{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T20:32:23Z","timestamp":1783715543232,"version":"3.55.0"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T00:00:00Z","timestamp":1731801600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T00:00:00Z","timestamp":1731801600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,17]]},"DOI":"10.1109\/sc41406.2024.00060","type":"proceedings-article","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T19:09:21Z","timestamp":1735067361000},"page":"1-14","source":"Crossref","is-referenced-by-count":11,"title":["High Performance Unstructured SpMM Computation Using Tensor Cores"],"prefix":"10.1109","author":[{"given":"Patrik","family":"Okanovic","sequence":"first","affiliation":[{"name":"ETH Zurich,Department of Computer Science,Zurich,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Grzegorz","family":"Kwasniewski","sequence":"additional","affiliation":[{"name":"ETH Zurich,Department of Computer Science,Zurich,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo Sylos","family":"Labini","sequence":"additional","affiliation":[{"name":"Free University of Bozen-Bolzano,Faculty of Engineering,Bolzano,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maciej","family":"Besta","sequence":"additional","affiliation":[{"name":"ETH Zurich,Department of Computer Science,Zurich,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Flavio","family":"Vella","sequence":"additional","affiliation":[{"name":"University of Trento,Trento,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"ETH Zurich,Department of Computer Science,Zurich,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926299"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719581"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2008.45"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.93"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3078597.3078616"},{"key":"ref7","first-page":"1","article-title":"Scaling betweenness centrality using communication-efficient sparse matrix multiplication","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (ACM\/IEEE Supercomputing)","author":"Solomonik"},{"key":"ref8","article-title":"Graph processing on fpgas: Taxonomy, survey, challenges","author":"Besta","year":"2019","journal-title":"arXiv preprint arXiv:1903.06697"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3477141"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3303431"},{"key":"ref12","article-title":"Cached operator reordering: A unified view for fast gnn training","author":"Bazinska","year":"2023","journal-title":"arXiv preprint arXiv:2308.12093"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607067"},{"issue":"1","key":"ref14","first-page":"10882","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler","year":"2021","journal-title":"The Journal of Machine Learning Research"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298681"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414654"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3017994"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00042"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607051"},{"key":"ref20","article-title":"Cusparse library","volume-title":"GPU Technology Conference","author":"Naumov"},{"key":"ref21","first-page":"1","article-title":"Efficient tensor corebased gpu kernels for structured sparsity under reduced precision","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Chen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607087"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356181"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01759-9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.15"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476252"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2016.42"},{"key":"ref28","volume-title":"How to optimize a cuda matmul kernel for cublas-like performance: a worklog","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/0713020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/s1064827501393393"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3571808"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD50377.2020.00105"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IA356718.2022.00009"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC55196.2022.9952814"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01244"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1188455.1188677"},{"key":"ref37","article-title":"A cellular computer to implement the Kalman filter algorithm","author":"Cannon","year":"1969"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1147\/rd.395.0575"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3331057"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532392"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/Cluster48925.2021.00035"},{"key":"ref43","first-page":"157","author":"Cuthill","year":"1972","journal-title":"Several Strategies for Reducing the Bandwidth of Matrices."},{"issue":"8","key":"ref44","doi-asserted-by":"crossref","first-page":"858","DOI":"10.1016\/j.parco.2005.04.012","article-title":"Performance optimization of irregular codes based on the combination of reordering and blocking techniques","volume":"31","author":"Pichel","year":"2005","journal-title":"Parallel Computing"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IA356718.2022.00009"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2017.00039"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6515"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.69"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3399732"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2016.64"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00071"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-008-0251-8"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3571157"},{"key":"ref54","article-title":"cusparselt documentation","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476182"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/iccd58817.2023.00076"}],"event":{"name":"SC24: International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Atlanta, GA, USA","start":{"date-parts":[[2024,11,17]]},"end":{"date-parts":[[2024,11,22]]}},"container-title":["SC24: International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx8\/10793057\/10793058\/10793184.pdf?arnumber=10793184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T06:37:29Z","timestamp":1735108649000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/10793184\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,17]]},"references-count":57,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/sc41406.2024.00060","relation":{},"subject":[],"published":{"date-parts":[[2024,11,17]]}}}