{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:45:07Z","timestamp":1787017507909,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,21]]},"DOI":"10.1145\/3695053.3731083","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T12:43:11Z","timestamp":1750423391000},"page":"1125-1139","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["EOD: Enabling Low Latency GNN Inference via Near-Memory Concatenate Aggregation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3336-7848","authenticated-orcid":false,"given":"Taehwan","family":"Kim","sequence":"first","affiliation":[{"name":"KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0432-9324","authenticated-orcid":false,"given":"Yunki","family":"Han","sequence":"additional","affiliation":[{"name":"KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1682-6936","authenticated-orcid":false,"given":"Seohye","family":"Ha","sequence":"additional","affiliation":[{"name":"KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2681-3948","authenticated-orcid":false,"given":"Jiwan","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9585-4591","authenticated-orcid":false,"given":"Lee-Sup","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"AF Agarap. 2018. Deep learning using rectified linear units (relu). arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1803.08375 (2018)."},{"key":"e_1_3_3_1_3_2","unstructured":"AMD. 2024. DRAM address mapping. Retrieved November 16 2024 from https:\/\/docs.amd.com\/r\/en-US\/pg313-network-on-chip\/DRAM-Address-Mapping"},{"key":"e_1_3_3_1_4_2","unstructured":"Jie Chen Tengfei Ma and Cao Xiao. 2018. Fastgcn: fast learning with graph convolutional networks via importance sampling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1801.10247 (2018)."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Avery Ching Sergey Edunov Maja Kabiljo Dionysios Logothetis and Sambavi Muthukrishnan. 2015. One trillion edges: graph processing at Facebook-scale. Proc. VLDB Endow. 8 12 (Aug. 2015) 1804\u20131815. 10.14778\/2824032.2824077","DOI":"10.14778\/2824032.2824077"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"e_1_3_3_1_7_2","volume-title":"Fast Graph Representation Learning with PyTorch Geometric","author":"Fey Matthias","year":"2019","unstructured":"Matthias Fey and Jan\u00a0Eric Lenssen. 2019. Fast Graph Representation Learning with PyTorch Geometric. https:\/\/github.com\/pyg-team\/pytorch_geometric"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Santo Fortunato. 2010. Community detection in graphs. Physics reports 486 3-5 (2010) 75\u2013174.","DOI":"10.1016\/j.physrep.2009.11.002"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00079"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Christina Giannoula Peiming Yang Ivan Fernandez Jiacheng Yang Sankeerth Durvasula Yu\u00a0Xin Li Mohammad Sadrosadati Juan\u00a0Gomez Luna Onur Mutlu and Gennady Pekhimenko. 2024. PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory Architectures. Proc. ACM Meas. Anal. Comput. Syst. 8 3 Article 43 (Dec. 2024) 36\u00a0pages. 10.1145\/3700434","DOI":"10.1145\/3700434"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Michelle Girvan and Mark\u00a0EJ Newman. 2002. Community structure in social and biological networks. Proceedings of the national academy of sciences 99 12 (2002) 7821\u20137826.","DOI":"10.1073\/pnas.122653799"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00051"},{"key":"e_1_3_3_1_13_2","unstructured":"Will Hamilton Zhitao Ying and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645383"},{"key":"e_1_3_3_1_17_2","unstructured":"Weihua Hu Matthias Fey Marinka Zitnik Yuxiao Dong Hongyu Ren Bowen Liu Michele Catasta and Jure Leskovec. 2020. Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems 33 (2020) 22118\u201322133."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070983"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00083"},{"key":"e_1_3_3_1_20_2","unstructured":"Intel. 2024. Maximize ROI and Performance for Demanding Workloads with Intel\u00ae Advanced Vector Extensions 512 (Intel\u00ae AVX-512). Retrieved November 16 2024 from https:\/\/www.intel.com\/content\/www\/us\/en\/products\/docs\/accelerator-engines\/what-is-intel-avx-512.html"},{"key":"e_1_3_3_1_21_2","unstructured":"Inc Intel. 2024. Intel\u00ae Core\u2122 Ultra Processors. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/embedded-processors\/core-ultra.html."},{"key":"e_1_3_3_1_22_2","unstructured":"Haozhu\u00a0Wang Jian\u00a0Zhang and Mengxin Zhu. 2022. Build a GNN-based real-time fraud detection solution using Amazon SageMaker Amazon Neptune and the Deep Graph Library. https:\/\/aws.amazon.com\/cn\/blogs\/machine-learning\/build-a-gnn-based-real-time-fraud-detection-solution-using-amazon-sagemaker-amazon-neptune-and-the-deep-graph-library\/. Accessed: (2024-11-06)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/2429384.2429446"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","unstructured":"U. Kang and Christos Faloutsos. 2013. Big graph mining: algorithms and discoveries. SIGKDD Explor. Newsl. 14 2 (April 2013) 29\u201336. 10.1145\/2481244.2481249","DOI":"10.1145\/2481244.2481249"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00070"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","unstructured":"Liu Ke Xuan Zhang Jinin So Jong-Geon Lee Shin-Haeng Kang Sukhan Lee Songyi Han YeonGon Cho Jin\u00a0Hyun Kim Yongsuk Kwon KyungSoo Kim Jin Jung Ilkwon Yun Sung\u00a0Joo Park Hyunsun Park Joonho Song Jeonghyeon Cho Kyomin Sohn Nam\u00a0Sung Kim and Hsien-Hsin\u00a0S. Lee. 2022. Near-Memory Processing in Action: Accelerating Personalized Recommendation With AxDIMM. IEEE Micro 42 1 (2022) 116\u2013127. 10.1109\/MM.2021.3097700","DOI":"10.1109\/MM.2021.3097700"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS61935.2024.10664793"},{"key":"e_1_3_3_1_28_2","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings","author":"Kipf Thomas\u00a0N.","year":"2017","unstructured":"Thomas\u00a0N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=SJU4ayYgl"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358284"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731711"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527391"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00070"},{"key":"e_1_3_3_1_34_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_35_2","doi-asserted-by":"publisher","unstructured":"Shengwen Liang Ying Wang Cheng Liu Lei He Huawei LI Dawen Xu and Xiaowei Li. 2021. EnGN: A High-Throughput and Energy-Efficient Accelerator for Large Graph Neural Networks. IEEE Trans. Comput. 70 9 (2021) 1511\u20131525. 10.1109\/TC.2020.3014632","DOI":"10.1109\/TC.2020.3014632"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589101"},{"key":"e_1_3_3_1_37_2","first-page":"103","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Liu Tianfeng","year":"2023","unstructured":"Tianfeng Liu, Yangrui Chen, Dan Li, Chuan Wu, Yibo Zhu, Jun He, Yanghua Peng, Hongzheng Chen, Hongzhi Chen, and Chuanxiong Guo. 2023. BGL: GPU-Efficient GNN Training by Optimizing Graph Data I\/O and Preprocessing. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). USENIX Association, Boston, MA, 103\u2013118. https:\/\/www.usenix.org\/conference\/nsdi23\/presentation\/liu-tianfeng"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3272010"},{"key":"e_1_3_3_1_39_2","unstructured":"Dmytro Lopushanskyy and Borun Shi. 2024. Graph Neural Networks on Graph Databases. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.11375 (2024)."},{"key":"e_1_3_3_1_40_2","unstructured":"Lingfei Lu Yudi Qiu Shiyan Yi and Yibo Fan. 2023. A flexible embedding-aware near memory processing architecture for recommendation system. IEEE Computer Architecture Letters (2023)."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557136"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480856"},{"key":"e_1_3_3_1_43_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_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.21"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00035"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00027"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480080"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00017"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"crossref","unstructured":"Scott Rixner William\u00a0J Dally Ujval\u00a0J Kapasi Peter Mattson and John\u00a0D Owens. 2000. Memory access scheduling. ACM SIGARCH Computer Architecture News 28 2 (2000) 128\u2013138.","DOI":"10.1145\/342001.339668"},{"key":"e_1_3_3_1_50_2","unstructured":"T\u00a0Konstantin Rusch Michael\u00a0M Bronstein and Siddhartha Mishra. 2023. A survey on oversmoothing in graph neural networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.10993 (2023)."},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071015"},{"key":"e_1_3_3_1_52_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Si Si","year":"2023","unstructured":"Si Si, Felix Yu, Ankit\u00a0Singh Rawat, Cho-Jui Hsieh, and Sanjiv Kumar. 2023. Serving graph compression for graph neural networks. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","unstructured":"Joonseop Sim Soohong Ahn Taeyoung Ahn Seungyong Lee Myunghyun Rhee Jooyoung Kim Kwangsik Shin Donguk Moon Euiseok Kim and Kyoung Park. 2023. Computational CXL-Memory Solution for Accelerating Memory-Intensive Applications. IEEE Computer Architecture Letters 22 1 (2023) 5\u20138. 10.1109\/LCA.2022.3226482","DOI":"10.1109\/LCA.2022.3226482"},{"key":"e_1_3_3_1_54_2","unstructured":"Petar Veli\u010dkovi\u0107 Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1710.10903 (2017)."},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00070"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00033"},{"key":"e_1_3_3_1_57_2","unstructured":"Xinyi Wu Zhengdao Chen William Wang and Ali Jadbabaie. 2022. A non-asymptotic analysis of oversmoothing in graph neural networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.10701 (2022)."},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"crossref","unstructured":"Zonghan Wu Shirui Pan Fengwen Chen Guodong Long Chengqi Zhang and S\u00a0Yu Philip. 2020. A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems 32 1 (2020) 4\u201324.","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00012"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071102"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"publisher","unstructured":"Sungmin Yun Hwayong Nam Jaehyun Park Byeongho Kim Jung\u00a0Ho Ahn and Eojin Lee. 2024. GraNDe: Efficient Near-Data Processing Architecture for Graph Neural Networks. IEEE Trans. Comput. 73 10 (2024) 2391\u20132404. 10.1109\/TC.2023.3283677","DOI":"10.1109\/TC.2023.3283677"},{"key":"e_1_3_3_1_63_2","unstructured":"Hanqing Zeng Hongkuan Zhou Ajitesh Srivastava Rajgopal Kannan and Viktor Prasanna. 2019. Graphsaint: Graph sampling based inductive learning method. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1907.04931 (2019)."},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511982"},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569670"},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071005"}],"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\/3695053.3731083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T07:08:09Z","timestamp":1750489689000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731083"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":65,"alternative-id":["10.1145\/3695053.3731083","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731083","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"}}]}}