{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T14:32:00Z","timestamp":1761921120713,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031312083"},{"type":"electronic","value":"9783031312090"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-31209-0_2","type":"book-chapter","created":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T15:11:26Z","timestamp":1682953886000},"page":"17-31","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Portable and\u00a0Heterogeneous LU Factorization on\u00a0IRIS"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1479-4310","authenticated-orcid":false,"given":"Pedro","family":"Valero-Lara","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6594-6225","authenticated-orcid":false,"given":"Jungwon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2449-6720","authenticated-orcid":false,"given":"Jeffrey S.","family":"Vetter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,2]]},"reference":[{"issue":"2","key":"2_CR1","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1080\/10556788.2012.762517","volume":"29","author":"S Bellavia","year":"2014","unstructured":"Bellavia, S., Morini, B., Porcelli, M.: New updates of incomplete LU factorizations and applications to large nonlinear systems. Optim. Methods Softw. 29(2), 321\u2013340 (2014). https:\/\/doi.org\/10.1080\/10556788.2012.762517","journal-title":"Optim. Methods Softw."},{"issue":"6","key":"2_CR2","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1109\/43.387732","volume":"14","author":"KM Eickhoff","year":"1995","unstructured":"Eickhoff, K.M., Engl, W.L.: Levelized incomplete LU factorization and its application to large-scale circuit simulation. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 14(6), 720\u2013727 (1995). https:\/\/doi.org\/10.1109\/43.387732","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"issue":"17","key":"2_CR3","doi-asserted-by":"publisher","first-page":"4594","DOI":"10.1109\/TSP.2015.2440219","volume":"63","author":"X Luciani","year":"2015","unstructured":"Luciani, X., Albera, L.: Joint eigenvalue decomposition of non-defective matrices based on the LU factorization with application to ICA. IEEE Trans. Signal Process. 63(17), 4594\u20134608 (2015). https:\/\/doi.org\/10.1109\/TSP.2015.2440219","journal-title":"IEEE Trans. Signal Process."},{"key":"2_CR4","doi-asserted-by":"publisher","unstructured":"Kudo, S., Nitadori, K., Ina, T., Imamura, T.: Implementation and numerical techniques for one eflop\/s HPL-AI benchmark on fugaku. In: 11th IEEE\/ACM Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, ScalA@SC 2020, Atlanta, GA, USA, 13 November 2020, pp. 69\u201376. IEEE (2020). https:\/\/doi.org\/10.1109\/ScalA51936.2020.00014","DOI":"10.1109\/ScalA51936.2020.00014"},{"issue":"4","key":"2_CR5","doi-asserted-by":"publisher","first-page":"042 102:1","DOI":"10.1007\/s11432-017-9221-0","volume":"61","author":"X Gan","year":"2018","unstructured":"Gan, X., et al.: Customizing the HPL for china accelerator. Sci. China Inf. Sci. 61(4), 042 102:1-042 102:11 (2018). https:\/\/doi.org\/10.1007\/s11432-017-9221-0","journal-title":"Sci. China Inf. Sci."},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Kim, J., Lee, S., Johnston, B., Vetter, J.S.: IRIS: a portable runtime system exploiting multiple heterogeneous programming systems. In: Proceedings of the 25th IEEE High Performance Extreme Computing Conference, ser. HPEC 2021, pp. 1\u20138 (2021)","DOI":"10.1109\/HPEC49654.2021.9622873"},{"key":"2_CR7","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.jpdc.2019.12.002","volume":"138","author":"P Valero-Lara","year":"2020","unstructured":"Valero-Lara, P., Catal\u00e1n, S., Martorell, X., Usui, T., Labarta, J.: slass: a fully automatic auto-tuned linear algebra library based on openmp extensions implemented in ompss (lass library). J. Parallel Distributed Comput. 138, 153\u2013171 (2020)","journal-title":"J. Parallel Distributed Comput."},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Valero-Lara, P., Catal\u00e1n, S., Martorell, X., Labarta, J.: BLAS-3 optimized by ompss regions (lass library). In: 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing, PDP 2019, Pavia, Italy, 13\u201315 February 2019, pp. 25\u201332. IEEE (2019)","DOI":"10.1109\/EMPDP.2019.8671545"},{"issue":"2","key":"2_CR9","doi-asserted-by":"publisher","first-page":"16:1","DOI":"10.1145\/3264491","volume":"45","author":"JJ Dongarra","year":"2019","unstructured":"Dongarra, J.J., et al.: PLASMA: parallel linear algebra software for multicore using openmp. ACM Trans. Math. Softw. 45(2), 16:1-16:35 (2019)","journal-title":"ACM Trans. Math. Softw."},{"key":"2_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/978-3-319-78024-5_22","volume-title":"Parallel Processing and Applied Mathematics","author":"P Valero-Lara","year":"2018","unstructured":"Valero-Lara, P., Mart\u00ednez-P\u00e9rez, I., Sirvent, R., Martorell, X., Pe\u00f1a, A.J.: NVIDIA GPUs scalability to solve multiple (batch) tridiagonal systems implementation of cuThomasBatch. In: Wyrzykowski, R., Dongarra, J., Deelman, E., Karczewski, K. (eds.) PPAM 2017. LNCS, vol. 10777, pp. 243\u2013253. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-78024-5_22"},{"issue":"24","key":"2_CR11","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4909","volume":"30","author":"P Valero-Lara","year":"2018","unstructured":"Valero-Lara, P., Mart\u00ednez-P\u00e9rez, I., Sirvent, R., Martorell, X., Pe\u00f1a, A.J.: cuThomasBatch and cuThomasVBatch, CUDA routines to compute batch of tridiagonal systems on NVIDIA GPUs. Concurr. Comput. Pract. Exp. 30(24), e4909 (2018)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Valero-Lara, P., Pinelli, A., Favier, J., Matias, M.P.: Block tridiagonal solvers on heterogeneous architectures. In: IEEE 10th International Symposium on Parallel and Distributed Processing with Applications, ser. ISPA 2012, pp. 609\u2013616 (2012)","DOI":"10.1109\/ISPA.2012.91"},{"issue":"4","key":"2_CR13","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1016\/j.cpc.2013.12.026","volume":"185","author":"P Valero-Lara","year":"2014","unstructured":"Valero-Lara, P., Pinelli, A., Prieto-Matias, M.: Fast finite difference Poisson solvers on heterogeneous architectures. Comput. Phys. Commun. 185(4), 1265\u20131272 (2014)","journal-title":"Comput. Phys. Commun."},{"issue":"4","key":"2_CR14","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1137\/S0895479897317685","volume":"20","author":"JW Demmel","year":"1999","unstructured":"Demmel, J.W., Gilbert, J.R., Li, X.S.: An asynchronous parallel supernodal algorithm for sparse gaussian elimination. SIAM J. Matrix Anal. Appl. 20(4), 915\u2013952 (1999)","journal-title":"SIAM J. Matrix Anal. Appl."},{"issue":"4","key":"2_CR15","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1109\/TPDS.2021.3097283","volume":"33","author":"CR Trott","year":"2022","unstructured":"Trott, C.R., et al.: Kokkos 3: programming model extensions for the exascale era. IEEE Trans. Parallel Distributed Syst. 33(4), 805\u2013817 (2022). https:\/\/doi.org\/10.1109\/TPDS.2021.3097283","journal-title":"IEEE Trans. Parallel Distributed Syst."},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Beckingsale, D., Hornung, R.D., Scogland, T., Vargas, A.: Performance portable C++ programming with RAJA. In: Hollingsworth, J.K., Keidar, I. (eds.) Proceedings of the 24th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2019, Washington, DC, USA, 16\u201320 February 2019, pp. 455\u2013456. ACM (2019)","DOI":"10.1145\/3293883.3302577"},{"issue":"7","key":"2_CR17","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3919","volume":"29","author":"P Valero-Lara","year":"2017","unstructured":"Valero-Lara, P., Jansson, J.: Heterogeneous CPU+GPU approaches for mesh refinement over lattice-boltzmann simulations. Concurr. Comput. Pract. Exp. 29(7), e3919 (2017)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"2_CR18","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.jocs.2015.07.002","volume":"10","author":"P Valero-Lara","year":"2015","unstructured":"Valero-Lara, P., Igual, F.D., Prieto-Mat\u00edas, M., Pinelli, A., Favier, J.: Accelerating fluid-solid simulations (lattice-boltzmann & immersed-boundary) on heterogeneous architectures. J. Comput. Sci. 10, 249\u2013261 (2015)","journal-title":"J. Comput. Sci."},{"key":"2_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-031-06156-1_35","volume-title":"Euro-Par 2021: Parallel Processing Workshops","author":"P Valero-Lara","year":"2021","unstructured":"Valero-Lara, P., Kim, J., Hernandez, O., Vetter, J.S.: Openmp target task: tasking and target offloading on heterogeneous systems. In: Chaves, R., et al. (eds.) Euro-Par 2021. LNCS, vol. 13098, pp. 445\u2013455. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-031-06156-1_35"},{"key":"2_CR20","unstructured":"Tomov, S., Dongarra, J., Baboulin, M.: Towards dense linear algebra for hybrid GPU accelerated manycore systems. Technical report, 2008-01 (2008)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2022: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-31209-0_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T15:11:46Z","timestamp":1682953906000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-31209-0_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031312083","9783031312090"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-31209-0_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"2 May 2023","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2022.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"102","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"25","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"25% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the workshops, 24 papers have been accepted from a total of 35 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}