{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:06:25Z","timestamp":1757617585850,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819628292"},{"type":"electronic","value":"9789819628308"}],"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\/978-981-96-2830-8_6","type":"book-chapter","created":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T19:20:21Z","timestamp":1743362421000},"page":"65-76","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Implementation of\u00a0the\u00a0LOBPCG Algorithm on\u00a0a\u00a0CPU-GPU Cluster"],"prefix":"10.1007","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[]},{"given":"Yonghua","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Zexin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Rongfeng","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Dingye","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xinyin","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,29]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Anzt, H., Sawyer, W., Tomov, S., Luszczek, P., Yamazaki, I., Dongarra, J.: Optimizing krylov subspace solvers on graphics processing units. In: Fourth International Workshop on Accelerators and Hybrid Exascale Systems (AsHES), IPDPS 2014, Phoenix, AZ. IEEE (2014)","DOI":"10.1109\/IPDPSW.2014.107"},{"key":"6_CR2","unstructured":"Anzt, H., Tomov, S., Dongarra, J.J.: Accelerating the LOBPCG method on GPUs using a blocked sparse matrix vector product. In: SpringSim (HPS), pp. 75\u201382 (2015)"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Anzt, H., Tsai, Y.M., Abdelfattah, A., Cojean, T., Dongarra, J.: Evaluating the performance of Nvidia\u2019s a100 ampere GPU for sparse and batched computations. In: 2020 IEEE\/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS), pp. 26\u201338. IEEE (2020)","DOI":"10.1109\/PMBS51919.2020.00009"},{"issue":"3","key":"6_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1527286.1527287","volume":"36","author":"CG Baker","year":"2009","unstructured":"Baker, C.G., Hetmaniuk, U.L., Lehoucq, R.B., Thornquist, H.K.: Anasazi software for the numerical solution of large-scale eigenvalue problems. ACM Trans. Math. Softw. (TOMS) 36(3), 1\u201323 (2009)","journal-title":"ACM Trans. Math. Softw. (TOMS)"},{"key":"6_CR5","unstructured":"Balay, S., et al.: PETSc Web (2024). https:\/\/petsc.org\/"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Bell, N., Garland, M.: Implementing sparse matrix-vector multiplication on throughput-oriented processors. In: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis, pp. 1\u201311 (2009)","DOI":"10.1145\/1654059.1654078"},{"key":"6_CR7","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1016\/0024-3795(94)90493-6","volume":"197","author":"\u00c5 Bj\u00f6rck","year":"1994","unstructured":"Bj\u00f6rck, \u00c5.: Numerics of gram-schmidt orthogonalization. Linear Algebra Appl. 197, 297\u2013316 (1994)","journal-title":"Linear Algebra Appl."},{"key":"6_CR8","doi-asserted-by":"publisher","unstructured":"Brown, C., Abdelfattah, A., Tomov, S., Dongarra, J.J.: Design, optimization, and benchmarking of dense linear algebra algorithms on AMD GPUs. In: 2020 IEEE High Performance Extreme Computing Conference, HPEC 2020, Waltham, MA, USA, 22\u201324 September 2020, pp.\u00a01\u20137. IEEE (2020). https:\/\/doi.org\/10.1109\/HPEC43674.2020.9286214","DOI":"10.1109\/HPEC43674.2020.9286214"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Bulu\u00e7, A., Fineman, J.T., Frigo, M., Gilbert, J.R., Leiserson, C.E.: Parallel sparse matrix-vector and matrix-transpose-vector multiplication using compressed sparse blocks. In: Proceedings of the Twenty-First Annual Symposium on Parallelism in Algorithms and Architectures, pp. 233\u2013244 (2009)","DOI":"10.1145\/1583991.1584053"},{"issue":"3","key":"6_CR10","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1137\/S1064827594270415","volume":"19","author":"E Chow","year":"1998","unstructured":"Chow, E., Saad, Y.: Approximate inverse preconditioners via sparse-sparse iterations. SIAM J. Sci. Comput. 19(3), 995\u20131023 (1998)","journal-title":"SIAM J. Sci. Comput."},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Daga, M., Greathouse, J.L.: Structural agnostic SPMV: adapting CSR-adaptive for irregular matrices. In: 2015 IEEE 22nd International conference on high performance computing (HiPC), pp. 64\u201374. IEEE (2015)","DOI":"10.1109\/HiPC.2015.55"},{"issue":"1","key":"6_CR12","first-page":"1","volume":"38","author":"TA Davis","year":"2011","unstructured":"Davis, T.A., Hu, Y.: The University of Florida sparse matrix collection. ACM Trans. Math. Softw. (TOMS) 38(1), 1\u201325 (2011)","journal-title":"ACM Trans. Math. Softw. (TOMS)"},{"key":"6_CR13","unstructured":"Dong, T., Haidar, A., Luszczek, P., Tomov, S., Abdelfattah, A., Dongarra, J.: Magma batched: a batched BLAS approach for small matrix factorizations and applications on GPUs. Technical report (2016)"},{"issue":"11","key":"6_CR14","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1002\/(SICI)1097-0363(19970615)24:11<1185::AID-FLD535>3.0.CO;2-X","volume":"24","author":"A Fortin","year":"1997","unstructured":"Fortin, A., Jardak, M., Gervais, J., Pierre, R.: Localization of Hopf bifurcations in fluid flow problems. Int. J. Numer. Meth. Fluids 24(11), 1185\u20131210 (1997)","journal-title":"Int. J. Numer. Meth. Fluids"},{"issue":"3","key":"6_CR15","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1145\/1089014.1089019","volume":"31","author":"V Hernandez","year":"2005","unstructured":"Hernandez, V., Roman, J.E., Vidal, V.: SLEPc: a scalable and flexible toolkit for the solution of eigenvalue problems. ACM Trans. Math. Softw. (TOMS) 31(3), 351\u2013362 (2005)","journal-title":"ACM Trans. Math. Softw. (TOMS)"},{"issue":"2","key":"6_CR16","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1137\/S1064827500366124","volume":"23","author":"AV Knyazev","year":"2001","unstructured":"Knyazev, A.V.: Toward the optimal preconditioned eigensolver: locally optimal block preconditioned conjugate gradient method. SIAM J. Sci. Comput. 23(2), 517\u2013541 (2001)","journal-title":"SIAM J. Sci. Comput."},{"issue":"5","key":"6_CR17","doi-asserted-by":"publisher","first-page":"2224","DOI":"10.1137\/060661624","volume":"29","author":"AV Knyazev","year":"2007","unstructured":"Knyazev, A.V., Argentati, M.E., Lashuk, I., Ovtchinnikov, E.E.: Block locally optimal preconditioned eigenvalue xolvers (BLOPEX) in HYPRE and PETSc. SIAM J. Sci. Comput. 29(5), 2224\u20132239 (2007)","journal-title":"SIAM J. Sci. Comput."},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Ruge, J.W., St\u00fcben, K.: Algebraic multigrid. In: Multigrid Methods, pp. 73\u2013130. SIAM (1987)","DOI":"10.1137\/1.9781611971057.ch4"},{"issue":"4","key":"6_CR19","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1002\/nla.1680010405","volume":"1","author":"Y Saad","year":"1994","unstructured":"Saad, Y.: ILUT: a dual threshold incomplete LU factorization. Numer. Linear Algebra Appl. 1(4), 387\u2013402 (1994)","journal-title":"Numer. Linear Algebra Appl."},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Saad, Y.: Numerical Methods for Large Eigenvalue Problems: Revised Edition. SIAM (2011)","DOI":"10.1137\/1.9781611970739"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Stathopoulos, A., McCombs, J.R.: PRIMME: PReconditioned Iterative MultiMethod Eigensolver: Methods and software description. ACM Trans. Math. Softw. 37(2), 21:1\u201321:30 (2010)","DOI":"10.1145\/1731022.1731031"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Sun, L., Ji, S., Ye, J.: A least squares formulation for a class of generalized eigenvalue problems in machine learning. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 977\u2013984 (2009)","DOI":"10.1145\/1553374.1553499"},{"issue":"5\u20136","key":"6_CR23","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.parco.2009.12.005","volume":"36","author":"S Tomov","year":"2010","unstructured":"Tomov, S., Dongarra, J., Baboulin, M.: Towards dense linear algebra for hybrid GPU accelerated manycore systems. Parallel Comput. 36(5\u20136), 232\u2013240 (2010). https:\/\/doi.org\/10.1016\/j.parco.2009.12.005","journal-title":"Parallel Comput."},{"issue":"9","key":"6_CR24","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1070\/PU1984v027n09ABEH004155","volume":"27","author":"A Turbiner","year":"1984","unstructured":"Turbiner, A.: The eigenvalue spectrum in quantum mechanics and the nonlinearization procedure. Soviet Physics Uspekhi 27(9), 668 (1984)","journal-title":"Soviet Physics Uspekhi"},{"issue":"1","key":"6_CR25","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1137\/0909010","volume":"9","author":"HF Walker","year":"1988","unstructured":"Walker, H.F.: Implementation of the GMRES method using householder transformations. SIAM J. Sci. Stat. Comput. 9(1), 152\u2013163 (1988)","journal-title":"SIAM J. Sci. Stat. Comput."},{"key":"6_CR26","volume-title":"Numerical Analysis of Electromagnetic Fields","author":"P Zhou","year":"2012","unstructured":"Zhou, P.: Numerical Analysis of Electromagnetic Fields. Springer, Cham (2012)"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Zhuzhunashvili, D., Knyazev, A.: Preconditioned spectral clustering for stochastic block partition streaming graph challenge. In: 2017 IEEE High Performance Extreme Computing Conference (HPEC), pp.\u00a01\u20136. IEEE (2017)","DOI":"10.1109\/HPEC.2017.8091045"}],"container-title":["Lecture Notes in Computer Science","Network and Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2830-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T08:27:22Z","timestamp":1757147242000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2830-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819628292","9789819628308"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2830-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"29 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Network and Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Haikou","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"npc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}