{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:31:20Z","timestamp":1760711480281,"version":"3.40.4"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003662","name":"Korea Evaluation Institute of Industrial Technology","doi-asserted-by":"publisher","award":["RS-2023-00236772"],"award-info":[{"award-number":["RS-2023-00236772"]}],"id":[{"id":"10.13039\/501100003662","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IITP-ITRC program funded by the Ministry of Science","award":["IITP-2025-RS-2020-II201847"],"award-info":[{"award-number":["IITP-2025-RS-2020-II201847"]}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2025-00560896"],"award-info":[{"award-number":["RS-2025-00560896"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tpds.2025.3549180","type":"journal-article","created":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:48:16Z","timestamp":1741373296000},"page":"918-931","source":"Crossref","is-referenced-by-count":1,"title":["Graphite: Hardware-Aware GNN Reshaping for Acceleration With GPU Tensor Cores"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5671-1870","authenticated-orcid":false,"given":"Hyeonjin","family":"Kim","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2472-595X","authenticated-orcid":false,"given":"Taesoo","family":"Lim","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9170-5986","authenticated-orcid":false,"given":"William J.","family":"Song","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/43601"},{"first-page":"1","article-title":"Introducing AMD CDNA2 architecture: Propelling humanity\u2019s foremost research with the world\u2019s most powerful HPC and AI accelerator","year":"2021","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.286.5439.509"},{"key":"ref4","first-page":"1","article-title":"Fast graph representation learning with pytorch geometric","volume-title":"Proc. Workshop Representation Learn. Graphs Manifolds Int. Conf. Learn. Representations","author":"Fey"},{"key":"ref5","first-page":"5125","article-title":"Learning graph representations with embedding propagation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Garcia-Duran"},{"key":"ref6","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00076"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070983"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00011"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451158"},{"key":"ref11","first-page":"1","volume-title":"METIS: A Software Package for Partitioning Unstructured Graphs, Partitioning Meshes, and Computing Fill-Reducing Orderings of Sparse Matrices","author":"Karypis","year":"2011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00047"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00065"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3247808"},{"key":"ref15","first-page":"2713","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553447"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835937"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2015.03.003"},{"key":"ref19","first-page":"443","article-title":"NeuGraph: Parallel deep neural network computation on large graphs","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Ma"},{"key":"ref20","article-title":"Cora","volume-title":"IEEE Dataport","author":"McCallum","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS51385.2021.00016"},{"key":"ref22","first-page":"1","article-title":"Wiki-CS: A wikipedia-based benchmark for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mernyei"},{"key":"ref23","first-page":"1","article-title":"Query-driven active surveying for collective classification","volume-title":"Proc. Int. Workshop Mining Learn. Graphs","author":"Namata"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.74.036104"},{"first-page":"1","article-title":"NVIDIA Tesla V100 GPU architecture: The World\u2019s most advanced data center GPU","year":"2017","key":"ref25"},{"first-page":"1","article-title":"NVIDIA A100 Tensor Core GPU architecture: Unprecedented acceleration at every scale","year":"2020","key":"ref26"},{"year":"2022","key":"ref27","article-title":"NVIDIA cuBLAS library: User guide"},{"year":"2023","key":"ref28","article-title":"cuSPARSE library"},{"year":"2023","key":"ref29","article-title":"CUTLASS: CUDA templates for linear algebra subroutines and solvers"},{"first-page":"1","article-title":"NVIDIA H100 tensor core GPU architecture: Exceptional performance, scalability, and security for the data center","year":"2023","key":"ref30"},{"year":"2024","key":"ref31","article-title":"NVIDIA CUDA C++ programing guide"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638470"},{"key":"ref33","first-page":"1","article-title":"Geom-GCN: Geometric graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pei"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2742839"},{"volume-title":"Natural Language Processing and Computational Linguistics: A Practical Guide to Text Analysis With Python, Gensim, SpaCy, and Keras","year":"2018","author":"Srinivasa-Desikan","key":"ref37"},{"key":"ref38","first-page":"2020","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Velickovic"},{"key":"ref39","first-page":"1","article-title":"Deep graph library: Towards efficient and scalable deep learning on graphs","volume-title":"Proc. Workshop Representation Learn. Graphs Manifolds Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref40","first-page":"515","article-title":"GNNAdvisor: An adaptive and efficient runtime system for GNN acceleration on GPUs","volume-title":"Proc. USENIX Symp. Operating Syst. Des. Implementation","author":"Wang"},{"key":"ref41","first-page":"149","article-title":"TC-GNN: Bridging sparse GNN computation and dense tensor cores on GPUs","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Wang"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915220"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/18.133259"},{"key":"ref44","first-page":"9104","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00071"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00012"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071102"},{"key":"ref49","first-page":"1","article-title":"GraphSAINT: Graph sampling based inductive learning method","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zeng"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/10960276\/10916722.pdf?arnumber=10916722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T17:19:37Z","timestamp":1744305577000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10916722\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":49,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2025.3549180","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"type":"print","value":"1045-9219"},{"type":"electronic","value":"1558-2183"},{"type":"electronic","value":"2161-9883"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}