{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T16:32:12Z","timestamp":1758126732520,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030967710"},{"type":"electronic","value":"9783030967727"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-030-96772-7_7","type":"book-chapter","created":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T21:13:08Z","timestamp":1647378788000},"page":"69-80","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Batched Jacobi SVD Algorithm on\u00a0GPUs and\u00a0Its Application to\u00a0Quantum Lattice Systems"],"prefix":"10.1007","author":[{"given":"Rongfeng","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shifang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghua","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,16]]},"reference":[{"issue":"1","key":"7_CR1","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.procs.2016.05.302","volume":"80","author":"A Abdelfattah","year":"2016","unstructured":"Abdelfattah, A., Baboulin, M., Dobrev, V., et al.: High-performance tensor contractions for GPUs. Procedia Comput. Sci. 80(1), 108\u2013118 (2016)","journal-title":"Procedia Comput. Sci."},{"issue":"6","key":"7_CR2","doi-asserted-by":"publisher","first-page":"2256","DOI":"10.1109\/JSTARS.2014.2328614","volume":"7","author":"JM Molero","year":"2014","unstructured":"Molero, J.M., Garz\u00f3n, E.M., Garc\u00eda, I., Quintana-Ort\u00ed, E.S., Plaza, A.: Efficient implementation of hyperspectral anomaly detection techniques on GPUs and multicore processors. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 7(6), 2256\u20132266 (2014)","journal-title":"IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens."},{"doi-asserted-by":"crossref","unstructured":"Villa, O., Gawande, N., Tumeo, A.: Accelerating subsurface transport simulation on heterogeneous clusters. In: IEEE International Conference on Cluster Computing, Indianapolis, pp. 1\u20138. IEEE (2013)","key":"7_CR3","DOI":"10.1109\/CLUSTER.2013.6702656"},{"issue":"3","key":"7_CR4","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1109\/TPDS.2019.2940192","volume":"31","author":"T Zhang","year":"2020","unstructured":"Zhang, T., Liu, X., Wang, X., Walid, A.: cuTensor-tubal: efficient primitives for tubal-rank tensor learning operations on GPUs. IEEE Trans. Parallel Distrib. Syst. 31(3), 595\u2013610 (2020)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"unstructured":"NVIDIA cuBLAS Homepage. https:\/\/docs.nvidia.com\/cuda\/pdf\/cublas_Library.pdf","key":"7_CR5"},{"unstructured":"AMD rocBLAS Homepage. https:\/\/github.com\/ROCmSoftwarePlatform\/rocBLAS","key":"7_CR6"},{"issue":"7","key":"7_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3431921","volume":"47","author":"A Abdelfattah","year":"2021","unstructured":"Abdelfattah, A., Costa, T., Dongarra, J., et al.: A set of batched basic linear algebra subprograms and LAPACK routines. ACM Trans. Math. Softw. 47(7), 1\u201323 (2021)","journal-title":"ACM Trans. Math. Softw."},{"doi-asserted-by":"crossref","unstructured":"Dong, T., Haidar, A., Tomov, S., Dongarra. J.: A fast batched cholesky factorization on a GPU. In: International Conference on Parallel Processing, pp. 432\u2013440. IEEE (2014)","key":"7_CR8","DOI":"10.1109\/ICPP.2014.52"},{"doi-asserted-by":"crossref","unstructured":"Abdelfattah, A., Haidar, A., Tomov, S., Dongarra. J.: Factorization and inversion of a million matrices using GPUs: challenges and countermeasures. In: International Conference on Computational Science, pp. 606\u2013615 (2017)","key":"7_CR9","DOI":"10.1016\/j.procs.2017.05.250"},{"unstructured":"NVIDIA cuSOLVER Homepage. https:\/\/docs.nvidia.com\/cuda\/cusolver\/index.html","key":"7_CR10"},{"issue":"5","key":"7_CR11","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1016\/j.jocs.2018.01.007","volume":"26","author":"T Dong","year":"2018","unstructured":"Dong, T., Haidar, A., Tomov, S., Dongarra, J.: Accelerating the SVD bi-diagonalization of a batch of small matrices using GPUs. J. Comput. Sci. 26(5), 237\u2013245 (2018)","journal-title":"J. Comput. Sci."},{"doi-asserted-by":"crossref","unstructured":"Badolato, I., Paula, L.D., Farias, R.: Many SVDs on GPU for image mosaic assemble. In: IEEE International Symposium on Computer Architecture and High Performance Computing Workshop, pp. 37\u201342 (2015)","key":"7_CR12","DOI":"10.1109\/SBAC-PADW.2015.22"},{"issue":"5","key":"7_CR13","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.parco.2017.09.001","volume":"74","author":"WH Boukaram","year":"2018","unstructured":"Boukaram, W.H., Turkiyyah, G., Ltaief, H., Keyes, D.E.: Batched QR and SVD algorithms on GPUs with applications in hierarchical matrix compression. Parallel Comput. 74(5), 19\u201333 (2018)","journal-title":"Parallel Comput."},{"unstructured":"KBLAS Homepage. https:\/\/github.com\/ecrc\/kblas-gpu, Accessed 30 Nov 2020","key":"7_CR14"},{"issue":"1","key":"7_CR15","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1137\/0906007","volume":"6","author":"PP Brent","year":"1985","unstructured":"Brent, P.P., Luk, F.T.: The solution of singular-value and symmetric eigenvalue problems on multiprocessor arrays. SIAM J. Sci. Stat. Comput. 6(1), 69\u201384 (1985)","journal-title":"SIAM J. Sci. Stat. Comput."},{"issue":"1","key":"7_CR16","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1137\/0910002","volume":"10","author":"FT Luk","year":"1989","unstructured":"Luk, F.T., Park, H.: On parallel Jacobi orderings. SIAM J. Sci. Stat. Comput. 10(1), 18\u201326 (1989)","journal-title":"SIAM J. Sci. Stat. Comput."},{"issue":"6","key":"7_CR17","doi-asserted-by":"publisher","first-page":"806","DOI":"10.1109\/12.24289","volume":"38","author":"FT Luk","year":"1989","unstructured":"Luk, F.T., Park, H.: A proof of convergence for two parallel jacobi SVD algorithms. IEEE Trans. Comput. 38(6), 806\u2013811 (1989)","journal-title":"IEEE Trans. Comput."},{"issue":"3","key":"7_CR18","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.jpdc.2021.02.013","volume":"151","author":"C Rivera","year":"2021","unstructured":"Rivera, C., Chen, J., Xiong, N., Zhang, J., Song, S.: TSM2X: high-performance tall-and-skinny matrix-matrix multiplication on GPUs. J. Parallel Distrib. Comput. 151(3), 70\u201385 (2021)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"10","key":"7_CR19","doi-asserted-by":"publisher","first-page":"3934","DOI":"10.1007\/s11227-015-1483-z","volume":"71","author":"J Filipovi\u010d","year":"2015","unstructured":"Filipovi\u010d, J., Madzin, M., Fousek, J., Matyska, L.: Optimizing CUDA code by kernel fusion: application on BLAS. J. Supercomput. 71(10), 3934\u20133957 (2015). https:\/\/doi.org\/10.1007\/s11227-015-1483-z","journal-title":"J. Supercomput."},{"issue":"4","key":"7_CR20","doi-asserted-by":"publisher","first-page":"40502","DOI":"10.1103\/PhysRevLett.93.040502","volume":"93","author":"G Vidal","year":"2004","unstructured":"Vidal, G.: Efficient simulation of one-dimensional quantum many-body systems. Phys. Rev. Lett. 93(4), 40502\u201340505 (2004)","journal-title":"Phys. Rev. Lett."},{"issue":"7","key":"7_CR21","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.cpc.2018.03.006","volume":"228","author":"S Dong","year":"2018","unstructured":"Dong, S., Liu, W., Wang, C., Han, Y., Guo, G., He, L.: TNSPackage: a fortran 2003 library designed for tensor network state methods. Comput. Phys. Commun. 228(7), 163\u2013177 (2018)","journal-title":"Comput. Phys. Commun."}],"container-title":["Lecture Notes in Computer Science","Parallel and Distributed Computing, Applications and Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-96772-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T21:13:51Z","timestamp":1647378831000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-96772-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030967710","9783030967727"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-96772-7_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"16 March 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PDCAT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel and Distributed Computing: Applications and Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 December 2021","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":"pdcat2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/cse.sysu.edu.cn\/pdcat2021\/","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":"97","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":"24","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":"34","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","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":"7","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}