{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T05:40:05Z","timestamp":1743572405872,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031856969","type":"print"},{"value":"9783031856976","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-85697-6_4","type":"book-chapter","created":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T05:07:00Z","timestamp":1743570420000},"page":"51-64","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sparse Matrix Ordering for\u00a0Fine Grain Parallel Triangular Solve Using SIMD"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9464-359X","authenticated-orcid":false,"given":"Aboul-Karim Mohamed El","family":"Maarouf","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luc","family":"Giraud","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdou","family":"Guermouche","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Guignon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,1]]},"reference":[{"key":"4_CR1","unstructured":"Anciaux-Sedrakian, A., Gayno, R., Guignon, T., Mohamed El\u00a0Maarouf, A.K.: Performance evaluation for solving large sparse linear systems on arm and x86 architectures (2024)"},{"key":"4_CR2","unstructured":"Anzt, H., Tomov, S., Dongarra, J.: Implementing a Sparse Matrix Vector Product for the SELL-C\/SELL-C-Sigma formats on NVIDIA GPUs. Technical report, UT-EECS-14-727 (2014-04 2014). https:\/\/www.icl.utk.edu\/files\/publications\/2014\/icl-utk-772-2014.pdf"},{"key":"4_CR3","unstructured":"Benzi, M., Joubert, W., Mateescu, G.: Numerical experiments with parallel orderings for ILU preconditioners. Electron. Trans. Numer. Anal. 8, 88\u2013114 (1999). http:\/\/etna.mcs.kent.edu\/volumes\/1993-2000\/vol8\/abstract.php?vol=8&pages=88-114"},{"key":"4_CR4","doi-asserted-by":"publisher","unstructured":"Benzi, M., Szyld, D.B., van Duin, A.: Orderings for incomplete factorization preconditioning of nonsymmetric problems. SIAM J. Sci. Comput. 20(5), 1652\u20131670 (1999). https:\/\/doi.org\/10.1137\/S1064827597326845","DOI":"10.1137\/S1064827597326845"},{"key":"4_CR5","doi-asserted-by":"publisher","unstructured":"Chow, E., Saad, Y.: Experimental study of ILU preconditioners for indefinite matrices. J. Comput. Appl. Math. 86(2), 387\u2013414 (1997). https:\/\/doi.org\/10.1016\/S0377-0427(97)00171-4, http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0377042797001714","DOI":"10.1016\/S0377-0427(97)00171-4"},{"key":"4_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/s101070100263","author":"ED Dolan","year":"2001","unstructured":"Dolan, E.D., Mor\u00e9, J.J.: Benchmarking optimization software with performance profiles. Math. Program. (2001). https:\/\/doi.org\/10.1007\/s101070100263","journal-title":"Math. Program."},{"issue":"4","key":"4_CR7","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1007\/BF01932738","volume":"29","author":"IS Duff","year":"1989","unstructured":"Duff, I.S., Meurant, G.A.: The effect of ordering on preconditioned conjugate gradients. BIT Numer. Math. 29(4), 635\u2013657 (1989). https:\/\/doi.org\/10.1007\/BF01932738","journal-title":"BIT Numer. Math."},{"key":"4_CR8","doi-asserted-by":"publisher","unstructured":"Erguiz, D., Dufrechou, E., Ezzatti, P.: Assessing sparse triangular linear system solvers on GPUs. In: 2017 International Symposium on Computer Architecture and High Performance Computing Workshops (SBAC-PADW), pp. 37\u201342 (2017). https:\/\/doi.org\/10.1109\/SBAC-PADW.2017.15","DOI":"10.1109\/SBAC-PADW.2017.15"},{"key":"4_CR9","unstructured":"Iwashita, T., Li, S., Fukaya, T.: Hierarchical block multi-color ordering: a new parallel ordering method for vectorization and parallelization of the sparse triangular solver in the ICCG method. CoRR abs\/1908.007410 (2019). http:\/\/arxiv.org\/abs\/1908.00741"},{"issue":"2","key":"4_CR10","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/s00493-010-2483-5","volume":"30","author":"HA Kierstead","year":"2010","unstructured":"Kierstead, H.A., Kostochka, A.V., Mydlarz, M., Szemer\u00e9di, E.: A fast algorithm for equitable coloring. Combinatorica 30(2), 217\u2013224 (2010). https:\/\/doi.org\/10.1007\/s00493-010-2483-5","journal-title":"Combinatorica"},{"issue":"5","key":"4_CR11","doi-asserted-by":"publisher","first-page":"C401","DOI":"10.1137\/130930352","volume":"36","author":"M Kreutzer","year":"2014","unstructured":"Kreutzer, M., Hager, G., Wellein, G., Fehske, H., Bishop, A.R.: A unified sparse matrix data format for efficient general sparse matrix-vector multiplication on modern processors with wide SIMD units. SIAM J. Sci. Comput. 36(5), C401\u2013C423 (2014). https:\/\/doi.org\/10.1137\/130930352","journal-title":"SIAM J. Sci. Comput."},{"key":"4_CR12","unstructured":"Lee, V.: AVX512 slower than AVX2 with Intel MKL DGEMM on Intel Gold 5118, July 2019. https:\/\/community.intel.com\/t5\/Software-Tuning-Performance\/AVX512-slower-than-AVX2-with-Intel-MKL-dgemm-on-Intel-Gold-5118\/td-p\/1135951"},{"key":"4_CR13","unstructured":"Mohamed El\u00a0Maarouf, A.K.: Factorisation incompl\u00e8te et r\u00e9solution de syst\u00e8mes triangulaires pour des machines exploitant un parall\u00e9lisme \u00e0 grain fin. Theses, Universit\u00e9 de Bordeaux, March 2023. https:\/\/theses.hal.science\/tel-04429547"},{"key":"4_CR14","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/978-1-4613-9353-5_11","volume-title":"Recent Advances in Iterative Methods","author":"Y Saad","year":"1994","unstructured":"Saad, Y.: Highly parallel preconditioners for general sparse matrices. In: Golub, G., Luskin, M., Greenbaum, A. (eds.) Recent Advances in Iterative Methods, pp. 165\u2013199. Springer, New York (1994). https:\/\/doi.org\/10.1007\/978-1-4613-9353-5_11"},{"key":"4_CR15","doi-asserted-by":"publisher","unstructured":"Saad, Y.: Iterative Methods for Sparse Linear Systems. Second Edition. SIAM (2003). https:\/\/doi.org\/10.1137\/1.9780898718003","DOI":"10.1137\/1.9780898718003"},{"key":"4_CR16","unstructured":"Schreiber, R., Tang, W.P.: Vectorizing the conjugate gradient method. In: Symposium of CYBER 205 Applications (1982)"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-85697-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T05:07:13Z","timestamp":1743570433000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-85697-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031856969","9783031856976"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-85697-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PPAM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel Processing and Applied Mathematics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ostrava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ppam2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ppam.edu.pl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}