{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T05:08:22Z","timestamp":1782968902636,"version":"3.54.5"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:00:00Z","timestamp":1709337600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:00:00Z","timestamp":1709337600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2127207"],"award-info":[{"award-number":["2127207"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,3,2]]},"DOI":"10.1109\/cgo57630.2024.10444827","type":"proceedings-article","created":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T18:47:35Z","timestamp":1709146055000},"page":"448-459","source":"Crossref","is-referenced-by-count":4,"title":["JITSPMM: Just-in-Time Instruction Generation for Accelerated Sparse Matrix-Matrix Multiplication"],"prefix":"10.1109","author":[{"given":"Qiang","family":"Fu","sequence":"first","affiliation":[{"name":"Advanced Micro Devices Inc.,Austin,TX,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas B.","family":"Rolinger","sequence":"additional","affiliation":[{"name":"NVIDIA,Austin,TX,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H. Howie","family":"Huang","sequence":"additional","affiliation":[{"name":"George Washington University,Washington, DC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3544559"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358275"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582047"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3563338"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1515\/9781400830329"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2007.05.001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3477141"},{"key":"ref9","article-title":"Deep graph library: Towards efficient and scalable deep learning on graphs","volume-title":"ICLR workshop on representation learning on graphs and manifolds","author":"Wang","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531467"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3473511"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599805"},{"key":"ref13","article-title":"Dropedge: Towards deep graph convolutional networks on node classification","author":"Rong","year":"2019","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Link prediction based on graph neural networks","volume":"31","author":"Zhang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"issue":"43","key":"ref16","first-page":"1","article-title":"Benchmarking graph neural networks","volume":"24","author":"Dwivedi","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2017.08.014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-06486-4_7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96983-1_48"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.57"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2012.202"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"ref23","article-title":"Fast graph representation learning with pytorch geometric","author":"Fey","year":"2019","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3461472"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358269"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00076"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxt038"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527403"},{"key":"ref29","first-page":"1025","article-title":"Optimizing CNN model inference on CPUs","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Liu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/248209.237140"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/872726.806984"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.14778\/2735508.2735518"},{"key":"ref33","first-page":"119","article-title":"A just-in-time compiler for memory-constrained low-power devices","volume-title":"Java Virtual Machine Research and Technology Symposium","author":"Shaylor","year":"2002"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840305"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.1998.742769"},{"key":"ref36","volume-title":"Xadd - exchange and add","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.1997.569611"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2006.1620789"},{"key":"ref39","volume-title":"Computer architecture: a quantitative approach","author":"Hennessy","year":"2011"},{"key":"ref40","volume-title":"Intel\u00ae 64 and ia-32 architectures software developer manuals","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-0064-3"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"ref43","volume-title":"Parallel programming in OpenMP","author":"Chandra","year":"2001"},{"key":"ref44","volume-title":"Asmjit project: Low-latency machine code generation","year":"2023"},{"key":"ref45","first-page":"1","article-title":"The new linuxperftools","volume":"18","author":"De Melo","year":"2010","journal-title":"Slides from Linux Kongress"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465013"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00034"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3208040.3208062"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.68"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.69"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.98"},{"key":"ref53","article-title":"Cusparse library","volume-title":"GPU Technology Conference","author":"Naumov","year":"2010"}],"event":{"name":"2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)","location":"Edinburgh, United Kingdom","start":{"date-parts":[[2024,3,2]]},"end":{"date-parts":[[2024,3,6]]}},"container-title":["2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10444766\/10444770\/10444827.pdf?arnumber=10444827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T05:47:11Z","timestamp":1709272031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10444827\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,2]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/cgo57630.2024.10444827","relation":{},"subject":[],"published":{"date-parts":[[2024,3,2]]}}}