Suchergebnisse - "2.5D algorithms"

Exploiting Multiple Levels of Parallelism in Sparse Matrix-Matrix Multiplication

Autoren: Azad, Ariful Ballard, Grey Buluç, Aydin et al.

Quelle: SIAM Journal on Scientific Computing. 38(6)

Schlagwörter: 4901 Applied Mathematics (for-2020), 4903 Numerical and Computational Mathematics (for-2020), 49 Mathematical Sciences (for-2020), parallel computing, numerical linear algebra, sparse matrix-matrix multiplication, 2.5D algorithms, 3D algorithms, multi threading, SpGEMM, 2D decomposition, graph algorithms, cs.DC, cs.DC, cs.NA, math.NA, 0102 Applied Mathematics (for), 0103 Numerical and Computational Mathematics (for), 0802 Computation Theory and Mathematics (for), Numerical & Computational Mathematics (science-metrix), 4901 Applied mathematics (for-2020), 4903 Numerical and computational mathematics (for-2020)

Dateibeschreibung: application/pdf

Zugangs-URL: https://escholarship.org/uc/item/9x19n6cd
https://escholarship.org/content/qt9x19n6cd/qt9x19n6cd.pdf

Exploiting Multiple Levels of Parallelism in Sparse Matrix-Matrix Multiplication

Weitere Verfasser: Williams, Samuel [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)]

Quelle: SIAM Journal on Scientific Computing; 38; 6

Dateibeschreibung: Medium: ED; Size: p. C624-C651

Zugangs-URL: http://www.osti.gov/scitech/servlets/purl/1378775

Planning Complex Inspection Tasks Using Redundant Roadmaps.

Autoren: Englot, Brendan Hover, Franz

Quelle: Springer Tracts in Advanced Robotics; p327-343, 17p

Numerical simulation and dimension reduction analysis of electromagnetic logging while drilling of horizontal wells in complex structures.

Autoren: Wu, Zhen-Guan Deng, Shao-Gui He, Xu-Quan et al.

Quelle: Petroleum Science (Springer Nature); Jun2020, Vol. 17 Issue 3, p645-657, 13p

Schlagwörter: HORIZONTAL wells, FAST Fourier transforms, FINITE difference method, SANDSTONE, MAGNETIC dipoles

Exploiting multiple levels of parallelism in sparse matrix-matrix multiplication

Autoren: Azad, A Ballard, G Buluç, A et al.

Quelle: SIAM Journal on Scientific Computing; vol 38, iss 6, C624-C651; 1064-8275

Index Begriffe: parallel computing, numerical linear algebra, sparse matrix-matrix multiplication, 2.5D algorithms, 3D algorithms, multi threading, SpGEMM, 2D decomposition, graph algorithms, cs.DC, cs.NA, math.NA, Numerical & Computational Mathematics, Applied Mathematics, Numerical and Computational Mathematics, Computation Theory and Mathematics, Electrical and Electronic Engineering, article

URL: https://escholarship.org/uc/item/9x19n6cd
https://escholarship.org/

Distributed-Memory Sparse Kernels for Machine Learning

Autoren: Bharadwaj, Vivek Buluç, Aydin Demmel, James

Index Begriffe: Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Machine Learning, text

URL: http://arxiv.org/abs/2203.07673

A simplified 3D finite difference method for electromagnetic logging while drilling simulation in symmetrical models.

Autoren: Li, Fengbo Wu, Zhenguan Ni, Weining et al.

Quelle: Frontiers in Earth Science; 2025, p1-13, 13p

Schlagwörter: SYMMETRIC domains, FINITE difference method, NATURAL gas prospecting, PETROLEUM prospecting, MAGNETIC dipoles

External phantom-based validation of a deep-learning network trained for upscaling of digital low count PET data.

Autoren: Braune, Anja Hosch, René Kersting, David et al.

Quelle: EJNMMI Physics; 4/16/2025, Vol. 12 Issue 1, p1-22, 22p

Schlagwörter: POSITRON emission tomography, GENERATIVE adversarial networks, ARTIFICIAL intelligence, IMAGE processing, DEEP learning, IMAGE denoising

Provably Efficient Algorithms for Numerical Tensor Algebra

Autoren: Solomonik, Edgar Demmel, James1

Index Begriffe: Computer science, numerical linear algebra, parallel algorithms, tensor computations, publication

URL: https://escholarship.org/uc/item/00b4r0mv
https://escholarship.org/

Provably Efficient Algorithms for Numerical Tensor Algebra

Autoren: Demmel, James Solomonik, Edgar

Index Begriffe: Computer science, numerical linear algebra, parallel algorithms, tensor computations, publication

URL: https://escholarship.org/uc/item/00b4r0mv
https://escholarship.org/content/qt00b4r0mv/qt00b4r0mv.pdf

Communication avoiding and overlapping for numerical linear algebra

Autoren: Georganas, Evangelos González-Domínguez, Jorge Solomonik, Edgar et al.

Index Begriffe: Program processors, Bandwidth, Partitioning algorithms, Linear algebra, Message systems, Hardware, Layout, conference output

URL: http://hdl.handle.net/2183/23395
http://dx.doi.org/10.1109/SC.2012.32

Communication Avoiding and Overlapping for Numerical Linear Algebra

Autoren: CALIFORNIA UNIV BERKELEY DEPT OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE Georganas, Evangelos Gonzalez-Dominguez, Jorge et al.

Quelle: DTIC

Index Begriffe: Theoretical Mathematics, LINEAR ALGEBRA, ALGORITHMS, COMMUNICATION AND RADIO SYSTEMS, COMPUTER PROGRAMS, CRITICAL PATH METHODS, NUMERICAL ANALYSIS, OVERLAP, Text

URL: https://apps.dtic.mil/docs/citations/ADA561679

Communication avoiding and overlapping for numerical linear algebra.

Autoren: Georganas, Evangelos Gonzalez-Dominguez, Jorge Solomonik, Edgar et al.

Quelle: 2012 International Conference for High Performance Computing, Networking, Storage & Analysis; 1/ 1/2012, p1-11, 11p

Fast forward modeling and response analysis of extra-deep azimuthal resistivity measurements in complex model.

Autoren: Zhang, Pan Deng, Shaogui Yuan, Xiyong et al.

Quelle: Frontiers in Earth Science; 2025, p1-13, 13p

Schlagwörter: FINITE element method, FEATURE extraction, BOUNDARY element methods, TECHNOLOGICAL innovations, DIRECTIONAL drilling

Increasing the Efficiency of Sparse Matrix-Matrix Multiplication with a 2.5D Algorithm and One-Sided MPI

Autoren: Lazzaro, Alfio VandeVondele, Joost Hutter, Juerg et al.

Index Begriffe: Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Mathematical Software, text

URL: http://arxiv.org/abs/1705.10218

Slicing Is All You Need: Towards A Universal One-Sided Algorithm for Distributed Matrix Multiplication

Autoren: Brock, Benjamin Golin, Renato

Schlagwörter: Artificial Intelligence, Distributed, Parallel, and Cluster Computing

Zugangs-URL: http://arxiv.org/abs/2510.08874

Exploiting Multiple Levels of Parallelism in Sparse Matrix-Matrix Multiplication

Autoren: Azad, Ariful Ballard, Grey Buluc, Aydin et al.

Index Begriffe: Computer Science - Distributed, Parallel, and Cluster Computing, Mathematics - Numerical Analysis, text

URL: http://arxiv.org/abs/1510.00844

EXPLOITING MULTIPLE LEVELS OF PARALLELISM IN SPARSE MATRIX-MATRIX MULTIPLICATION.

Autoren: AZAD, ARIFUL BALLARD, GREY BULUÇ, AYDIN et al.

Quelle: SIAM Journal on Scientific Computing; 2016, Vol. 38 Issue 6, pC624-C651, 28p

Schlagwörter: SPARSE matrices, MATRICES (Mathematics), MULTIPLICATION

Communication-optimal parallel 2.5D matrix multiplication and LU factorization algorithms

Autoren: Edgar Solomonik James Demmel The Pennsylvania State University CiteSeerX Archives

Weitere Verfasser: Edgar Solomonik James Demmel The Pennsylvania State University CiteSeerX Archives

Quelle: http://www.netlib.org/lapack/lawnspdf/lawn248.pdf.

Dateibeschreibung: application/pdf

Relation: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.5038; http://www.netlib.org/lapack/lawnspdf/lawn248.pdf

Verfügbarkeit: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.5038
http://www.netlib.org/lapack/lawnspdf/lawn248.pdf

Communication Avoiding and Overlapping for Numerical Linear Algebra

Autoren: Yili Zheng Juan Touriño Jorge González-Domínguez et al.

Quelle: RUC. Repositorio da Universidade da Coruña
instname

Schlagwörter: Bandwidth, Hardware, Layout, Message systems, Linear algebra, 0102 computer and information sciences, 0101 mathematics, Program processors, 01 natural sciences, Partitioning algorithms

Zugangs-URL: https://ruc.udc.es/dspace/bitstream/2183/23395/2/E.Georganas_2012_Communication_Avoiding_and_Overlapping_for_Numerical_Linear_Algebra.pdf
http://hdl.handle.net/2183/23395