{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T10:49:49Z","timestamp":1775558989900,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819583980","type":"print"},{"value":"9789819583997","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-8399-7_13","type":"book-chapter","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T09:53:44Z","timestamp":1775555624000},"page":"230-246","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A GCN Accelerator with\u00a0Unified Architecture"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9841-5962","authenticated-orcid":false,"given":"Meng","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6915-955X","authenticated-orcid":false,"given":"Mingyu","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5172-9411","authenticated-orcid":false,"given":"Lei","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4069-2251","authenticated-orcid":false,"given":"Wenming","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8778-7149","authenticated-orcid":false,"given":"Zhimin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4598-1685","authenticated-orcid":false,"given":"Xiaochun","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5219-0908","authenticated-orcid":false,"given":"Dongrui","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Lin, H., et al.: A comprehensive survey on distributed training of graph neural networks. Proceedings of the IEEE (2023)","DOI":"10.1109\/JPROC.2023.3337442"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Philip, S.Y.: A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems (2020)","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Yan, M., et al.: Characterizing and understanding GCNs on GPU. IEEE Computer Architecture Letters (2020)","DOI":"10.1109\/LCA.2020.2970395"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Leng, J., Ma, L., Miao, Y., Li, C., Guo, M.: Architectural implications of graph neural networks. IEEE Computer Architecture Letters (2020)","DOI":"10.1109\/LCA.2020.2988991"},{"issue":"2","key":"13_CR5","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1109\/LCA.2022.3198281","volume":"21","author":"M Yan","year":"2022","unstructured":"Yan, M., et al.: Characterizing and understanding HGNNs on GPUs. IEEE Comput. Archit. Lett. 21(2), 69\u201372 (2022)","journal-title":"IEEE Comput. Archit. Lett."},{"issue":"1","key":"13_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3703356","volume":"22","author":"D Han","year":"2025","unstructured":"Han, D., Yan, M., Ye, X., Fan, D.: Characterizing and understanding HGNN training on GPUs. ACM Trans. Archit. Code Optim. 22(1), 1\u201325 (2025)","journal-title":"ACM Trans. Archit. Code Optim."},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Yan, M., et al.: HyGCN: a GCN accelerator with hybrid architecture. In: 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA) (2020)","DOI":"10.1109\/HPCA47549.2020.00012"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Chen, D., et al.: MetaNMP: leveraging cartesian-like product to accelerate HGNNs with near-memory processing. In: Proceedings of the 50th Annual International Symposium on Computer Architecture (2023)","DOI":"10.1145\/3579371.3589091"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Xue, R., et al.: HiHGNN: accelerating HGNNs through parallelism and data reusability exploitation. IEEE Transactions on Parallel and Distributed Systems (2024)","DOI":"10.1109\/TPDS.2024.3394841"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Wu, M., Yan, M., Li, W., Ye, X., Fan, D., Xie, Y.: Survey on characterizing and understanding GNNs from a computer architecture perspective. IEEE Transactions on Parallel and Distributed Systems (2025)","DOI":"10.1109\/TPDS.2025.3532089"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Zeng, H., Prasanna, V.: GraphACT: accelerating GCN training on CPU-FPGA heterogeneous platforms. In: Proceedings of the 2020 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 255\u2013265 (2020)","DOI":"10.1145\/3373087.3375312"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Stevens, J.R., Das, D., Avancha, S., Kaul, B., Raghunathan, A.: GNNerator: a hardware\/software framework for accelerating graph neural networks. In: 2021 58th ACM\/IEEE Design Automation Conference (DAC). IEEE (2021)","DOI":"10.1109\/DAC18074.2021.9586122"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, B., Zeng, H., Prasanna, V.: Hardware acceleration of large scale GCN inference. In: 2020 IEEE 31st International Conference on Application-specific Systems, Architectures and Processors (ASAP), pp. 61\u201368. IEEE (2020)","DOI":"10.1109\/ASAP49362.2020.00019"},{"issue":"12","key":"13_CR14","doi-asserted-by":"publisher","first-page":"4883","DOI":"10.1109\/TCAD.2023.3279302","volume":"42","author":"K Zhong","year":"2023","unstructured":"Zhong, K., et al.: CoGNN: an algorithm-hardware co-design approach to accelerate GNN inference with minibatch sampling. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 42(12), 4883\u20134896 (2023)","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"issue":"4","key":"13_CR15","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1109\/TC.2022.3197083","volume":"72","author":"K Kiningham","year":"2023","unstructured":"Kiningham, K., Levis, P., R\u00e9, C.: GRIP: a graph neural network accelerator architecture. IEEE Trans. Comput. 72(4), 914\u2013925 (2023)","journal-title":"IEEE Trans. Comput."},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Sarkar, R., Abi-Karam, S., He, Y., Sathidevi, L., Hao, C.: FlowGNN: a dataflow architecture for real-time workload-agnostic graph neural network inference. In: 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 1099\u20131112 (2023)","DOI":"10.1109\/HPCA56546.2023.10071015"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Yoo, M., Song, J., Lee, J., Kim, N., Kim, Y., Lee, J.: SGCN: exploiting compressed-sparse features in deep graph convolutional network accelerators. In: 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 1\u201314 (2023)","DOI":"10.1109\/HPCA56546.2023.10071102"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Chen, C., Li, K., Li, Y., Zou, X.: ReGNN: a redundancy-eliminated graph neural networks accelerator. In: 2022 IEEE International Symposium on High-Performance Computer Architecture (HPCA). IEEE (2022)","DOI":"10.1109\/HPCA53966.2022.00039"},{"key":"13_CR19","unstructured":"Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? In: International Conference on Learning Representations (2018)"},{"key":"13_CR20","unstructured":"Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. Adv. Neural Inf. Process. (NeurIPS) 30 (2017)"},{"key":"13_CR21","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. CoRR (2016)"},{"issue":"2","key":"13_CR22","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1109\/JAS.2021.1004311","volume":"9","author":"X Liu","year":"2021","unstructured":"Liu, X., et al.: Sampling methods for efficient training of graph convolutional networks: a survey. IEEE\/CAA J. Automatica Sinica 9(2), 205\u2013234 (2021)","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Auten, A., Tomei, M., Kumar, R.: Hardware acceleration of graph neural networks. In: 2020 57th ACM\/IEEE Design Automation Conference (DAC), pp. 1\u20136. IEEE (2020)","DOI":"10.1109\/DAC18072.2020.9218751"},{"issue":"1","key":"13_CR24","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/LCA.2021.3077956","volume":"20","author":"H Li","year":"2021","unstructured":"Li, H., et al.: Hardware acceleration for GCNs via bidirectional fusion. IEEE Comput. Archit. Lett. 20(1), 66\u201369 (2021)","journal-title":"IEEE Comput. Archit. Lett."},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Xue, R., et al.: SiHGNN: leveraging properties of semantic graphs for efficient HGNN acceleration. IEEE Trans. Comput.-Aided Design Integr. Circuits Syst. 1\u20131 (2025)","DOI":"10.1109\/TCAD.2025.3546881"},{"key":"13_CR26","unstructured":"Jouppi, N.P., et al.: In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, pp. 1\u201312 (2017)"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Xue, R., et al.: GDR-HGNN: a heterogeneous graph neural networks accelerator frontend with graph decoupling and recoupling. In: DAC \u201924: 61st ACM\/IEEE Design Automation Conference (2024)","DOI":"10.1145\/3649329.3656540"},{"issue":"12","key":"13_CR28","first-page":"3140","volume":"71","author":"G Sun","year":"2022","unstructured":"Sun, G., et al.: Multi-node acceleration for large-scale GCNs. IEEE Trans. Comput. 71(12), 3140\u20133152 (2022)","journal-title":"IEEE Trans. Comput."},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Geng, T., et al.: AWB-GCN: a graph convolutional network accelerator with runtime workload rebalancing. In: 2020 53rd Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO) (2020)","DOI":"10.1109\/MICRO50266.2020.00079"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Hwang, R., et al.: GROW: a row-stationary sparse-dense GEMM accelerator for memory-efficient graph convolutional neural networks. In: 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 42\u201355 (2023)","DOI":"10.1109\/HPCA56546.2023.10070983"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Ham, T.J., Wu, L., Sundaram, N., Satish, N., Martonosi, M.: Graphicionado: a high-performance and energy-efficient accelerator for graph analytics. In: 2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp. 1\u201313. IEEE (2016)","DOI":"10.1109\/MICRO.2016.7783759"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Yan, M., et al.: Alleviating irregularity in graph analytics acceleration: a hardware\/software co-design approach. In: Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 615\u2013628 (2019)","DOI":"10.1145\/3352460.3358318"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8399-7_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T09:53:53Z","timestamp":1775555633000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8399-7_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819583980","9789819583997"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8399-7_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"8 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}