{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:08:24Z","timestamp":1781885304667,"version":"3.54.5"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"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":[[2021,11,1]]},"DOI":"10.1109\/iccad51958.2021.9643582","type":"proceedings-article","created":{"date-parts":[[2021,12,23]],"date-time":"2021-12-23T23:06:46Z","timestamp":1640300806000},"page":"1-9","source":"Crossref","is-referenced-by-count":70,"title":["GraphLily: Accelerating Graph Linear Algebra on HBM-Equipped FPGAs"],"prefix":"10.1109","author":[{"given":"Yuwei","family":"Hu","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Cornell University,Ithaca,NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixiao","family":"Du","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Cornell University,Ithaca,NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ecenur","family":"Ustun","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Cornell University,Ithaca,NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiru","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Cornell University,Ithaca,NY"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2015.130"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3276491"},{"key":"ref33","article-title":"Graphblast: A highperformance linear algebra-based graph framework on the gpu","author":"yang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM48280.2020.00024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00068"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2015.8"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2017.8257937"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021737"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1344671.1344704"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2006.887921"},{"key":"ref10","article-title":"Powergraph: Distributed graph-parallel computation on natural graphs","author":"gonzalez","year":"0","journal-title":"Proceedings of the 5th USENIX Symposium on Operating Systems Design and Implementation (OSDI)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ReConFig.2015.7393332"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439289"},{"key":"ref12","article-title":"Analysis and optimization of the implicit broadcasts in fpga hls to improve maximum frequency","author":"guo","year":"2020","journal-title":"Design Automation Conf (DAC)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"ref14","article-title":"Open graph benchmark: Datasets for machine learning on graphs","author":"hu","year":"2020","journal-title":"ar Xiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/FPGA.1993.279483"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2016.7761646"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2012.12"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.2172\/7093021","author":"kincaid","year":"1989","journal-title":"ITPACKV 2D User's Guide"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/FPGA.1993.279478"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522740"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2012.25"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847265"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.50"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3186728.3164139"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439290"},{"key":"ref8","article-title":"Graph algorithms via suitesparse:graphblas: triangle counting and k-truss","author":"davis","year":"2018","journal-title":"IEEE High Performance Extreme Computing Conf (HPEC)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071131"},{"key":"ref2","article-title":"Fgpu: An simt-architecture for fpgas","author":"kadi","year":"0","journal-title":"Proc Int Symp Field Programmable Gate Arrays (FPGA)"},{"key":"ref9","article-title":"A high memory bandwidth fpga accelerator for sparse matrix-vector multiplication","author":"jeremy","year":"0","journal-title":"Field-Programmable Custom Computing Machines (FCCM)"},{"key":"ref1","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2818185"},{"key":"ref22","article-title":"Graphgen: An fpga framework for vertex-centric graph computation","author":"eriko","year":"0","journal-title":"Field-Programmable Custom Computing Machines (FCCM)"},{"key":"ref21","article-title":"Streambox-hbm: Stream analytics on high bandwidth hybrid memory","author":"hongyu","year":"2019","journal-title":"Architectural Support for Programming Languages and Operating Systems (A SPL OS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2960480"},{"key":"ref41","article-title":"Hitgraph: High-throughput graph processing framework on fpga","author":"shijie","year":"2019","journal-title":"IEEE Trans on Parallel and Distributed Systems (TPDS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847337"},{"key":"ref26","article-title":"A reconfigurable fabric for accelerating large-scale datacenter services","author":"andrew","year":"0","journal-title":"Int'l Symp on Computer Architecture (ISCA)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1993498.1993501"}],"event":{"name":"2021 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","location":"Munich, Germany","start":{"date-parts":[[2021,11,1]]},"end":{"date-parts":[[2021,11,4]]}},"container-title":["2021 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9643423\/9643432\/09643582.pdf?arnumber=9643582","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T08:57:53Z","timestamp":1674205073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9643582\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,1]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iccad51958.2021.9643582","relation":{},"subject":[],"published":{"date-parts":[[2021,11,1]]}}}