{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:55:26Z","timestamp":1776930926520,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","funder":[{"name":"NSERC discovery grants","award":["RGPIN-2023-04897,DGECR-2023-00133"],"award-info":[{"award-number":["RGPIN-2023-04897,DGECR-2023-00133"]}]},{"name":"NSERC alliance grant","award":["ALLRP 58631923"],"award-info":[{"award-number":["ALLRP 58631923"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3712285.3759796","type":"proceedings-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T16:05:39Z","timestamp":1762963539000},"page":"602-616","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Sparsified Preconditioned Conjugate Gradient Solver on GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4708-186X","authenticated-orcid":false,"given":"Da","family":"Ma","sequence":"first","affiliation":[{"name":"McMaster University, Hamilton, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5966-5774","authenticated-orcid":false,"given":"Khalid","family":"Ahmad","sequence":"additional","affiliation":[{"name":"University of Utah, Salt Lake City, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2968-5176","authenticated-orcid":false,"given":"Kazem","family":"Cheshmi","sequence":"additional","affiliation":[{"name":"McMaster University, Hamilton, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9001-5107","authenticated-orcid":false,"given":"Hari","family":"Sundar","sequence":"additional","affiliation":[{"name":"University of Utah, Salt Lake City, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3058-7573","authenticated-orcid":false,"given":"Mary","family":"Hall","sequence":"additional","affiliation":[{"name":"University of Utah, Salt Lake City, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_3_2_2","volume-title":"Data-driven Techniques to Accelerate Sparse Computations on Graphical Processing Units (GPUs)","author":"Ahmad Khalid","year":"2024","unstructured":"Khalid Ahmad. 2024. Data-driven Techniques to Accelerate Sparse Computations on Graphical Processing Units (GPUs). The University of Utah."},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6494992"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"crossref","unstructured":"Edward Anderson and Youcef Saad. 1989. Solving sparse triangular linear systems on parallel computers. International Journal of High Speed Computing 1 01 (1989) 73\u201395.","DOI":"10.1142\/S0129053389000056"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ScalA.2016.011"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00033"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971538"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.5555\/1481537"},{"key":"e_1_3_3_3_9_2","volume-title":"Regression diagnostics: Identifying influential data and sources of collinearity","author":"Belsley David\u00a0A","year":"2005","unstructured":"David\u00a0A Belsley, Edwin Kuh, and Roy\u00a0E Welsch. 2005. Regression diagnostics: Identifying influential data and sources of collinearity. John Wiley & Sons."},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"crossref","unstructured":"Massimo Bernaschi Mauro Carrozzo Andrea Franceschini and Carlo Janna. 2019. A dynamic pattern factored sparse approximate inverse preconditioner on graphics processing units. SIAM Journal on Scientific Computing 41 3 (2019) C139\u2013C160.","DOI":"10.1137\/18M1197461"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"crossref","unstructured":"Wajih Boukaram Stefano Zampini George Turkiyyah and David\u00a0E Keyes. 2024. Cholesky Factorization of Tile Low Rank Matrices on GPUs. (2024).","DOI":"10.1137\/1.9781611977967.6"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"crossref","unstructured":"Yan Chen Xuhong Tian Hui Liu Zhangxin Chen Bo Yang Wenyuan Liao Peng Zhang Ruijian He and Min Yang. 2018. Parallel ILU preconditioners in GPU computation. Soft Computing 22 (2018) 8187\u20138205.","DOI":"10.1007\/s00500-017-2764-7"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.5555\/AAI28774188"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126936"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00065"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607097"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"crossref","unstructured":"Edmond Chow. 2001. Parallel implementation and practical use of sparse approximate inverse preconditioners with a priori sparsity patterns. The International Journal of High Performance Computing Applications 15 1 (2001) 56\u201374.","DOI":"10.1177\/109434200101500106"},{"key":"e_1_3_3_3_18_2","unstructured":"Timothy\u00a0A Davis. 2008. User Guide for CHOLMOD: a sparse Cholesky factorization and modification package. Department of Computer and Information Science and Engineering University of Florida Gainesville FL USA (2008)."},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Timothy\u00a0A Davis and Yifan Hu. 2011. The University of Florida sparse matrix collection. ACM Transactions on Mathematical Software (TOMS) 38 1 (2011) 1\u201325.","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"crossref","unstructured":"Jack Dongarra Michael\u00a0A Heroux and Piotr Luszczek. 2016. High-performance conjugate-gradient benchmark: A new metric for ranking high-performance computing systems. The International Journal of High Performance Computing Applications 30 1 (2016) 3\u201310.","DOI":"10.1177\/1094342015593158"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"crossref","unstructured":"Sergiy\u00a0Yu Fialko and Filip Zeglen. 2016. Preconditioned conjugate gradient method for solution of large finite element problems on CPU and GPU. Journal of Telecommunications and Information Technology2 (2016) 26\u201333.","DOI":"10.26636\/jtit.2016.2.716"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"crossref","unstructured":"Goran Flegar Hartwig Anzt Terry Cojean and Enrique\u00a0S Quintana-Orti. 2021. Adaptive precision block-Jacobi for high performance preconditioning in the Ginkgo linear algebra software. ACM Transactions on Mathematical Software (TOMS) 47 2 (2021) 1\u201328.","DOI":"10.1145\/3441850"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"crossref","unstructured":"Pieter Ghysels and Ryan Synk. 2022. High performance sparse multifrontal solvers on modern GPUs. Parallel Comput. 110 (2022) 102897.","DOI":"10.1016\/j.parco.2022.102897"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-85665-6_34"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Nicholas\u00a0J Higham and Theo Mary. 2022. Mixed precision algorithms in numerical linear algebra. Acta Numerica 31 (2022) 347\u2013414.","DOI":"10.1017\/S0962492922000022"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ScalA54577.2021.00006"},{"key":"e_1_3_3_3_27_2","volume-title":"Proceedings of the 2020 USENIX Annual Technical Conference (USENIX ATC \u201920)","author":"Keahey Kate","year":"2020","unstructured":"Kate Keahey, Jason Anderson, Zhuo Zhen, Pierre Riteau, Paul Ruth, Dan Stanzione, Mert Cevik, Jacob Colleran, Haryadi\u00a0S. Gunawi, Cody Hammock, Joe Mambretti, Alexander Barnes, Fran\u00e7ois Halbach, Alex Rocha, and Joe Stubbs. 2020. Lessons Learned from the Chameleon Testbed. In Proceedings of the 2020 USENIX Annual Technical Conference (USENIX ATC \u201920). USENIX Association."},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"crossref","unstructured":"Daniel Kressner Yuxin Ma and Meiyue Shao. 2023. A mixed precision LOBPCG algorithm. Numerical Algorithms 94 4 (2023) 1653\u20131671.","DOI":"10.1007\/s11075-023-01550-9"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2897518.2897640"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3625549.3658683"},{"key":"e_1_3_3_3_31_2","unstructured":"Yin\u00a0Tat Lee Richard Peng and Daniel\u00a0A Spielman. 2015. Sparsified cholesky solvers for SDD linear systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1506.08204 (2015)."},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"crossref","unstructured":"Xiaoye\u00a0S Li. 2005. An overview of SuperLU: Algorithms implementation and user interface. ACM Transactions on Mathematical Software (TOMS) 31 3 (2005) 302\u2013325.","DOI":"10.1145\/1089014.1089017"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"crossref","unstructured":"Neil Lindquist Piotr Luszczek and Jack Dongarra. 2021. Accelerating restarted GMRES with mixed precision arithmetic. IEEE Transactions on Parallel and Distributed Systems 33 4 (2021) 1027\u20131037.","DOI":"10.1109\/TPDS.2021.3090757"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374548"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-43659-3_45"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404413"},{"key":"e_1_3_3_3_37_2","unstructured":"Maxim Naumov. 2011. Parallel solution of sparse triangular linear systems in the preconditioned iterative methods on the GPU. NVIDIA Corp. Westford MA USA Tech. Rep. NVR-2011 1 (2011)."},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-07518-1_8"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/2591796.2591832"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"crossref","unstructured":"Hadi Pouransari Pieter Coulier and Eric Darve. 2017. Fast hierarchical solvers for sparse matrices using extended sparsification and low-rank approximation. SIAM Journal on Scientific Computing 39 3 (2017) A797\u2013A830.","DOI":"10.1137\/15M1046939"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.5555\/829576"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404400"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD63648.2024.00015"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCET.2018.8542314"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126921"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00121"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"crossref","unstructured":"Haoyuan Zhang Wenpeng Ma Wu Yuan Jian Zhang and Zhonghua Lu. 2024. Mixed-precision block incomplete sparse approximate preconditioner on Tensor core. CCF Transactions on High Performance Computing 6 1 (2024) 54\u201367.","DOI":"10.1007\/s42514-023-00165-9"}],"event":{"name":"SC '25: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St. Louis MO USA","acronym":"SC '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:54:28Z","timestamp":1773255268000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712285.3759796"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":46,"alternative-id":["10.1145\/3712285.3759796","10.1145\/3712285"],"URL":"https:\/\/doi.org\/10.1145\/3712285.3759796","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}