Mostrar el registro sencillo del ítem
dc.contributor.author | Anzt, Hartwig | es_ES |
dc.contributor.author | Dongarra, Jack | es_ES |
dc.contributor.author | Flegar, Goran | es_ES |
dc.contributor.author | Higham, Nicholas J. | es_ES |
dc.contributor.author | Quintana Ortí, Enrique Salvador | es_ES |
dc.date.accessioned | 2020-12-10T04:32:04Z | |
dc.date.available | 2020-12-10T04:32:04Z | |
dc.date.issued | 2019-03-25 | es_ES |
dc.identifier.issn | 1532-0626 | es_ES |
dc.identifier.uri | http://hdl.handle.net/10251/156663 | |
dc.description | This is the peer reviewed version of the following article: Anzt, H, Dongarra, J, Flegar, G, Higham, NJ, Quintana-Ortí, ES. Adaptive precision in block-Jacobi preconditioning for iterative sparse linear system solvers. Concurrency Computat Pract Exper. 2019; 31:e4460, which has been published in final form at https://doi.org/10.1002/cpe.4460. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving. | es_ES |
dc.description.abstract | [EN] We propose an adaptive scheme to reduce communication overhead caused by data movement by selectively storing the diagonal blocks of a block-Jacobi preconditioner in different precision formats (half, single, or double). This specialized preconditioner can then be combined with any Krylov subspace method for the solution of sparse linear systems to perform all arithmetic in double precision. We assess the effects of the adaptive precision preconditioner on the iteration count and data transfer cost of a preconditioned conjugate gradient solver. A preconditioned conjugate gradient method is, in general, a memory bandwidth-bound algorithm, and therefore its execution time and energy consumption are largely dominated by the costs of accessing the problem's data in memory. Given this observation, we propose a model that quantifies the time and energy savings of our approach based on the assumption that these two costs depend linearly on the bit length of a floating point number. Furthermore, we use a number of test problems from the SuiteSparse matrix collection to estimate the potential benefits of the adaptive block-Jacobi preconditioning scheme. | es_ES |
dc.description.sponsorship | Impuls und Vernetzungsfond of the Helmholtz Association, Grant/Award Number: VH-NG-1241; MINECO and FEDER, Grant/Award Number: TIN2014-53495-R; H2020 EU FETHPC Project, Grant/Award Number: 732631; MathWorks; Engineering and Physical Sciences Research Council, Grant/Award Number: EP/P020720/1; Exascale Computing Project, Grant/Award Number: 17-SC-20-SC | es_ES |
dc.language | Inglés | es_ES |
dc.publisher | John Wiley & Sons | es_ES |
dc.relation.ispartof | Concurrency and Computation Practice and Experience | es_ES |
dc.rights | Reserva de todos los derechos | es_ES |
dc.subject | Adaptive precision | es_ES |
dc.subject | Block-Jacobi preconditioning | es_ES |
dc.subject | Communication reduction | es_ES |
dc.subject | Energy efficiency | es_ES |
dc.subject | Krylov subspace methods | es_ES |
dc.subject | Sparse linear systems | es_ES |
dc.subject.classification | ARQUITECTURA Y TECNOLOGIA DE COMPUTADORES | es_ES |
dc.title | Adaptive precision in block-Jacobi preconditioning for iterative sparse linear system solvers | es_ES |
dc.type | Artículo | es_ES |
dc.identifier.doi | 10.1002/cpe.4460 | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/EC/H2020/732631/EU/Open transPREcision COMPuting/ | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/MINECO//TIN2014-53495-R/ES/COMPUTACION HETEROGENEA DE BAJO CONSUMO/ | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/UKRI//EP%2FP020720%2F1/GB/Inference, COmputation and Numerics for Insights into Cities (ICONIC)/ | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/Helmholtz Association of German Research Centers//VH-NG-1241/ | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/DOE//17-SC-20-SC/ | es_ES |
dc.rights.accessRights | Abierto | es_ES |
dc.contributor.affiliation | Universitat Politècnica de València. Departamento de Informática de Sistemas y Computadores - Departament d'Informàtica de Sistemes i Computadors | es_ES |
dc.description.bibliographicCitation | Anzt, H.; Dongarra, J.; Flegar, G.; Higham, NJ.; Quintana Ortí, ES. (2019). Adaptive precision in block-Jacobi preconditioning for iterative sparse linear system solvers. Concurrency and Computation Practice and Experience. 31(6):1-12. https://doi.org/10.1002/cpe.4460 | es_ES |
dc.description.accrualMethod | S | es_ES |
dc.relation.publisherversion | https://doi.org/10.1002/cpe.4460 | es_ES |
dc.description.upvformatpinicio | 1 | es_ES |
dc.description.upvformatpfin | 12 | es_ES |
dc.type.version | info:eu-repo/semantics/publishedVersion | es_ES |
dc.description.volume | 31 | es_ES |
dc.description.issue | 6 | es_ES |
dc.relation.pasarela | S\381008 | es_ES |
dc.contributor.funder | Mathworks | es_ES |
dc.contributor.funder | UK Research and Innovation | es_ES |
dc.contributor.funder | U.S. Department of Energy | es_ES |
dc.contributor.funder | European Regional Development Fund | es_ES |
dc.contributor.funder | Ministerio de Economía y Competitividad | es_ES |
dc.contributor.funder | Helmholtz Association of German Research Centers | es_ES |
dc.contributor.funder | Engineering and Physical Sciences Research Council, Reino Unido | es_ES |
dc.description.references | Saad, Y. (2003). Iterative Methods for Sparse Linear Systems. doi:10.1137/1.9780898718003 | es_ES |
dc.description.references | Anzt H Dongarra J Flegar G Quintana-Ortí ES Batched Gauss-Jordan elimination for block-Jacobi preconditioner generation on GPUs 2017 Austin, TX http://doi.acm.org/10.1145/3026937.3026940 | es_ES |
dc.description.references | Anzt H Dongarra J Flegar G Quintana-Ortí ES Variable-size batched LU for small matrices and its integration into block-Jacobi preconditioning 2017 Bristol, UK https://doi.org/10.1109/ICPP.2017.18 | es_ES |
dc.description.references | Dongarra J Hittinger J Bell J Applied Mathematics Research for Exascale Computing [Technical Report] Washington, DC 2014 https://science.energy.gov/~/media/ascr/pdf/research/am/docs/EMWGreport.pdf | es_ES |
dc.description.references | Duranton M De Bosschere K Cohen A Maebe J Munk H HiPEAC Vision 2015 https://www.hipeac.org/publications/vision/ 2015 | es_ES |
dc.description.references | Lucas R Top Ten Exascale Research Challenges http://science.energy.gov/~/media/ascr/ascac/pdf/meetings/20140210/Top10reportFEB14.pdf 2014 | es_ES |
dc.description.references | Lavignon JF ETP4HPC Strategic Research Agenda Achieving HPC Leadership in Europe 2013 http://www.etp4hpc.eu/ | es_ES |
dc.description.references | Carson, E., & Higham, N. J. (2017). A New Analysis of Iterative Refinement and Its Application to Accurate Solution of Ill-Conditioned Sparse Linear Systems. SIAM Journal on Scientific Computing, 39(6), A2834-A2856. doi:10.1137/17m1122918 | es_ES |
dc.description.references | Carson E Higham NJ Accelerating the solution of linear systems by iterative refinement in three precisions July 2017 http://eprints.ma.man.ac.uk/2562 SIAM Journal on Scientific Computing | es_ES |
dc.description.references | Shalf J The evolution of programming models in response to energy efficiency constraints October 2013 Norman, OK http://www.oscer.ou.edu/Symposium2013/oksupercompsymp2013_talk_shalf_20131002.pdf | es_ES |
dc.description.references | Golub, G. H., & Ye, Q. (1999). Inexact Preconditioned Conjugate Gradient Method with Inner-Outer Iteration. SIAM Journal on Scientific Computing, 21(4), 1305-1320. doi:10.1137/s1064827597323415 | es_ES |
dc.description.references | Barrett, R., Berry, M., Chan, T. F., Demmel, J., Donato, J., Dongarra, J., … van der Vorst, H. (1994). Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods. doi:10.1137/1.9781611971538 | es_ES |
dc.description.references | Notay, Y. (2000). Flexible Conjugate Gradients. SIAM Journal on Scientific Computing, 22(4), 1444-1460. doi:10.1137/s1064827599362314 | es_ES |
dc.description.references | Knyazev, A. V., & Lashuk, I. (2008). Steepest Descent and Conjugate Gradient Methods with Variable Preconditioning. SIAM Journal on Matrix Analysis and Applications, 29(4), 1267-1280. doi:10.1137/060675290 | es_ES |
dc.description.references | CROZ, J. J. D., & HIGHAM, N. J. (1992). Stability of Methods for Matrix Inversion. IMA Journal of Numerical Analysis, 12(1), 1-19. doi:10.1093/imanum/12.1.1 | es_ES |
dc.description.references | Higham, N. J. (2002). Accuracy and Stability of Numerical Algorithms. doi:10.1137/1.9780898718027 | es_ES |
dc.description.references | Chow E Scott J On the use of iterative methods and blocking for solving sparse triangular systems in incomplete factorization preconditioning Swindon, UK Rutherford Appleton Laboratory 2016 | es_ES |