{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T04:09:18Z","timestamp":1743826158298,"version":"3.40.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:00:00Z","timestamp":1727049600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:00:00Z","timestamp":1727049600000},"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":[[2024,9,23]]},"DOI":"10.1109\/hpec62836.2024.10938448","type":"proceedings-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T19:07:19Z","timestamp":1743707239000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Towards Just-in-Time Instruction Generation for Accelerated Sparse Matrix-Matrix Multiplication on GPUs"],"prefix":"10.1109","author":[{"given":"Seth David","family":"Kay","sequence":"first","affiliation":[{"name":"George Washington University,GraphLab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"H. Howie","family":"Huang","sequence":"additional","affiliation":[{"name":"George Washington University,GraphLab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icct.2017.8359956"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3544559"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12190"},{"journal-title":"Segmented Operations for Sparse Matrix Computation on Vector Multiprocessors","year":"1993","author":"Blelloch","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/18m1210691"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/0613024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/sc41405.2020.00076"},{"key":"ref9","article-title":"Optimizing sparse matrix multiplications for graph neural networks","volume-title":"International Workshop on Languages and Compilers for Parallel Computing. Cham: Springer International Publishing","author":"Shenghao","year":"2021"},{"key":"ref10","first-page":"185876","volume":"26","author":"Youcef","year":"1990","journal-title":"SPARSKIT: A basic tool kit for sparse matrix computations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CGO57630.2024.10444827"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1583991.1584053"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS51385.2021.00016"},{"volume-title":"Overview -Numba documentation","year":"2024","key":"ref14"},{"article-title":"How to Optimize Data Transfers in CUDA C\/C++","volume-title":"NVIDIA Technical Blog","year":"2024","key":"ref15"},{"article-title":"Using Shared Memory in CUDA C\/C++","volume-title":"NVIDIA Technical Blog","year":"2024","key":"ref16"},{"volume-title":"NVIDIA Profiler","year":"2024","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2017.8091036"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1145\/3676847","article-title":"Optimization of Large-Scale Sparse Matrix-Vector Multiplication on Multi-GPU Systems","volume-title":"ACM Trans. Archit. Code Optim. Just Accepted","author":"Gao","year":"2024"},{"issue":"3","key":"ref20","first-page":"253","article-title":"DTC-SpMM: Bridging the Gap in Accelerating General Sparse Matrix Multiplication with Tensor Cores","volume-title":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","volume":"3","author":"Fan","year":"2024"},{"key":"ref21","first-page":"41","article-title":"Falcon: Scaling IO Performance in multi-SSD Volumes","volume-title":"Proceedings of the 2017 USENIX Conference on Usenix Annual Technical Conference. USENIX Association","author":"Kumar"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2618791"}],"event":{"name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","start":{"date-parts":[[2024,9,23]]},"location":"Wakefield, MA, USA","end":{"date-parts":[[2024,9,27]]}},"container-title":["2024 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10938401\/10938415\/10938448.pdf?arnumber=10938448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T11:25:52Z","timestamp":1743765952000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10938448\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,23]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/hpec62836.2024.10938448","relation":{},"subject":[],"published":{"date-parts":[[2024,9,23]]}}}