Výsledky vyhľadávania - "Communication-avoiding algorithms"

Communication Avoiding Block Low-Rank Parallel Multifrontal Triangular Solve with Many Right-Hand Sides: Communication avoiding block low-rank parallel multifrontal triangular solve with many right-hand sides

Autori: Amestoy, Patrick Boiteau, Olivier Buttari, Alfredo a ďalší

Prispievatelia: Amestoy, Patrick Boiteau, Olivier Buttari, Alfredo a ďalší

Zdroj: SIAM Journal on Matrix Analysis and Applications. 45:148-166

Predmety: block low-rank matrices, linear systems, Numerical methods for low-rank matrix approximation, matrix compression, [MATH] Mathematics [math], Parallel numerical computation, [INFO] Computer Science [cs], Direct numerical methods for linear systems and matrix inversion, communication avoiding algorithms, Computational methods for sparse matrices, LU factorization, low-rank approximations, numerical linear algebra, data sparse matrices, [INFO]Computer Science [cs], triangular solve, [MATH]Mathematics [math]

Popis súboru: application/xml; application/pdf

Prístupová URL adresa: https://zbmath.org/7791523
https://doi.org/10.1137/23m1568600
https://hal.science/hal-04082415v1/document
https://doi.org/10.1137/23m1568600
https://hal.science/hal-04082415v1

I/O-Optimal Algorithms for Symmetric Linear Algebra Kernels

Autori: Beaumont, Olivier Eyraud-Dubois, Lionel Vérité, Mathieu a ďalší

Prispievatelia: Beaumont, Olivier Eyraud-Dubois, Lionel Vérité, Mathieu a ďalší

Zdroj: Proceedings of the 34th ACM Symposium on Parallelism in Algorithms and Architectures. :423-433

Predmety: syrk, FOS: Computer and information sciences, linear algebra, Computer Science - Distributed, Parallel, and Cluster Computing, communication-avoiding algorithms, [INFO.INFO-DC] Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], 0202 electrical engineering, electronic engineering, information engineering, symmetric kernels, Distributed, Parallel, and Cluster Computing (cs.DC), 02 engineering and technology, 0101 mathematics, 01 natural sciences, cholesky

Popis súboru: application/pdf

Prístupová URL adresa: http://arxiv.org/abs/2202.10217
https://inria.hal.science/hal-03580531v1
https://inria.hal.science/hal-03580531v1/document

A 3D Parallel Algorithm for QR Decomposition

Autori: Ballard, Grey Demmel, James Grigori, Laura a ďalší

Zdroj: SPAA'18: PROCEEDINGS OF THE 30TH ACM SYMPOSIUM ON PARALLELISM IN ALGORITHMS AND ARCHITECTURES. abs/1805.05278

Predmety: Communications Engineering, Engineering, communication-avoiding algorithms, bandwidth-latency tradeoffs, communication-memory tradeoffs, cs.DC

Popis súboru: application/pdf

Prístupová URL adresa: https://escholarship.org/uc/item/6qz3r1gf
https://escholarship.org/content/qt6qz3r1gf/qt6qz3r1gf.pdf

Recent Developments in Iterative Methods for Reducing Synchronization

Autori: Zou, Qinmeng Magoulès, Frédéric

Prispievatelia: Zou, Qinmeng Magoulès, Frédéric

Zdroj: 2019 18th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES). :163-166

Predmety: asynchronous iterations, FOS: Computer and information sciences, Computer Science - Distributed, Parallel, and Cluster Computing, pipelined Krylov subspace methods, communication-avoiding algorithms, Computer Science - Mathematical Software, [MATH] Mathematics [math], Distributed, Parallel, and Cluster Computing (cs.DC), [INFO] Computer Science [cs], 0101 mathematics, Mathematical Software (cs.MS), 01 natural sciences, s-step iterative methods

Popis súboru: application/pdf

Prístupová URL adresa: http://arxiv.org/pdf/1912.00816
http://arxiv.org/abs/1912.00816
https://hal.science/hal-02399831v2/document
https://hal.science/hal-02399831v2
https://doi.org/10.1109/dcabes48411.2019.00048
https://hal.archives-ouvertes.fr/hal-02399831
https://www.arxiv-vanity.com/papers/1912.00816/
http://arxiv.org/pdf/1912.00816.pdf
https://arxiv.org/abs/1912.00816
https://dblp.uni-trier.de/db/journals/corr/corr1912.html#abs-1912-00816
https://ui.adsabs.harvard.edu/abs/2019arXiv191200816Z/abstract
https://arxiv.org/abs/1912.00816

Shifted Cholesky QR for Computing the QR Factorization of Ill-Conditioned Matrices

Autori: Fukaya, Takeshi Kannan, Ramaseshan Nakatsukasa, Yuji a ďalší

Zdroj: SIAM Journal on Scientific Computing. 42:A477-A503

Predmety: 65F30, 15A23, 65F15, 15A18, 65G50, Cholesky QR factorization, communication-avoiding algorithms, QR factorization, FOS: Mathematics, Mathematics - Numerical Analysis, Numerical Analysis (math.NA), 0101 mathematics, oblique inner product, 01 natural sciences, roundoff error analysis

Prístupová URL adresa: https://epubs.siam.org/doi/pdf/10.1137/18M1218212
http://arxiv.org/abs/1809.11085
https://dblp.uni-trier.de/db/journals/siamsc/siamsc42.html#FukayaKNYY20
https://eprints.lib.hokudai.ac.jp/dspace/handle/2115/79165
https://epubs.siam.org/doi/abs/10.1137/18M1218212
https://epubs.siam.org/doi/pdf/10.1137/18M1218212
https://ora.ox.ac.uk/objects/uuid:edc0552b-315f-4e3b-8ff9-cb7f83bde39a
https://doi.org/10.1137/18m1218212

Multiscale high-order/low-order (HOLO) algorithms and applications

Prispievatelia: Womeldorff, Geoffrey [Los Alamos National Lab. (LANL), Los Alamos, NM (United States)] (ORCID:0000000303838100)

Zdroj: Journal of Computational Physics; 330; C

Popis súboru: Medium: ED; Size: p. 21-45

Prístupová URL adresa: http://www.osti.gov/scitech/servlets/purl/1375167

A Communication-Optimal N-Body Algorithm for Direct Interactions

Autori: Driscoll, Michael Georganas, Evangelos Koanantakool, Penporn a ďalší

Zdroj: IEEE 27TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS 2013)

Predmety: 46 Information and Computing Sciences (for-2020), 4601 Applied Computing (for-2020), parallel algorithms, communication-avoiding algorithms, particle methods, parallel algorithms, communication-avoiding algorithms, particle methods

Popis súboru: application/pdf

Prístupová URL adresa: https://escholarship.org/uc/item/4m17p8bw
https://escholarship.org/content/qt4m17p8bw/qt4m17p8bw.pdf

Reconstructing householder vectors from Tall-Skinny QR

Prispievatelia: Nguyen, Hong [Univ. of California, Berkeley, CA (United States)]

Zdroj: Journal of Parallel and Distributed Computing; 85; C

Popis súboru: Medium: ED; Size: p. 3-31

Prístupová URL adresa: http://www.osti.gov/scitech/servlets/purl/1236219

Communication-avoiding symmetric-indefinite factorization

Prispievatelia: Yamazaki, Ichitaro [Univ. of Tennessee, Knoxville, TN (United States)]

Zdroj: SIAM Journal on Matrix Analysis and Applications; 35; 4

Popis súboru: Medium: ED; Size: 43 p.

Prístupová URL adresa: http://www.osti.gov/scitech/servlets/purl/1237467

A Computation- and Communication-Optimal Parallel Direct 3-Body Algorithm

Autori: Koanantakool, Penporn Yelick, Katherine

Zdroj: SC14: INTERNATIONAL CONFERENCE FOR HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS, vol 2015-January, iss January

Predmety: 46 Information and Computing Sciences (for-2020), 4601 Applied Computing (for-2020), parallel algorithms, communication-avoiding algorithms, particle methods, n-body

Prístupová URL adresa: https://escholarship.org/uc/item/4cq164ch

A Class of Communication-avoiding Algorithms for Solving General Dense Linear Systems on CPU/GPU Parallel Machines

Autori: Jack Dongarra Marc Baboulin Simplice Donfack a ďalší

Zdroj: Procedia Computer Science. 9:17-26

Predmety: linear system solvers, dense linear algebra libraries, communication-avoiding algorithms, LU factorization, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, hybrid multicore/GPU computing, 0101 mathematics, 01 natural sciences

Prístupová URL adresa: http://www.netlib.org/utk/people/JackDongarra/PAPERS/calu-hpu-iccs-2012.pdf
https://www.lri.fr/~baboulin/ICCS2012.pdf
https://hal.archives-ouvertes.fr/hal-00656457
http://www.sciencedirect.com/science/article/pii/S187705091200124X
http://dblp.uni-trier.de/db/journals/procedia/procedia9.html#BaboulinDDGRT12

Communication Avoidance for Algorithms with Sparse All-to-all Interactions

Autori: Koanantakool, Penporn

Predmety: Computer science, Communication-avoiding algorithms, Graphical model estimator, Linear algebra, N-body, Parallel algorithms, Sparse all-to-all interactions

Popis súboru: application/pdf

Prístupová URL adresa: https://escholarship.org/uc/item/78p995pk
https://escholarship.org/content/qt78p995pk/qt78p995pk.pdf

Communication-optimal parallel algorithm for Strassen’s matrix multiplication

Autori: Grey Ballard James Demmel Benjamin Lipshitz a ďalší

Prispievatelia: Grey Ballard James Demmel Benjamin Lipshitz a ďalší

Zdroj: http://www.cs.berkeley.edu/~odedsc/papers/SPAA12-CAPS.pdf.

Predmety: Categories and Subject Descriptors, F.2.1 [Analysis of Algorithms and Problem Complexity, Numerical Algorithms and Problems, Computations on matrices ACM General Terms, algorithms Keywords, parallel algorithms, communication-avoiding algorithms, fast matrix multiplication

Popis súboru: application/pdf

Relation: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.297.1626

Dostupnosť: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.297.1626
http://www.cs.berkeley.edu/~odedsc/papers/SPAA12-CAPS.pdf

Graph Expansion and Communication Costs of Fast Matrix Multiplication

Autori: Grey Ballard, James Demmel, Olga Holtz, Oded Schwartz The Pennsylvania State University CiteSeerX Archives

Prispievatelia: Grey Ballard, James Demmel, Olga Holtz, Oded Schwartz The Pennsylvania State University CiteSeerX Archives

Zdroj: http://www.cs.berkeley.edu/%7Eodedsc/papers/SLB-JACM3.pdf.

Predmety: Categories and Subject Descriptors, F.2.1 [Analysis of Algorithms and Problem Complexity, Computations on Matrices General Terms, Algorithms, Design, Performance Additional Key Words and Phrases, Communication-avoiding algorithms, Fast matrix multiplication, I/O- Complexity ACM Reference Format

Popis súboru: application/pdf

Relation: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.278.7787

Dostupnosť: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.278.7787
http://www.cs.berkeley.edu/%7Eodedsc/papers/SLB-JACM3.pdf

Tuning Hardware and Software for Multiprocessors

Autori: Mohiyuddin, Marghoob

Predmety: Computer engineering, Computer science, auto-tuning, communication-avoiding algorithms, energy-efficient hardware, hardware/software codesign, high-performance computing, linear algebra

Popis súboru: application/pdf

Prístupová URL adresa: https://escholarship.org/uc/item/1dg4w04b
https://escholarship.org/content/qt1dg4w04b/qt1dg4w04b.pdf

Communication-avoiding Krylov subspace methods

Autori: Hoemmen, Mark

Predmety: Computer Science, Mathematics, communication-avoiding algorithms, iterative methods, linear algebra, numerical methods, parallel algorithms, sparse matrices

Popis súboru: application/pdf

Prístupová URL adresa: https://escholarship.org/uc/item/7757521k
https://escholarship.org/content/qt7757521k/qt7757521k.pdf

A class of communication-avoiding algorithms for solving general dense linear systems on CPU/GPU parallel machines

Autori: Baboulin, Marc Donfack, Simplice Dongarra, Jack a ďalší

Prispievatelia: Baboulin, Marc Donfack, Simplice Dongarra, Jack a ďalší

Zdroj: https://inria.hal.science/hal-00656457 ; [Research Report] RR-7854, INRIA. 2012.

Predmety: hybrid multicore/GPU computing, dense linear algebra libraries, linear system solvers, communication-avoiding algorithms, LU factorization, [INFO.INFO-NA]Computer Science [cs]/Numerical Analysis [cs.NA]

Dostupnosť: https://inria.hal.science/hal-00656457
https://inria.hal.science/hal-00656457v3/document
https://inria.hal.science/hal-00656457v3/file/RR-7854.pdf

Solving dense linear systems on accelerated multicore architectures

Résoudre des systèmes linéaires denses sur des architectures composées de processeurs multicœurs et d'accélerateurs

Autori: Rémy, Adrien

Thesis Advisors: Paris 11, Baboulin, Marc

Predmety: Systèmes linéaires denses, Factorisation LU, Bibliothèques logicielles pour l’algèbre linéaire dense, Bibliothèque MAGMA, Calcul hybride multicœur/GPU, Processeurs graphiques, Intel Xeon Phi, ccNUMA, Communication-avoiding, Randomisation, Placement des processus légers, Dense linear systems, LU factorization, Dense linear algebra libraries, MAGMA library, Hybrid multicore/GPU computing, Graphics process units, Communication-avoiding algorithms, Randomization, Thread placement

Dostupnosť: http://www.theses.fr/2015PA112138/document

Contention Bounds for Combinations of Computation Graphs and Network Topologies

Autori: Ballard, Grey Demmel, James Gearhart, Andrew a ďalší

Prispievatelia: Ballard, Grey Demmel, James Gearhart, Andrew a ďalší

Zdroj: DTIC

Predmety: Computer Systems, NETWORK TOPOLOGY, ALGORITHMS, COMPUTATIONS, DATA LINKS, GRAPHS, COMMUNICATION-AVOIDING ALGORITHMS, STRONG SCALING, COMMUNICATION COSTS

Popis súboru: text/html

Relation: http://www.dtic.mil/docs/citations/ADA614374

Dostupnosť: http://www.dtic.mil/docs/citations/ADA614374
http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA614374

Solving dense linear systems on accelerated multicore architectures ; Résoudre des systèmes linéaires denses sur des architectures composées de processeurs multicœurs et d’accélerateurs

Autori: Rémy, Adrien Laboratoire de Recherche en Informatique (LRI) Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS) a ďalší

Prispievatelia: Rémy, Adrien Laboratoire de Recherche en Informatique (LRI) Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS) a ďalší

Zdroj: https://theses.hal.science/tel-01225745 ; Hardware Architecture [cs.AR]. Université Paris Sud - Paris XI, 2015. English. ⟨NNT : 2015PA112138⟩.

Predmety: Thread placement, Randomization, Communication-avoiding algorithms, ccNUMA, Intel Xeon Phi, Graphics process units, Hybrid multicore/GPU computing, MAGMA library, Dense linear algebra libraries, LU factorization, Dense linear systems, Calcul hybride multicœur/GPU, Placement des processus légers, Randomisation, Communication-avoiding, Processeurs graphiques, Bibliothèque MAGMA, Bibliothèques logicielles pour l’algèbre linéaire dense, Factorisation LU, Systèmes linéaires denses, [INFO.INFO-AR]Computer Science [cs]/Hardware Architecture [cs.AR]

Relation: NNT: 2015PA112138

Dostupnosť: https://theses.hal.science/tel-01225745
https://theses.hal.science/tel-01225745v1/document
https://theses.hal.science/tel-01225745v1/file/VD2_REMY_ADRIEN_08072015.pdf