Filters








648,801 Hits in 3.1 sec

Parallel Numerical Algorithms [chapter]

Patrick Amestoy, Daniela di Serafino, Rob Bisseling, Enrique S. Quintana-Ortí, Marian Vajteršic
2010 Lecture Notes in Computer Science  
Heath Parallel Numerical Algorithms 10 / 66 Triangular Systems Parallel Algorithms Wavefront Algorithms Cyclic Algorithms Fine-Grain Algorithm 2-D Algorithm 1-D Column Algorithm 1-D Row Algorithm  ...  Heath Parallel Numerical Algorithms 11 / 66 Triangular Systems Parallel Algorithms Wavefront Algorithms Cyclic Algorithms Fine-Grain Algorithm 2-D Algorithm 1-D Column Algorithm 1-D Row Algorithm  ... 
doi:10.1007/978-3-642-15291-7_7 fatcat:bktre4vnlbf2xbx5lml4qiflge

Parallel Numerical Algorithms: An Introduction [chapter]

David E. Keyes
1997 ICASE/LaRC Interdisciplinary Series in Science and Engineering  
The field of parallel numerical algorithms could be defined as "scientific computing in the presence of nonuniform memory access."  ...  If future computational scientists will find the title "Parallel Numerical Algorithms" anachronistic, they will at least concur with the importance of "parallel algorithmic thinking," and readers of this  ... 
doi:10.1007/978-94-011-5412-3_1 fatcat:f5tnen3tarhc3firxlkaj4at4e

Parallel processing of numerical transport algorithms

B.R. Wienke, R.E. Hiromoto
1985 Computer Physics Communications  
lily. wtvstm TO Conference on Vector and Parallel Processors in Computational Sciehce 11, Oxford, England, 08/2[1 -08/31/84. *$@f 4' ', !)  ...  PARALLEL ITERATION SCHEMES The foregoing stra!rgics have evo!vcd over a number of years in production applications. They form a compart nucleus for developing pmallcl algorithms.  ...  The parallel chaotic sweeps require fewer iterations than parallel inuer-outer sweeps and less time to inner convergence.  ... 
doi:10.1016/0010-4655(85)90174-2 fatcat:ywawzjf3wfdlblruw3tnf5z2f4

3. A Bibliography on Parallel and Vector Numerical Algorithms [chapter]

James M. Ortega, Robert G. Voigt, Charles H. Romine
1990 Parallel Algorithms for Matrix Computations  
Vectorization of a penalty function algorithm for well scheduling, in Gary [3] I. ABU-SHOMAYS [1985].  ...  Although this is a bibliography on numerical methods, we have included a number of other references on machine architecture, programming languages, and other topics of interest to scientific computing.  ...  GENTLEMAN [1981] , Design of numerical algorithms for parallel processing. Presented at I [746] J . GILBERT [1988] . A n eficient parallel sparse partial pivoting algorithm,Tech.  ... 
doi:10.1137/1.9781611971705.ch3 fatcat:pkjwqy26bfcjneyf76jqebybei

Parallelism Resource of Numerical Algorithms. Version 1 [article]

Valentina N. Aleeva, Rifkhat Zh. Aleev
2022 arXiv   pre-print
We also describe a software Q-system for studying the parallelism resource of numerical algorithms. This system enables to compute and compare the parallelism resources of numerical algorithms.  ...  Furthermore, we suggest a method for designing of parallel programs for numerical algorithms. This method is based on a representation of a numerical algorithm in the form of a Q-determinant.  ...  We can construct the Q-determinant for any numerical algorithm. 2. We can describe the Q-effective implementation of the algorithm. 3.  ... 
arXiv:2207.11915v1 fatcat:y3jaydohhjfgzlyjfmhgoz7zyy

Asynchronous Parallel Stochastic Gradient Descent - A Numeric Core for Scalable Distributed Machine Learning Algorithms [article]

Janis Keuper, Franz-Josef Pfreundt
2015 arXiv   pre-print
The implementation of a vast majority of machine learning (ML) algorithms boils down to solving a numerical optimization problem.  ...  This paper presents a novel parallel updating algorithm for SGD, which utilizes the asynchronous single-sided communication paradigm.  ...  This leaves little room for algorithmic optimization other than the choice of the numerical optimization method.  ... 
arXiv:1505.04956v5 fatcat:rhrjhdl6jvg5xdn2wcyjqxwsva

PAGANI: A Parallel Adaptive GPU Algorithm for Numerical [article]

Ioannis Sakiotis, Kamesh Arumugam, Marc Paterno, Desh Ranjan, Balša Terzić, Mohammad Zubair
2021 arXiv   pre-print
We present a new adaptive parallel algorithm for the challenging problem of multi-dimensional numerical integration on massively parallel architectures.  ...  Our algorithm typically outperforms other existing deterministic parallel methods.  ...  This paper presents a deterministic parallel algorithm for multidimensional numerical integration suitable for GPUs that outperforms existing deterministic methods.  ... 
arXiv:2104.06494v2 fatcat:vzfw7xay6naapm4nutmyzoxagm

Novel modifications of parallel Jacobi algorithms

Sanja Singer, Saša Singer, Vedran Novaković, Aleksandar Ušćumlić, Vedran Dunjko
2011 Numerical Algorithms  
the parallel one-sided algorithms.  ...  The numerical testing performed indicates that the hyperbolic algorithms may be superior to the trigonometric ones, although, in theory, the latter seem more natural.  ...  In the final section, we give some results of numerical testing.  ... 
doi:10.1007/s11075-011-9473-6 fatcat:jg5xshm5bnferogqvdglevfeua

Parallel numerical algorithms for optimization of electrical cables

Raim. Èiegis, Rem. Èiegis, M. Meilûnas, G. Jankevièiutë, V. Starikovièius
2008 Mathematical Modelling and Analysis  
Let T (X, t) describe a distribution of the temperature in electrical cables [1]: Initial and boundary conditions: We have proposed efficient parallel numerical algorithms for simulation of temperature  ...  Parallel multilevel algorithms are developed using the master-slave and data decomposition paradigms [4] .  ...  Parallel multilevel algorithms are developed using the master-slave and data decomposition paradigms [4] .  ... 
doi:10.3846/1392-6292.2008.13.471-482 fatcat:vfcopxuovnahrj2ugnwuqzl3da

Parallel Distance-k Coloring Algorithms for Numerical Optimization [chapter]

Assefaw Hadish Gebremedhin, Fredrik Manne, Alex Pothen
2002 Lecture Notes in Computer Science  
In the current work, we present the first practical shared address space parallel algorithms for these problems.  ...  Hence, there is a need for both shared-and distributed-memory parallel algorithms for the stated graph coloring problems.  ...  Introduction Numerical optimization algorithms that rely on derivative information often need to compute the Jacobian or Hessian matrix.  ... 
doi:10.1007/3-540-45706-2_130 fatcat:tfzfj4q3nvgrjj6rihbrgshtoa

BSF: a parallel computation model for scalability estimation of iterative numerical algorithms on cluster computing systems [article]

Leonid B. Sokolinsky
2020 arXiv   pre-print
The paper includes several examples of applying the BSF model to designing and analyzing parallel nu-merical algorithms.  ...  This paper examines a new parallel computation model called bulk synchronous farm (BSF) that focuses on estimating the scalability of compute-intensive iterative algorithms aimed at cluster computing systems  ...  The design of numerical algorithms for such computing clusters requires new approaches to achieve the high efficiency of parallelization.  ... 
arXiv:2008.03485v4 fatcat:gtljbckt5zeohnvppihfoz5r2e

Parallel Algorithm For Numerical Solution Of Three-Dimensional Poisson Equation

Alibek Issakhov
2012 Zenodo  
In this paper developed and realized absolutely new algorithm for solving three-dimensional Poisson equation.  ...  Moreover in the view of rising productivity of difficult calculation there was applied the most up-to-date and the most effective parallel programming technology - MPI in combination with OpenMP direction  ...  Algorithm for Numerical Solution of Three-Dimensional Poisson Equation P World Academy of Science, Engineering and Technology International Journal of Mathematical and Computational Sciences Vol  ... 
doi:10.5281/zenodo.1071213 fatcat:scfs5bnfhva5fghmlidyj6n6ry

Numerical Reproducibility and Parallel Computations: Issues for Interval Algorithms

Nathalie Revol, Philippe Theveny
2014 IEEE transactions on computers  
This problem is especially stringent for HPC numerical simulations. In what follows, the focus is on parallel implementations of interval arithmetic using floating-point arithmetic.  ...  For interval computations, numerical reproducibility is of course an issue for testing and debugging purposes.  ...  The difficulty with this definition is to devise an algorithm that is efficient on parallel platforms and that computes the correct rounding of the exact result.  ... 
doi:10.1109/tc.2014.2322593 fatcat:jxuzqkwh7zexzpgf5gxdtmv2d4

Parallel reactive molecular dynamics: Numerical methods and algorithmic techniques

H.M. Aktulga, J.C. Fogarty, S.A. Pandit, A.Y. Grama
2012 Parallel Computing  
Parallel formulations of these methods have been shown to be among the most scalable scientific computing applications. Many instances of  ...  Acknowledgment The authors would like to thank Adri van Duin for significant help through all aspects of software development, Aidan Thompson and Steve Plimpton for various discussions on parallel ReaxFF  ...  Algorithmic and Numerical Techniques PuReMD features several algorithmic and numerical techniques to achieve excellent per-timestep execution time.  ... 
doi:10.1016/j.parco.2011.08.005 fatcat:z6rvynvrbra7dmqtn3w52wcnoa

A scalable multiphysics algorithm for massively parallel direct numerical simulations of electrophoretic motion

Dominik Bartuschat, Ulrich Rüde
2018 Journal of Computational Science  
In this article we introduce a novel coupled algorithm for massively parallel direct numerical simulations of electrophoresis in microfluidic flows.  ...  This multiphysics algorithm employs an Eulerian description of fluid and ions, combined with a Lagrangian representation of moving charged particles.  ...  To this end, we present a parallel multiphysics algorithm for direct numerical simulations of electrophoretic particle motion.  ... 
doi:10.1016/j.jocs.2018.05.011 fatcat:5bc3jsue3fdydmvntil2aysxha
« Previous Showing results 1 — 15 out of 648,801 results