{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T20:45:34Z","timestamp":1774989934247,"version":"3.50.1"},"reference-count":102,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/hpca68181.2026.11408516","type":"proceedings-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:47:22Z","timestamp":1772657242000},"page":"1-17","source":"Crossref","is-referenced-by-count":0,"title":["AutoGNN: End-to-End Hardware-Driven Graph Preprocessing for Enhanced GNN Performance"],"prefix":"10.1109","author":[{"given":"Seungkwan","family":"Kang","sequence":"first","affiliation":[{"name":"Computer Architecture and Memory Systems Laboratory, KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungjun","family":"Lee","sequence":"additional","affiliation":[{"name":"Computer Architecture and Memory Systems Laboratory, KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghyun","family":"Gouk","sequence":"additional","affiliation":[{"name":"Panmnesia, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miryeong","family":"Kwon","sequence":"additional","affiliation":[{"name":"Panmnesia, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyunkyu","family":"Choi","sequence":"additional","affiliation":[{"name":"Panmnesia, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhyeok","family":"Jang","sequence":"additional","affiliation":[{"name":"Panmnesia, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangwon","family":"Lee","sequence":"additional","affiliation":[{"name":"Panmnesia, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiwon","family":"Choi","sequence":"additional","affiliation":[{"name":"Computer Architecture and Memory Systems Laboratory, KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wonil","family":"Choi","sequence":"additional","affiliation":[{"name":"Hanyang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahmut Taylan","family":"Kandemir","sequence":"additional","affiliation":[{"name":"Pennsylvania State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Myoungsoo","family":"Jung","sequence":"additional","affiliation":[{"name":"Computer Architecture and Memory Systems Laboratory, KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gengnn: A generic fpga framework for graph neural network acceleration","author":"Abi-Karam","year":"2022","journal-title":"ArXiv, vol. abs\/2201.08475"},{"key":"ref2","volume-title":"A faster radix sort implementation","author":"Adinets","year":"2020"},{"key":"ref3","volume-title":"User behavior data from taobao for recommendation","year":"2018"},{"key":"ref4","volume-title":"Vpk180 evaluation board user guide","year":"2023"},{"key":"ref5","volume-title":"Amd kintex ultrascale fpga","year":"2025"},{"key":"ref6","volume-title":"Xilinx sorting application user guide","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3071274"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975499.2"},{"key":"ref9","author":"Blelloch","year":"1990","journal-title":"Prefix sums and their applications"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456233"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3314044"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00039"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM57271.2023.00029"},{"key":"ref14","first-page":"941","article-title":"Stochastic training of graph convolutional networks with variance reduction","volume-title":"in Proceedings of the 35th International Conference on Machine Learning, ICML2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10\u201315, 2018, ser. Proceedings of Machine Learning Research","volume":"80","author":"Chen"},{"key":"ref15","article-title":"Fastgcn: Fast learning with graph convolutional networks via importance sampling","author":"Chen","year":"2018","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689068"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3079142"},{"key":"ref18","first-page":"1","article-title":"fusegnn: Accelerating graph convolutional neural network training on gpgpu","volume-title":"in Proceedings of the 39th International Conference on Computer-Aided Design","author":"Chen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/s0097539702403098"},{"key":"ref20","volume-title":"Graphs and graph representations","year":"2020"},{"key":"ref21","article-title":"A comprehensive study on large-scale graph training: Benchmarking and rethinking","author":"Duan","year":"2022","journal-title":"ArXiv, vol. abs\/2210.07494"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186183"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313488"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3008732"},{"key":"ref25","article-title":"Fast graph representation learning with pytorch geometric","author":"Fey","year":"2019","journal-title":"arXiv preprint"},{"key":"ref26","first-page":"310","article-title":"Mega evolving graph accelerator","volume-title":"in Proceedings of the 56th Annual IEEE\/ACM International Symposium on Microarchitecture","author":"Gao"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00079"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613168"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP61560.2024.00026"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/asap61560.2024.00026"},{"key":"ref31","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"in Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref32","article-title":"Graph neural networks with continual learning for fake news detection from social media","author":"Han","year":"2020","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/dac63849.2025.11132631"},{"key":"ref34","article-title":"Parallel prefix sum (scan) with cuda","volume":"3","author":"Harris","year":"2007","journal-title":"GPU Gems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"ref36","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","author":"Hoefler","year":"2021","journal-title":"ArXiv, vol. abs\/2102.00554"},{"key":"ref37","article-title":"Leskovec, and Jure, \u201cOpen graph benchmark: Datasets for machine learning on graphs","author":"Weihua","year":"2020","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00076"},{"key":"ref39","first-page":"4563","article-title":"Adaptive sampling towards fast graph representation learning","volume-title":"in Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3\u20138, 2018","author":"Huang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3044343"},{"key":"ref41","volume-title":"Maximizing performance with massively parallel hash maps on gpus","author":"Juenger","year":"2023"},{"key":"ref42","article-title":"Accelerating training and inference of graph neural networks with fast sampling and pipelining","author":"Kaler","year":"2021","journal-title":"ArXiv, vol. abs\/2110.08450"},{"key":"ref43","article-title":"Accelerating training and inference of graph neural networks with fast sampling and pipelining","volume-title":"in Proceedings of the Fifth Conference on Machine Learning and Systems, MLSys2022, Santa Clara, CA, USA, August 29 - September 1, 2022","author":"Kaler"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2022.3197083"},{"key":"ref45","author":"Kipf","year":"2017","journal-title":"Semi-supervised classification with graph convolutional networks"},{"key":"ref46","article-title":"Partitioning schemes for quicksort and quickselect","author":"Kiwiel","year":"2003","journal-title":"ArXiv, vol. cs.DS\/0312054"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1950413.1950427"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2009.5377616"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626497000292"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403258"},{"key":"ref51","volume-title":"SNAP Datasets: Stanford large network dataset collection","author":"Leskovec","year":"2014"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527439"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527439"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00018"},{"key":"ref55","first-page":"1","article-title":"Deepburning-gl: an automated framework for generating graph neural network accelerators","volume-title":"in Proceedings of the 39th International Conference on Computer-Aided Design","author":"Liang"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.3014632"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557084"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004311"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26419-1_30"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2015.7168848"},{"key":"ref61","first-page":"443","article-title":"\\{NeuGraph\\}: Parallel deep neural network computation on large graphs","volume-title":"in 2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Ma"},{"key":"ref62","volume-title":"Dynamic dma mapping guide","author":"Miller"},{"key":"ref63","article-title":"Fastsample: Accelerating distributed graph neural network training for billion-scale graphs","author":"Mostafa","year":"2023","journal-title":"ArXiv, vol. abs\/2311.17847"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1466"},{"key":"ref65","volume-title":"Nvidia ampere ga102 gpu architecture"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ISORC.2017.3"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718003"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2018.00023"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071015"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00178"},{"issue":"2","key":"ref71","first-page":"021001","article-title":"Vlimant, and Jean-Roch, \u201cGraph neural networks in particle physics","volume":"2","author":"Jonathan","year":"2020","journal-title":"Machine Learning: Science and Technology"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2016.34"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710854"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00044"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00074"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3597428"},{"key":"ref77","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv preprint"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3147.3165"},{"key":"ref79","article-title":"Deep graph library: A graph-centric, highly-performant package for graph neural networks","author":"Wang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref80","first-page":"23341","article-title":"How powerful are spectral graph neural networks","volume-title":"in International Conference on Machine Learning, ICML2022, 17\u201323 July 2022, Baltimore, Maryland, USA, ser. Proceedings of Machine Learning Research","volume":"162","author":"Wang"},{"key":"ref81","first-page":"515","article-title":"\\{GNNAdvisor\\}: An adaptive and efficient runtime system for $\\{$ GNN $\\}$ acceleration on \\{GPUs\\}","volume-title":"in 15th USENIX symposium on operating systems design and implementation (OSDI 21)","author":"Wang"},{"key":"ref82","volume-title":"Bus-independent device accesses","author":"Wilcox"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3535101"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2025.3558042"},{"key":"ref86","volume-title":"Logicore ip axi hwicap product specification"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00012"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00041"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449925"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403085"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375312"},{"key":"ref93","article-title":"Graphsaint: Graph sampling based inductive learning method","author":"Zeng","year":"2019","journal-title":"arXiv preprint"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM51124.2021.00012"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP49362.2020.00019"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415539"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446702"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6508"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330686"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539177"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref102","first-page":"1124711","article-title":"Layerdependent importance sampling for training deep and large graph convolutional networks","volume-title":"in Advances in Neural Information Processing Systems32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8\u201314, 2019","author":"Zou"}],"event":{"name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11408404\/11408433\/11408516.pdf?arnumber=11408516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T19:48:22Z","timestamp":1774986502000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408516\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":102,"URL":"https:\/\/doi.org\/10.1109\/hpca68181.2026.11408516","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}