{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T03:40:56Z","timestamp":1742960456312,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319589428"},{"type":"electronic","value":"9783319589435"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-58943-5_7","type":"book-chapter","created":{"date-parts":[[2017,5,27]],"date-time":"2017-05-27T08:42:07Z","timestamp":1495874527000},"page":"83-95","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Task-Based Sparse Hybrid Linear Solver for Distributed Memory Heterogeneous Architectures"],"prefix":"10.1007","author":[{"given":"Emmanuel","family":"Agullo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luc","family":"Giraud","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stojce","family":"Nakov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,5,28]]},"reference":[{"key":"7_CR1","unstructured":"MAGMA Users\u2019 Guide, version 0.2, November 2009. http:\/\/icl.cs.utk.edu\/magma"},{"key":"7_CR2","unstructured":"PLASMA Users\u2019 Guide: Parallel Linear Algebra Software for Multicore Architectures, Version 2.0, November 2009. http:\/\/icl.cs.utk.edu\/plasma"},{"issue":"2\u20133","key":"7_CR3","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.crme.2010.11.005","volume":"339","author":"E Agullo","year":"2011","unstructured":"Agullo, E., Giraud, L., Guermouche, A., Roman, J.: Parallel hierarchical hybrid linear solvers for emerging computing platforms. C. R. Acad. Sci. Mec. 339(2\u20133), 96\u2013105 (2011)","journal-title":"C. R. Acad. Sci. Mec."},{"key":"7_CR4","unstructured":"Agullo, E., Augonnet, C., Dongarra, J., Ltaief, H., Namyst, R., Thibault, S., Tomov, S.: Faster, cheaper, better - a hybridization methodology to develop linear algebra software for GPUs. In: Hwu, W.W. (ed.) GPU Computing Gems, vol. 2. Morgan Kaufmann, September 2010"},{"key":"7_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1007\/978-3-642-40047-6_53","volume-title":"Euro-Par 2013 Parallel Processing","author":"E Agullo","year":"2013","unstructured":"Agullo, E., Buttari, A., Guermouche, A., Lopez, F.: Multifrontal QR factorization for multicore architectures over runtime systems. In: Wolf, F., Mohr, B., Mey, D. (eds.) Euro-Par 2013. LNCS, vol. 8097, pp. 521\u2013532. Springer, Heidelberg (2013). doi:10.1007\/978-3-642-40047-6_53"},{"key":"7_CR6","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1145\/2898348","volume":"43","author":"E Agullo","year":"2016","unstructured":"Agullo, E., Buttari, A., Guermouche, A., Lopez, F.: Implementing multifrontal sparse solvers for multicore architectures with Sequential Task Flow runtime systems. ACM Trans. Math. Softw. 43, 13 (2016)","journal-title":"ACM Trans. Math. Softw."},{"key":"7_CR7","unstructured":"Agullo, E., Giraud, L., Guermouche, A., Nakov, S., Roman, J.: Task-based conjugate-gradient for multi-GPUs platforms. Research report RR-8192, INRIA (2012)"},{"key":"7_CR8","volume-title":"Optimizing Compilers for Modern Architectures: A Dependence-Based Approach","author":"R Allen","year":"2002","unstructured":"Allen, R., Kennedy, K.: Optimizing Compilers for Modern Architectures: A Dependence-Based Approach. Morgan Kaufmann, San Francisco (2002)"},{"issue":"1","key":"7_CR9","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1137\/S0895479899358194","volume":"23","author":"PR Amestoy","year":"2001","unstructured":"Amestoy, P.R., Duff, I.S., Koster, J., L\u2019Excellent, J.-Y.: A fully asynchronous multifrontal solver using distributed dynamic scheduling. SIAM J. Matrix Anal. Appl. 23(1), 15\u201341 (2001)","journal-title":"SIAM J. Matrix Anal. Appl."},{"issue":"2","key":"7_CR10","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1016\/j.parco.2005.07.004","volume":"32","author":"PR Amestoy","year":"2006","unstructured":"Amestoy, P.R., Guermouche, A., L\u2019Excellent, J.-Y., Pralet, S.: Hybrid scheduling for the parallel solution of linear systems. Parallel Comput. 32(2), 136\u2013156 (2006)","journal-title":"Parallel Comput."},{"key":"7_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1007\/978-3-642-03869-3_80","volume-title":"Euro-Par 2009 Parallel Processing","author":"C Augonnet","year":"2009","unstructured":"Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.-A.: StarPU: a unified platform for task scheduling on heterogeneous multicore architectures. In: Sips, H., Epema, D., Lin, H.-X. (eds.) Euro-Par 2009. LNCS, vol. 5704, pp. 863\u2013874. Springer, Heidelberg (2009). doi:10.1007\/978-3-642-03869-3_80"},{"key":"7_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1007\/978-3-642-03869-3_79","volume-title":"Euro-Par 2009 Parallel Processing","author":"E Ayguad\u00e9","year":"2009","unstructured":"Ayguad\u00e9, E., Badia, R.M., Igual, F.D., Labarta, J., Mayo, R., Quintana-Ort\u00ed, E.S.: An extension of the StarSs programming model for platforms with multiple GPUs. In: Sips, H., Epema, D., Lin, H.-X. (eds.) Euro-Par 2009. LNCS, vol. 5704, pp. 851\u2013862. Springer, Heidelberg (2009). doi:10.1007\/978-3-642-03869-3_79"},{"key":"7_CR13","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719642","volume-title":"ScaLAPACK Users\u2019 Guide","author":"LS Blackford","year":"1997","unstructured":"Blackford, L.S., Choi, J., Cleary, A., D\u2019Azevedo, E., Demmel, J., Dhillon, I., Dongarra, J., Hammarling, S., Henry, G., Petitet, A., Stanley, K., Walker, D., Whaley, R.C.: ScaLAPACK Users\u2019 Guide. SIAM Press, Philadelphia (1997)"},{"key":"7_CR14","unstructured":"Bosilca, G., Bouteiller, A., Danalis, A., Faverge, M., Haidar, H., Herault, T., Kurzak, J., Langou, J., Lemarinier, P., Ltaief, H., Luszczek, P., YarKhan, A., Dongarra, J.: Distributed-memory task execution and dependence tracking within DAGuE and the DPLASMA project. Innovative Computing Laboratory Technical report (2010)"},{"issue":"6","key":"7_CR15","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MCSE.2013.98","volume":"15","author":"G Bosilca","year":"2013","unstructured":"Bosilca, G., Bouteiller, A., Danalis, A., Faverge, M., H\u00e9rault, T., Dongarra, J.J.: PaRSEC: exploiting heterogeneity to enhance scalability. Comput. Sci. Eng. 15(6), 36\u201345 (2013)","journal-title":"Comput. Sci. Eng."},{"issue":"4","key":"7_CR16","doi-asserted-by":"publisher","first-page":"C323","DOI":"10.1137\/110846427","volume":"35","author":"A Buttari","year":"2013","unstructured":"Buttari, A.: Fine-grained multithreading for the multifrontal QR factorization of sparse matrices. SIAM J. Sci. Comput. 35(4), C323\u2013C345 (2013)","journal-title":"SIAM J. Sci. Comput."},{"issue":"4","key":"7_CR17","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1002\/nla.237","volume":"8","author":"LM Carvalho","year":"2001","unstructured":"Carvalho, L.M., Giraud, L., Meurant, G.: Local preconditioners for two-level non-overlapping domain decomposition methods. Numer. Linear Algebra Appl. 8(4), 207\u2013227 (2001)","journal-title":"Numer. Linear Algebra Appl."},{"issue":"1","key":"7_CR18","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1137\/0613018","volume":"13","author":"TFC Chan","year":"1992","unstructured":"Chan, T.F.C., Mathew, T.P.: The interface probing technique in domain decomposition. SIAM J. Matrix Anal. Appl. 13(1), 212\u2013238 (1992)","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Gaidamour, J., H\u00e9non, P.: A parallel direct\/iterative solver based on a Schur complement approach. In: 2013 IEEE 16th International Conference on Computational Science and Engineering, pp. 98\u2013105 (2008)","DOI":"10.1109\/CSE.2008.36"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Gaidamour, J., H\u00e9non, P.: HIPS: a parallel hybrid direct\/iterative solver based on a Schur complement approach. In: Proceedings of PMAA (2008)","DOI":"10.1109\/CSE.2008.36"},{"key":"7_CR21","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1016\/j.parco.2008.01.006","volume":"34","author":"L Giraud","year":"2008","unstructured":"Giraud, L., Haidar, A., Watson, L.T.: Parallel scalability study of hybrid preconditioners in three dimensions. Parallel Comput. 34, 363\u2013379 (2008)","journal-title":"Parallel Comput."},{"issue":"2","key":"7_CR22","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s11075-008-9248-x","volume":"51","author":"L Giraud","year":"2009","unstructured":"Giraud, L., Haidar, A.: Parallel algebraic hybrid solvers for large 3D convection-diffusion problems. Numer. Algorithms 51(2), 151\u2013177 (2009)","journal-title":"Numer. Algorithms"},{"issue":"5\u20136","key":"7_CR23","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/j.parco.2009.12.006","volume":"36","author":"L Giraud","year":"2010","unstructured":"Giraud, L., Haidar, A., Pralet, S.: Using multiple levels of parallelism to enhance the performance of domain decomposition solvers. Parallel Comput. 36(5\u20136), 285\u2013296 (2010)","journal-title":"Parallel Comput."},{"key":"7_CR24","unstructured":"Haidar, A.: On the parallel scalability of hybrid linear solvers for large 3D problems. Ph.D. thesis, Institut National Polytechnique de Toulouse, 17 December 2008"},{"issue":"2","key":"7_CR25","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/S0167-8191(01)00141-7","volume":"28","author":"P H\u00e9non","year":"2002","unstructured":"H\u00e9non, P., Ramet, P., Roman, J.: PaStiX: a high-performance parallel direct solver for sparse symmetric definite systems. Parallel Comput. 28(2), 301\u2013321 (2002)","journal-title":"Parallel Comput."},{"issue":"6","key":"7_CR26","doi-asserted-by":"publisher","first-page":"2266","DOI":"10.1137\/040608258","volume":"28","author":"P H\u00e9non","year":"2006","unstructured":"H\u00e9non, P., Saad, Y.: A parallel multistage ILU factorization based on a hierarchical graph decomposition. SIAM J. Sci. Comput. 28(6), 2266\u20132293 (2006)","journal-title":"SIAM J. Sci. Comput."},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Jaulmes, L., Casas, M., Moret\u00f3, M., Ayguad\u00e9, E., Labarta, J., Valero, M.: Exploiting asynchrony from exact forward recovery for due in iterative solvers. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2015, pp. 53:1\u201353:12. ACM, New York (2015)","DOI":"10.1145\/2807591.2807599"},{"key":"7_CR28","unstructured":"Karypis, G., Kumar, V.: MeTiS - Unstructured Graph Partitioning and Sparse Matrix Ordering System - Version 2.0. University of Minnesota, June 1995"},{"key":"7_CR29","unstructured":"Lacoste, X.: Scheduling and memory optimizations for sparse direct solver on multi-core\/multi-GPU cluster systems. Ph.D. thesis, LaBRI, Universit\u00e9 Bordeaux, Talence, France, February 2015"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Lacoste, X., Faverge, M., Ramet, P., Thibault, S., Bosilca, G.: Taking advantage of hybrid systems for sparse direct solvers via task-based runtimes, May 2014","DOI":"10.1109\/IPDPSW.2014.9"},{"issue":"1","key":"7_CR31","doi-asserted-by":"publisher","first-page":"012015","DOI":"10.1088\/1742-6596\/180\/1\/012015","volume":"180","author":"XS Li","year":"2009","unstructured":"Li, X.S., Shao, M., Yamazaki, I., Ng, E.G.: Factorization-based sparse solvers and preconditioners. J. Phys. Conf. Ser. 180(1), 012015 (2009)","journal-title":"J. Phys. Conf. Ser."},{"issue":"2","key":"7_CR32","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1145\/779359.779361","volume":"29","author":"XS Li","year":"2003","unstructured":"Li, X.S., Demmel, J.W.: SuperLU_DIST: a scalable distributed-memory sparse direct solver for unsymmetric linear systems. ACM Trans. Math. Softw. 29(2), 110\u2013140 (2003)","journal-title":"ACM Trans. Math. Softw."},{"key":"7_CR33","unstructured":"Lopez, F.: Task-based multifrontal QR solver for heterogeneous architectures. Ph.D. thesis, University Paul Sabatier, Toulouse, France (2015, submitted)"},{"key":"7_CR34","series-title":"Lecture Notes in Computational Science and Engineering","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77209-5","volume-title":"Domain Decomposition Methods for the Numerical Solution of Partial Differential Equations","author":"TPA Mathew","year":"2008","unstructured":"Mathew, T.P.A.: Domain Decomposition Methods for the Numerical Solution of Partial Differential Equations. Lecture Notes in Computational Science and Engineering, vol. 61. Springer, Heidelberg (2008). doi:10.1007\/978-3-540-77209-5"},{"key":"7_CR35","unstructured":"Nakov, S.: On the design of sparse hybrid linear solvers for modern parallel architectures. Theses, Universit\u00e9 de Bordeaux, December 2015"},{"key":"7_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1007\/BFb0031609","volume-title":"High-Performance Computing and Networking","author":"F Pellegrini","year":"1997","unstructured":"Pellegrini, F., Roman, J.: Sparse matrix ordering with Scotch. In: Hertzberger, B., Sloot, P. (eds.) HPCN-Europe 1997. LNCS, vol. 1225, pp. 370\u2013378. Springer, Heidelberg (1997). doi:10.1007\/BFb0031609"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Rajamanickam, S., Boman, E.G., Heroux, M.A.: ShyLU: a hybrid-hybrid solver for multicore platforms. In: International Parallel and Distributed Processing Symposium, pp. 631\u2013643 (2012)","DOI":"10.1109\/IPDPS.2012.64"},{"issue":"8","key":"7_CR38","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/79173.79181","volume":"33","author":"LG Valiant","year":"1990","unstructured":"Valiant, L.G.: A bridging model for parallel computation. Commun. ACM 33(8), 103\u2013111 (1990)","journal-title":"Commun. ACM"},{"issue":"6","key":"7_CR39","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/MCSE.2009.207","volume":"11","author":"FG Van Zee","year":"2009","unstructured":"Van Zee, F.G., Chan, E., van de Geijn, R.A., Quintana-Orti, E.S., Quintana-Orti, G.: The libflame library for dense matrix computations. Comput. Sci. Eng. 11(6), 56\u201363 (2009)","journal-title":"Comput. Sci. Eng."},{"key":"7_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/978-3-642-19328-6_38","volume-title":"High Performance Computing for Computational Science \u2013 VECPAR 2010","author":"I Yamazaki","year":"2011","unstructured":"Yamazaki, I., Li, X.S.: On techniques to improve robustness and scalability of a parallel hybrid linear solver. In: Palma, J.M.L.M., Dayd\u00e9, M., Marques, O., Lopes, J.C. (eds.) VECPAR 2010. LNCS, vol. 6449, pp. 421\u2013434. Springer, Heidelberg (2011). doi:10.1007\/978-3-642-19328-6_38"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2016: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-58943-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,28]],"date-time":"2021-05-28T00:24:18Z","timestamp":1622161458000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-58943-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319589428","9783319589435"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-58943-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"28 May 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 August 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/europar2016.inria.fr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}