{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:43:05Z","timestamp":1783784585881,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ESF Investing in your future","award":["RYC-2017- 23269"],"award-info":[{"award-number":["RYC-2017- 23269"]}]},{"name":"MCIN\/AEI\/10.13039\/501100011033","award":["PID2019-107255GB-C21"],"award-info":[{"award-number":["PID2019-107255GB-C21"]}]},{"name":"Departament de Recerca i Universitats de la Generalitat de Catalunya","award":["2021 SGR 00865"],"award-info":[{"award-number":["2021 SGR 00865"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,3]]},"DOI":"10.1145\/3625549.3658683","type":"proceedings-article","created":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T15:55:29Z","timestamp":1725033329000},"page":"200-213","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Extending Sparse Patterns to Improve Inverse Preconditioning on GPU Architectures"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8727-0518","authenticated-orcid":false,"given":"Sergi","family":"Laut","sequence":"first","affiliation":[{"name":"Computer Sciences, Barcelona Supercomputing Center, Barcelona, Catalunya, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3747-7104","authenticated-orcid":false,"given":"Ricard","family":"Borrell","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center, Barcelona, Catalunya, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4564-2093","authenticated-orcid":false,"given":"Marc","family":"Casas","sequence":"additional","affiliation":[{"name":"Computer Sciences, Barcelona Supercomputing Center, Barcelona, Catalunya, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,30]]},"reference":[{"issue":"1","key":"e_1_3_2_1_1_1","first-page":"1","volume":"5","year":"2022","unstructured":"2022. ROCm Release: 5.1.1. https:\/\/docs.amd.com\/category\/ROCm_v5.1.1","journal-title":"ROCm Release"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019170609950"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Hartwig Anzt Edmond Chow Thomas Huckle and Jack Dongarra. 2016. Batched Generation of Incomplete Sparse Approximate Inverses on GPUs. 49--56. 10.1109\/ScalA.2016.011","DOI":"10.1109\/ScalA.2016.011"},{"key":"e_1_3_2_1_5_1","volume-title":"Dongarra","author":"Anzt Hartwig","year":"2014","unstructured":"Hartwig Anzt, Stanimire Tomov, and Jack J. Dongarra. 2014. Implementing a Sparse Matrix Vector Product for the SELL-C \/ SELL-C-\u03c3 formats on NVIDIA GPUs."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971538"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.112"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654078"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827594271421"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1137\/15M1027826"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1137\/18M1197461"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2015.12.008"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926278"},{"key":"e_1_3_2_1_14_1","volume-title":"Explicit caching HYB: a new high-performance SpMV framework on GPGPU. (04","author":"Chen Chong","year":"2022","unstructured":"Chong Chen. 2022. Explicit caching HYB: a new high-performance SpMV framework on GPGPU. (04 2022)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2018.00116"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1137\/S106482759833913X"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1177\/109434200101500106"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827594270415"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-044481999-4\/50173-0"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1984-0758197-9"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5402\/2012\/127647"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/898758"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2014.08.022"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1017\/flo.2021.17"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827594276552"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-02427-0"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5598"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1137\/100810368"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1137\/100810368"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1137\/090779760"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/nla.2080"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/nla.614"},{"key":"e_1_3_2_1_34_1","volume-title":"Version 2.0. (01","author":"Karypis George","year":"1995","unstructured":"George Karypis and Vipin Kumar. 1995. METIS - Unstructured Graph Partitioning and Sparse Matrix Ordering System, Version 2.0. (01 1995)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-1506(199910\/11)6:73.0.CO;2-0"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1137\/0614004"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1137\/130930352"},{"key":"e_1_3_2_1_38_1","unstructured":"I.B. Labutin and I.V. Surodina. 2013. Algorithm for sparse approximate inverse preconditioners in the conjugate gradient method. 19 (01 2013) 120--126."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3431379.3460642"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531472"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","unstructured":"Oriol Lehmkuhl Ivette Rodriguez and R. Borrell. 2020. Effect of the Actuation on the Boundary Layer of an Airfoil at Moderate Reynolds Number. 313--319. 10.1007\/978-3-030-42822-8_41","DOI":"10.1007\/978-3-030-42822-8_41"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1137\/120872735"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-012-0825-3"},{"key":"e_1_3_2_1_44_1","first-page":"2063","article-title":"VBSF: a new storage format for SIMD sparse matrix-vector multiplication on modern processors","volume":"76","author":"Li Yishui","year":"2019","unstructured":"Yishui Li, Peizhen Xie, Xinhai Chen, Jie Liu, Bo Yang, Shengguo Li, Chunye Gong, Xinbiao Gan, and Han Xu. 2019. VBSF: a new storage format for SIMD sparse matrix-vector multiplication on modern processors. The Journal of Supercomputing 76 (2019), 2063--2081. https:\/\/api.semanticscholar.org\/CorpusID:106410121","journal-title":"The Journal of Supercomputing"},{"key":"e_1_3_2_1_45_1","volume-title":"CSR5: An Efficient Storage Format for Cross-Platform Sparse Matrix-Vector Multiplication. CoRR abs\/1503.05032","author":"Liu Weifeng","year":"2015","unstructured":"Weifeng Liu and Brian Vinter. 2015. CSR5: An Efficient Storage Format for Cross-Platform Sparse Matrix-Vector Multiplication. CoRR abs\/1503.05032 (2015). arXiv:1503.05032 http:\/\/arxiv.org\/abs\/1503.05032"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465013"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.57"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/PADSW.2014.7097819"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1137\/140980260"},{"key":"e_1_3_2_1_50_1","volume-title":"Fitzek","author":"P\u00e9ter Vingelmann NVIDIA","year":"2020","unstructured":"NVIDIA, P\u00e9ter Vingelmann, and Frank H.P. Fitzek. 2020. CUDA, release: 10.2.89. https:\/\/developer.nvidia.com\/cuda-toolkit"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compfluid.2013.10.035"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the international workshop on solution techniques for large-scale CFD problems (02","author":"Saad Yousef","year":"2002","unstructured":"Yousef Saad. 2002. Preconditioned Krylov Subspace Methods for CFD Applications. Proceedings of the international workshop on solution techniques for large-scale CFD problems (02 2002)."},{"key":"e_1_3_2_1_53_1","volume-title":"Iterative Methods for Sparse Linear Systems","author":"Saad Yousef","unstructured":"Yousef Saad. 2003. Iterative Methods for Sparse Linear Systems (2nd ed.). Society for Industrial and Applied Mathematics, USA.","edition":"2"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079086"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.finel.2010.11.005"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555255"}],"event":{"name":"HPDC '24: 33rd International Symposium on High-Performance Parallel and Distributed Computing","location":"Pisa Italy","acronym":"HPDC '24","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3625549.3658683","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3625549.3658683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:38Z","timestamp":1750287038000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3625549.3658683"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,3]]},"references-count":55,"alternative-id":["10.1145\/3625549.3658683","10.1145\/3625549"],"URL":"https:\/\/doi.org\/10.1145\/3625549.3658683","relation":{},"subject":[],"published":{"date-parts":[[2024,6,3]]},"assertion":[{"value":"2024-08-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}