Conference (DAC). 241--246","author":"Changchun","unstructured":"Changchun Zhou et al. 2021. An Energy-Efficient Low-Latency 3D-CNN Accelerator Leveraging Temporal Locality, Full Zero-Skipping, and Hierarchical Load Balance. In 2021 58th ACM\/IEEE Design Automation Conference (DAC). 241--246."}],"event":{"name":"ASPDAC '25: 30th Asia and South Pacific Design Automation Conference","location":"Tokyo Japan","acronym":"ASPDAC '25","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEICE","IPSJ","IEEE CAS","IEEE CEDA"]},"container-title":["Proceedings of the 30th Asia and South Pacific Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658617.3697674","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658617.3697674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:17:49Z","timestamp":1750281469000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658617.3697674"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,20]]},"references-count":21,"alternative-id":["10.1145\/3658617.3697674","10.1145\/3658617"],"URL":"https:\/\/doi.org\/10.1145\/3658617.3697674","relation":{},"subject":[],"published":{"date-parts":[[2025,1,20]]},"assertion":[{"value":"2025-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}