Výsledky vyhledávání - Algorithms for specific class of architecture

Towards Megacity-Scale Wind Flow Simulations on Many-Core CPU-Accelerator Systems: Towards megacity-scale wind flow simulations on many-core CPU-accelerator systems

Autoři: Lei Xu Qingyang Zhang Kai Lu a další

Zdroj: SIAM Journal on Scientific Computing. 47:B402-B427

Témata: Numerical algorithms for specific classes of architectures, lattice Boltzmann method, city-wide meteorological micro-scale, heterogeneous parallel computing, Particle methods and lattice-gas methods, high-performance computing, computational wind engineering

Popis souboru: application/xml

Genetic NEAT-Based Method for Multi-Class Classification

Autoři: Alfaham, Abdallah Van Raemdonck, Stijn Mercelis, Siegfried

Zdroj: urn:isbn:9798331529314
ACAI 2024 - 2024 7th International Conference on Algorithms, Computing and Artificial Intelligence (2024); 2024 7th International Conference on Algorithms, Computing and Artificial Intelligence (ACAI), Guangzhou, China [CN], 20-12-2024 => 22-12-2024

Témata: Automated Architecture, Genetic Algorithms, NEAT, Supervised Learning, Automated architecture, Class labels, Evolutionary mechanisms, Genetic mechanism, Machine learning problem, Multi-class classification, Neuro evolutions, Neuroevolution of augmenting topologies, Performance, Specific class, Artificial Intelligence, Computer Science Applications, Computer Vision and Pattern Recognition, Statistics, Probability and Uncertainty, Computational Mathematics, Control and Optimization, Modeling and Simulation, Engineering, computing & technology, Computer science, Ingénierie, informatique & technologie, Sciences informatiques

Relation: http://xplorestaging.ieee.org/ielx8/10899099/10899447/10899662.pdf?arnumber=10899662

Přístupová URL adresa: https://orbi.uliege.be/handle/2268/334608

Deep Neural Network for Solving Differential Equations Motivated by Legendre-Galerkin Approximation: Deep neural network for solving differential equations motivated by Legendre-Galerkin approximation

Autoři: Chudomelka, Bryce Hong, Youngjoon Morgan, John a další

Zdroj: International Journal of Numerical Analysis and Modeling. 21:652-673

Témata: data driven numerical method, Numerical algorithms for specific classes of architectures, neural network, deep learning, spectral element method, Legendre-Galerkin method, Spectral, collocation and related methods for boundary value problems involving PDEs, Numerical solution of discretized equations for boundary value problems involving PDEs, Computational aspects of data analysis and big data, Artificial neural networks and deep learning

Popis souboru: application/xml

Přístupová URL adresa: https://zbmath.org/7954065
https://doi.org/10.4208/ijnam2024-1026

SlabLU: a two-level sparse direct solver for elliptic PDEs

Autoři: Anna Yesypenko Per-Gunnar Martinsson

Zdroj: Advances in Computational Mathematics. 50

Témata: Finite difference methods for boundary value problems involving PDEs, Numerical Analysis, Random matrices (algebraic aspects), GPU, Numerical methods for low-rank matrix approximation, matrix compression, high-order discretization, Parallel numerical computation, Numerical Analysis (math.NA), Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs, Numerical solution of discretized equations for boundary value problems involving PDEs, Direct numerical methods for linear systems and matrix inversion, multifrontal solver, 01 natural sciences, Factorization of matrices, direct solver, Computational methods for sparse matrices, Numerical algorithms for specific classes of architectures, Boundary value problems for second-order elliptic equations, sparse direct solver, FOS: Mathematics, Spectral, collocation and related methods for boundary value problems involving PDEs, randomized linear algebra, Helmholtz equation, 0101 mathematics

Popis souboru: application/xml

Přístupová URL adresa: http://arxiv.org/abs/2211.07572

A fine-grain load-adaptive algorithm of the 2D discrete wavelet transform for multithreaded architectures

Autoři: Ashfaq Khokhar Guang R. Gao Parimala Thulasiraman a další

Zdroj: Journal of Parallel and Distributed Computing. 64:68-78

Témata: Numerical algorithms for specific classes of architectures, Numerical methods for wavelets, 0202 electrical engineering, electronic engineering, information engineering, Parallel numerical computation, 02 engineering and technology, Parallel algorithms in computer science, 0101 mathematics, multithreaded algorithm, 01 natural sciences

Popis souboru: application/xml

Přístupová URL adresa: https://zbmath.org/2099275
https://doi.org/10.1016/j.jpdc.2003.06.003

Memory-Efficient Sparse Matrix-Matrix Multiplication by Row Merging on Many-Core Architectures: Memory-efficient sparse matrix-matrix multiplication by row merging on many-core architectures

Autoři: Kerstin Küpper Uwe Naumann Felix Gremse

Zdroj: SIAM Journal on Scientific Computing. 40:C429-C449

Témata: Computational methods for sparse matrices, Complexity and performance of numerical algorithms, sparse matrix-matrix multiplication, Numerical algorithms for specific classes of architectures, GPU-programming, algebraic multigrid, Galerkin product, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, fluorescence-mediated tomography

Popis souboru: application/xml

Přístupová URL adresa: https://dblp.uni-trier.de/db/journals/siamsc/siamsc40.html#GremseKN18
https://publications.rwth-aachen.de/record/745400
https://epubs.siam.org/doi/abs/10.1137/17M1121378
https://doi.org/10.1137/17M1121378

Three-Dimensional Numerical Simulation of Droplet Evaporation Using the Lattice Boltzmann Method Based on GPU-CUDA Accelerated Algorithm: Three-dimensional numerical simulation of droplet evaporation using the lattice Boltzmann method based on GPU-CUDA accelerated algorithm

Autoři: Qingyu Zhang Changsheng Zhu Mingfang Zhu

Zdroj: Communications in Computational Physics. 23:1150-1166

Témata: 0209 industrial biotechnology, Numerical algorithms for specific classes of architectures, lattice Boltzmann modeling, Particle methods and lattice-gas methods, 02 engineering and technology, GPU computing, 0101 mathematics, contact angle, 01 natural sciences, evaporation

Popis souboru: application/xml

Přístupová URL adresa: https://zbmath.org/7415735
https://doi.org/10.4208/cicp.oa-2016-0185

VLSI algorithms and architectures for complex householder transformation with applications to array processing: VLSI algorithms and architectures for complex Householder transformation with applications to array processing

Autoři: K.J.R. Liu Kung Yao S.F. Hsieh a další

Zdroj: Journal of VLSI signal processing systems for signal, image and video technology. 4:53-68

Témata: Numerical algorithms for specific classes of architectures, Hardware implementations of nonnumerical algorithms (VLSI algorithms, etc.), 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology

Popis souboru: application/xml

Přístupová URL adresa: https://drum.lib.umd.edu/bitstream/1903/5131/1/TR_91-84.pdf
https://zbmath.org/644410
https://doi.org/10.1007/bf00930618
https://dblp.uni-trier.de/db/journals/vlsisp/vlsisp4.html#TangLHY92
https://doi.org/10.1007/BF00930618
https://link.springer.com/article/10.1007/BF00930618
https://drum.lib.umd.edu/handle/1903/5131
https://rd.springer.com/article/10.1007/BF00930618
https://drum.lib.umd.edu/bitstream/1903/5131/1/TR_91-84.pdf

A balanced submatrix merging algorithm for multiprocessor architectures

Autoři: Eleanor Chu Alan George

Zdroj: Parallel Computing. 18:1-10

Témata: Numerical solutions to overdetermined systems, pseudoinverses, Numerical algorithms for specific classes of architectures, multiprocessor machines, Distributed algorithms, large scale least squares computations, parallel algorithms, Givens rotations, 0102 computer and information sciences, 0101 mathematics, merging algorithm, 01 natural sciences

Popis souboru: application/xml

Přístupová URL adresa: https://zbmath.org/35977
https://doi.org/10.1016/0167-8191(92)90106-h
http://dblp.uni-trier.de/db/journals/pc/pc18.html#ChuG92
https://repository.exst.jaxa.jp/dspace/handle/a-is/329431
https://www.sciencedirect.com/science/article/pii/016781919290106H
https://dblp.uni-trier.de/db/journals/pc/pc18.html#ChuG92
https://ntrs.nasa.gov/search.jsp?R=19920041868

MFEM: A modular finite element methods library: MFEM: a modular finite element methods library

Autoři: Robert Anderson Julian Andrej Andrew Barker a další

Přispěvatelé: Robert Anderson Julian Andrej Andrew Barker a další

Zdroj: Computers & Mathematics with Applications. 81:42-74

Témata: Finite element methods, FOS: Computer and information sciences, Multigrid methods, domain decomposition for boundary value problems involving PDEs, Finite element methods applied to problems in solid mechanics, Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs, Mesh generation, refinement, and adaptive methods for boundary value problems involving PDEs, 01 natural sciences, Multistep, Runge-Kutta and extrapolation methods for ordinary differential equations, High-order methods, Numerical algorithms for specific classes of architectures, Finite difference methods for initial value and initial-boundary value problems involving PDEs, 0103 physical sciences, FOS: Mathematics, finite element methods, numerical PDEs, Mathematics - Numerical Analysis, 0101 mathematics, High-performance computing, Numerical methods for eigenvalue problems for boundary value problems involving PDEs, Open-source scientific software, matrix-free algorithms, high-performance computing, Parallel numerical computation, Numerical Analysis (math.NA), Software, source code, etc. for problems pertaining to numerical analysis, Matrix-free algorithms, high-order methods, Computer Science - Mathematical Software, Finite element, Rayleigh-Ritz and Galerkin methods for initial value and initial-boundary value problems involving PDEs, open-source scientific software, Numerical PDEs, Mathematical Software (cs.MS), Finite element methods applied to problems in fluid mechanics

Popis souboru: application/xml; application/pdf

Přístupová URL adresa: https://www.sciencedirect.com/science/article/am/pii/S0898122120302583
http://arxiv.org/abs/1911.09220
https://zbmath.org/7288706
https://doi.org/10.1016/j.camwa.2020.06.009
https://ui.adsabs.harvard.edu/abs/2019arXiv191109220A/abstract
https://repository.tudelft.nl/islandora/object/uuid%3A553103d4-1337-44a3-9638-47ff85dbd5d1
http://export.arxiv.org/pdf/1911.09220
http://doi.org/10.1016/j.camwa.2020.06.009
https://dblp.uni-trier.de/db/journals/corr/corr1911.html#abs-1911-09220
https://arxiv.org/abs/1911.09220
http://resolver.tudelft.nl/uuid:553103d4-1337-44a3-9638-47ff85dbd5d1

Geometric computer vision meets deep learning for autonomous driving applications

Autoři: García López, Javier

Thesis Advisors: Moreno-Noguer, Francesc, Agudo Martínez, Antonio, Institut de Robòtica i Informàtica Industrial

Zdroj: TDX (Tesis Doctorals en Xarxa)

Témata: 3D pose estimation, Deep learning, Neural architecture search, Depth estimation, Adaptive network design, Embedded platform, Estimación de pose 3D, Aprendizaje profundo, Diseño de red adaptativo, Sistemas embebidos, Àrees temàtiques de la UPC::Informàtica

Popis souboru: application/pdf

Přístupová URL adresa: http://hdl.handle.net/10803/672708
https://dx.doi.org/10.5821/dissertation-2117-355673

Modeling the Performance of Geometric Multigrid Stencils on Multicore Computer Architectures: Modeling the performance of geometric multigrid stencils on multicore computer architectures

Autoři: Ghysels, Pieter Vanroose, Wim

Zdroj: SIAM journal on scientific computing

Témata: Computer. Automation, Finite difference methods for boundary value problems involving PDEs, performance model, bandwidth, Complexity and performance of numerical algorithms, Multigrid methods, domain decomposition for boundary value problems involving PDEs, Numerical algorithms for specific classes of architectures, multicore, 0101 mathematics, multigrid, 01 natural sciences, Mathematics

Popis souboru: application/xml; pdf

Přístupová URL adresa: https://repository.uantwerpen.be/docman/irua/e52f99/a7ee861e.pdf
https://zbmath.org/6444115
https://doi.org/10.1137/130935781
https://hdl.handle.net/10067/1244840151162165141
https://repository.uantwerpen.be/docman/irua/e52f99/a7ee861e.pdf

GPU acceleration of Volumetric Lattice Boltzmann Method for patient-specific computational hemodynamics: GPU acceleration of volumetric lattice Boltzmann method for patient-specific computational hemodynamics

Autoři: Zhiqiang Wang Alan P. Sawchuck Huidan Yu a další

Zdroj: Computers & Fluids. 115:192-200

Témata: Physiological flow, patient-specific computational hemodynamics, Numerical algorithms for specific classes of architectures, parallel computing, volumetric lattice Boltzmann Method, 0103 physical sciences, graphics processor unit, Particle methods and lattice-gas methods, Physiological flows, 01 natural sciences

Popis souboru: application/xml

Přístupová URL adresa: https://zbmath.org/6893439
https://doi.org/10.1016/j.compfluid.2015.04.004
https://www.sciencedirect.com/science/article/pii/S0045793015001139

2D Prediction of the Nutritional Composition of Dishes from Food Images: Deep Learning Algorithm Selection and Data Curation Beyond the Nutrition5k Project.

Autoři: Bianco, Rachele Coluccia, Sergio Marinoni, Michela a další

Zdroj: Nutrients. Jul2025, Vol. 18 Issue 13, p2196. 23p.

A framework for high‐performance matrix multiplication based on hierarchical abstractions, algorithms and optimized low‐level kernels: A framework for high-performance matrix multiplication based on hierarchical abstractions, algorithms and optimized low-level kernels

Autoři: Vinod K. Valsalam Anthony Skjellum

Zdroj: Concurrency and Computation: Practice and Experience. 14:805-839

Témata: Strassen's algorithm, Computing methodologies and applications, Numerical algorithms for specific classes of architectures, polyalgorithms, matrix multiplication, Other matrix algorithms, Morton order, Distributed algorithms, kernel interface, 0101 mathematics, 01 natural sciences, hierarchical matrix storage

Popis souboru: application/xml

VLSI architectures for the discrete wavelet transform

Autoři: Mary Jane Irwin Robert Michael Owens M. Vishwanath

Zdroj: IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing. 42:305-316

Témata: linear systolic arrays, discrete wavelet transform, Numerical algorithms for specific classes of architectures, Mallat's pyramid algorithm, Hardware implementations of nonnumerical algorithms (VLSI algorithms, etc.), recursive pyramid algorithm, VLSI architectures, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, Numerical methods for discrete and fast Fourier transforms

Popis souboru: application/xml

Přístupová URL adresa: https://ieeexplore.ieee.org/abstract/document/386170
https://pennstate.pure.elsevier.com/en/publications/vlsi-architectures-for-the-discrete-wavelet-transform
http://ieeexplore.ieee.org/document/386170

An optimal schedule for Gaussian elimination on an MIMD architecture

Autoři: Rachid Saad

Zdroj: Journal of Computational and Applied Mathematics. 185:91-106

Témata: computational complexity, Scheduling, Applied Mathematics, Parallel numerical computation, MIMD, 0102 computer and information sciences, Direct numerical methods for linear systems and matrix inversion, 01 natural sciences, Computational Mathematics, Complexity and performance of numerical algorithms, Numerical algorithms for specific classes of architectures, Gaussian elimination, scheduling, 0101 mathematics, parallel computation

Popis souboru: application/xml

Přístupová URL adresa: https://zbmath.org/2217860
https://doi.org/10.1016/j.cam.2005.01.028
https://www.sciencedirect.com/science/article/pii/S0377042705000518
http://ui.adsabs.harvard.edu/abs/2006JCoAM.185...91S/abstract
https://dialnet.unirioja.es/servlet/articulo?codigo=1275896
https://core.ac.uk/display/82764463

Optimization Based Nonoverlapping Domain Decomposition Algorithms and Their Convergence: Optimization based nonoverlapping domain decomposition algorithms and their convergence

Autoři: Qiang Du

Zdroj: SIAM Journal on Numerical Analysis. 39:1056-1077

Témata: Variational methods for second-order elliptic equations, Multigrid methods, domain decomposition for boundary value problems involving PDEs, Laplace operator, Helmholtz equation (reduced wave equation), Poisson equation, Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs, Poisson equation, algorithms, 01 natural sciences, domain decomposition, Numerical algorithms for specific classes of architectures, finite element, 0101 mathematics, parallel computation, optimization, large scale problems

Popis souboru: application/xml

Přístupová URL adresa: https://zbmath.org/1764349
https://doi.org/10.1137/s0036142900380273
https://dblp.uni-trier.de/db/journals/siamnum/siamnum39.html#Du01
https://www.jstor.org/stable/3061945
https://locus.siam.org/doi/abs/10.1137/S0036142900380273
https://epubs.siam.org/doi/abs/10.1137/S0036142900380273

Algorithm 810: The SLEIGN2 Sturm-Liouville Code: Algorithm 810: The SLEIGN2 Sturm-Liouville code

Autoři: Anton Zettl William Norrie Everitt P. B. Bailey

Zdroj: ACM Transactions on Mathematical Software. 27:143-192

Témata: Numerical algorithms for specific classes of architectures, 65l15 34l16 65y15, Numerical methods for ordinary differential equations, 0101 mathematics, 01 natural sciences

Popis souboru: application/xml

Přístupová URL adresa: https://zbmath.org/2187795
https://doi.org/10.1145/383738.383739
https://dialnet.unirioja.es/servlet/articulo?codigo=2646310
https://dl.acm.org/doi/10.1145/383738.383739
https://doi.org/10.1145/383738.383739
https://dblp.uni-trier.de/db/journals/toms/toms27.html#BaileyEZ01

Systolic and hyper-systolic algorithms for the gravitational N-body problem, with an application to Brownian motion: Systolic and hyper-systolic algorithms for the gravitational \(N\)-body problem, with an application to Brownian motion

Autoři: David Merritt Ernst Nils Dorband Marc Hemsendorf

Zdroj: Journal of Computational Physics. 185:484-511

Témata: FOS: Computer and information sciences, supermassive black hole, Astrophysics (astro-ph), systolic algorithm, gravitational \(N\)-body problem, FOS: Physical sciences, Equations of motion in general relativity and gravitational theory, Computational Physics (physics.comp-ph), Astrophysics, 01 natural sciences, Milky Way galaxy, Numerical algorithms for specific classes of architectures, Computer Science - Distributed, Parallel, and Cluster Computing, 0103 physical sciences, Computational methods for problems pertaining to relativity and gravitational theory, Analysis of algorithms, distributed-memory computers, Distributed, Parallel, and Cluster Computing (cs.DC), Brownian motion, Physics - Computational Physics

Popis souboru: application/xml

Přístupová URL adresa: http://arxiv.org/pdf/astro-ph/0112092.pdf
http://arxiv.org/abs/astro-ph/0112092
https://dl.acm.org/doi/10.1016/S0021-9991%2802%2900067-0
http://www.sciencedirect.com/science/article/pii/S0021999102000670
https://ui.adsabs.harvard.edu/abs/2003JCoPh.185..484D/abstract
https://dblp.uni-trier.de/db/journals/corr/corr0112.html#astro-ph-0112092
https://www.sciencedirect.com/science/article/pii/S0021999102000670
https://arxiv.org/abs/astro-ph/0112092
https://arxiv.org/abs/astro-ph/0112092
http://export.arxiv.org/pdf/astro-ph/0112092
https://arxiv.org/pdf/astro-ph/0112092.pdf