{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T10:08:52Z","timestamp":1743156532691,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":41,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819708109"},{"type":"electronic","value":"9789819708116"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-0811-6_4","type":"book-chapter","created":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T17:02:24Z","timestamp":1708966944000},"page":"59-77","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing GNN Inference Processing on\u00a0Very Long Vector Processor"],"prefix":"10.1007","author":[{"given":"Kangkang","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huayou","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaorun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yalin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,27]]},"reference":[{"key":"4_CR1","unstructured":"Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX conference on Operating Systems Design and Implementation, pp. 265\u2013283 (2016)"},{"key":"4_CR2","unstructured":"Abi-Karam, S., He, Y., Sarkar, R., Sathidevi, L., Qiao, Z., Hao, C.: GenGNN: a generic FPGA framework for graph neural network acceleration. CoRR abs\/2201.08475 (2022). https:\/\/arxiv.org\/abs\/2201.08475"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Azad, A., Bulu\u00e7, A., Gilbert, J.R.: Parallel triangle counting and enumeration using matrix algebra. In: 2015 IEEE International Parallel and Distributed Processing Symposium Workshop, IPDPS 2015, Hyderabad, India, 25\u201329 May 2015, pp. 804\u2013811. IEEE Computer Society (2015)","DOI":"10.1109\/IPDPSW.2015.75"},{"issue":"6","key":"4_CR4","doi-asserted-by":"publisher","first-page":"e33","DOI":"10.1093\/nar\/gkx1313","volume":"46","author":"A Azad","year":"2018","unstructured":"Azad, A., Pavlopoulos, G.A., Ouzounis, C.A., Kyrpides, N.C., Bulu\u00e7, A.: HipMCL: a high-performance parallel implementation of the markov clustering algorithm for large-scale networks. Nucleic Acids Res. 46(6), e33\u2013e33 (2018)","journal-title":"Nucleic Acids Res."},{"issue":"4","key":"4_CR5","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1177\/1094342011403516","volume":"25","author":"A Bulu\u00e7","year":"2011","unstructured":"Bulu\u00e7, A., Gilbert, J.R.: The combinatorial BLAS: design, implementation, and applications. Int. J. High Perform. Comput. Appl. 25(4), 496\u2013509 (2011)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"4_CR6","unstructured":"Chen, J., Ma, T., Xiao, C.: FastGCN: fast learning with graph convolutional networks via importance sampling. arXiv e-prints (2018)"},{"key":"4_CR7","unstructured":"Chen, J., Zhu, J., Song, L.: Stochastic training of graph convolutional networks with variance reduction (2017)"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Davis, T.A.: Algorithm 1000: Suitesparse: Graphblas: graph algorithms in the language of sparse linear algebra. ACM Trans. Math. Softw. 45(4), 44:1\u201344:25 (2019)","DOI":"10.1145\/3322125"},{"key":"4_CR9","doi-asserted-by":"publisher","unstructured":"Fang, J., Liao, X., Huang, C., Dong, D.: Performance evaluation of memory-centric armv8 many-core architectures: a case study with phytium 2000+. J. Comput. Sci. Technol. 36(1), 33\u201343 (2021). https:\/\/doi.org\/10.1007\/s11390-020-0741-6","DOI":"10.1007\/s11390-020-0741-6"},{"key":"4_CR10","unstructured":"Fey, M., Lenssen, J.E.: Fast graph representation learning with PyTorch Geometric (2019)"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Geng, T., et al.: AWB-GCN: a graph convolutional network accelerator with runtime workload rebalancing. In: 53rd Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO 2020, Athens, Greece, pp. 922\u2013936. IEEE (2020)","DOI":"10.1109\/MICRO50266.2020.00079"},{"issue":"2","key":"4_CR12","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/s11390-019-1914-z","volume":"34","author":"C Gui","year":"2019","unstructured":"Gui, C., et al.: A survey on graph processing accelerators: challenges and opportunities. J. Comput. Sci. Technol. 34(2), 339\u2013371 (2019)","journal-title":"J. Comput. Sci. Technol."},{"key":"4_CR13","unstructured":"Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs (2017)"},{"key":"4_CR14","unstructured":"Hamilton, W.L., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA, pp. 1024\u20131034 (2017)"},{"key":"4_CR15","unstructured":"Han, X., Zhao, T., Liu, Y., Hu, X., Shah, N.: MLPInit: embarrassingly simple GNN training acceleration with MLP initialization. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, 1\u20135 May 2023. OpenReview.net (2023). https:\/\/openreview.net\/pdf?id=P8YIphWNEGO"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Heinecke, A., Henry, G., Hutchinson, M., Pabst, H.: LIBXSMM: accelerating small matrix multiplications by runtime code generation. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2016, Salt Lake City, UT, USA, pp. 981\u2013991. IEEE Computer Society (2016)","DOI":"10.1109\/SC.2016.83"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: FeatGraph: a flexible and efficient backend for graph neural network systems. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2020, Virtual Event\/Atlanta, Georgia, USA, p. 71. IEEE\/ACM (2020)","DOI":"10.1109\/SC41405.2020.00075"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Huang, K., Zhai, J., Zheng, Z., Yi, Y., Shen, X.: Understanding and bridging the gaps in current GNN performance optimizations. In: PPoPP 2021: 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, Virtual Event, Republic of Korea, pp. 119\u2013132. ACM (2021)","DOI":"10.1145\/3437801.3441585"},{"key":"4_CR19","doi-asserted-by":"publisher","unstructured":"Jang, J., Kwon, M., Gouk, D., Bae, H., Jung, M.: GraphTensor: comprehensive GNN-acceleration framework for efficient parallel processing of massive datasets. In: IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023, St. Petersburg, FL, USA, 15\u201319 May 2023, pp. 2\u201312. IEEE (2023). https:\/\/doi.org\/10.1109\/IPDPS54959.2023.00011","DOI":"10.1109\/IPDPS54959.2023.00011"},{"key":"4_CR20","unstructured":"Kaler, T., et al.: Accelerating training and inference of graph neural networks with fast sampling and pipelining. In: Marculescu, D., Chi, Y., Wu, C. (eds.) Proceedings of Machine Learning and Systems 2022, MLSys 2022, Santa Clara, CA, USA, August 29 - September 1 2022. mlsys.org (2022). https:\/\/proceedings.mlsys.org\/paper\/2022\/hash\/35f4a8d465e6e1edc05f3d8ab658c551-Abstract.html"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Kepner, J., et al.: Mathematical foundations of the graphBLAS. In: 2016 IEEE High Performance Extreme Computing Conference, HPEC 2016, Waltham, MA, USA, pp. 1\u20139. IEEE (2016)","DOI":"10.1109\/HPEC.2016.7761646"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Kepner, J., Gilbert, J.R.: Graph Algorithms in the Language of Linear Algebra, Software, Environments, Tools, vol. 22. SIAM (2011)","DOI":"10.1137\/1.9780898719918"},{"key":"4_CR23","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France (2017)"},{"issue":"9","key":"4_CR24","doi-asserted-by":"publisher","first-page":"1511","DOI":"10.1109\/TC.2020.3014632","volume":"70","author":"S Liang","year":"2021","unstructured":"Liang, S., et al.: EnGN: a high-throughput and energy-efficient accelerator for large graph neural networks. IEEE Trans. Comput. 70(9), 1511\u20131525 (2021)","journal-title":"IEEE Trans. Comput."},{"key":"4_CR25","doi-asserted-by":"publisher","unstructured":"Lin, Y., Zhang, B., Prasanna, V.K.: HP-GNN: generating high throughput GNN training implementation on CPU-FPGA heterogeneous platform. In: Adler, M., Ienne, P. (eds.) FPGA 2022: The 2022 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, Virtual Event, USA, 27 February 2022\u20131 March 2022, pp. 123\u2013133. ACM (2022). https:\/\/doi.org\/10.1145\/3490422.3502359","DOI":"10.1145\/3490422.3502359"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Malewicz, G., et al.: Pregel: a system for large-scale graph processing. In: Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2010, Indianapolis, Indiana, USA, pp. 135\u2013146. ACM (2010)","DOI":"10.1145\/1807167.1807184"},{"key":"4_CR27","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library, vol. 32 (2019)"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Shun, J., Blelloch, G.E.: Ligra: a lightweight graph processing framework for shared memory. In: ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2013, Shenzhen, China, 23\u201327 February 2013, pp. 135\u2013146. ACM (2013)","DOI":"10.1145\/2517327.2442530"},{"issue":"11","key":"4_CR29","doi-asserted-by":"publisher","first-page":"1214","DOI":"10.14778\/2809974.2809983","volume":"8","author":"N Sundaram","year":"2015","unstructured":"Sundaram, N., et al.: GraphMat: high performance graph analytics made productive. Proc. VLDB Endow. 8(11), 1214\u20131225 (2015)","journal-title":"Proc. VLDB Endow."},{"issue":"12","key":"4_CR30","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1109\/JPROC.2017.2761740","volume":"105","author":"V Sze","year":"2017","unstructured":"Sze, V., Chen, Y., Yang, T., Emer, J.S.: Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295\u20132329 (2017)","journal-title":"Proc. IEEE"},{"key":"4_CR31","unstructured":"Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: Graph attention networks. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net (2018). https:\/\/openreview.net\/forum?id=rJXMpikCZ"},{"issue":"20","key":"4_CR32","first-page":"10","volume":"1050","author":"P Velickovic","year":"2017","unstructured":"Velickovic, P., et al.: Graph attention networks. Stat 1050(20), 10\u201348550 (2017)","journal-title":"Stat"},{"key":"4_CR33","unstructured":"Wang, M., et al.: Deep graph library: towards efficient and scalable deep learning on graphs. CoRR abs\/1909.01315 (2019)"},{"key":"4_CR34","unstructured":"Wang, Y., et al.: GNNAdvisor: an adaptive and efficient runtime system for GNN acceleration on GPUs. In: Brown, A.D., Lorch, J.R. (eds.) 15th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2021, 14\u201316 July 2021, pp. 515\u2013531. USENIX Association (2021). https:\/\/www.usenix.org\/conference\/osdi21\/presentation\/wang-yuke"},{"key":"4_CR35","doi-asserted-by":"publisher","unstructured":"Wu, Y., et al.: Seastar: vertex-centric programming for graph neural networks. In: Barbalace, A., Bhatotia, P., Alvisi, L., Cadar, C. (eds.) EuroSys 2021: Sixteenth European Conference on Computer Systems, Online Event, United Kingdom, 26\u201328 April 2021, pp. 359\u2013375. ACM (2021). https:\/\/doi.org\/10.1145\/3447786.3456247","DOI":"10.1145\/3447786.3456247"},{"key":"4_CR36","unstructured":"Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA (2019)"},{"issue":"1","key":"4_CR37","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/LCA.2020.2970395","volume":"19","author":"M Yan","year":"2020","unstructured":"Yan, M., et al.: Characterizing and understanding GCNs on GPU. IEEE Comput. Archit. Lett. 19(1), 22\u201325 (2020)","journal-title":"IEEE Comput. Archit. Lett."},{"key":"4_CR38","doi-asserted-by":"publisher","unstructured":"Yin, S., Wang, Q., Hao, R., Zhou, T., Mei, S., Liu, J.: Optimizing irregular-shaped matrix-matrix multiplication on multi-core DSPs. In: IEEE International Conference on Cluster Computing, CLUSTER 2022, Heidelberg, Germany, 5\u20138 September 2022, pp. 451\u2013461. IEEE (2022). https:\/\/doi.org\/10.1109\/CLUSTER51413.2022.00055","DOI":"10.1109\/CLUSTER51413.2022.00055"},{"key":"4_CR39","unstructured":"Zeng, H., Zhou, H., Srivastava, A., Kannan, R., Prasanna, V.: GraphSAINT: graph sampling based inductive learning method (2020)"},{"issue":"1","key":"4_CR40","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1109\/LCA.2017.2762308","volume":"19","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., Leng, J., Ma, L., Miao, Y., Li, C., Guo, M.: Architectural implications of graph neural networks. IEEE Comput. Archit. Lett. 19(1), 59\u201362 (2020)","journal-title":"IEEE Comput. Archit. Lett."},{"key":"4_CR41","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","volume":"1","author":"J Zhou","year":"2020","unstructured":"Zhou, J., et al.: Graph neural networks: a review of methods and applications. AI Open 1, 57\u201381 (2020)","journal-title":"AI Open"}],"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\/978-981-97-0811-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T17:03:00Z","timestamp":1708966980000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-0811-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819708109","9789819708116"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-0811-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"27 February 2024","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":"Tianjin","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tjutanklab.com\/ica3pp2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Online submission system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"439","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"145","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}