Results 211 to 220 of about 28,321 (263)
Some of the next articles are maybe not open access.
Prototyping Framework for Parallel Numerical Computations
2014Our research is focused on the simplification of parallel programming for distributed memory systems. Our goal is to build a unifying framework for creating, debugging, profiling, and verifying parallel applications. The result of this effort is an open source tool Kaira. In this paper, we focus on prototyping of parallel applications. We have extended
Ondrej Meca +3 more
openaire +1 more source
Numerically stable parallel computation of (co-)variance
Proceedings of the 30th International Conference on Scientific and Statistical Database Management, 2018With the advent of big data, we see an increasing interest in computing correlations in huge data sets with both many instances and many variables. Essential descriptive statistics such as the variance, standard deviation, covariance, and correlation can suffer from a numerical instability known as "catastrophic cancellation" that can lead to problems ...
Erich Schubert, Michael Gertz 0001
openaire +1 more source
Numerical algorithms for parallel computers
Proceedings of the May 19-22, 1980, national computer conference on - AFIPS '80, 1980Numerical methods are generally judged on their ability to produce a reasonably accurate answer in a reasonable amount of time. This paper deals with the latter criterion in the context of non-standard architectures---namely vector and array processors.
openaire +1 more source
Numerically intensive computing as a benchmark for parallel computer architectures
1995We compare execution time for typical numerical problems, obtained on different parallel architectures, including typical vector supercomputers, multiprocessors and network of computers with PVM environment.
Krzysztof Boryczko +3 more
openaire +1 more source
Numerically-intensive "plug-and-play" parallel computing
Proceedings 2001 IEEE International Conference on Cluster Computing, 2001At UCLA's Plasma Physics Group, we have been successful in building and using a numerically-intensive parallel computing cluster using Power Macintosh hardware and the Macintosh Operating System. Our solution makes the problem of building and operating a parallel computer far easier than using other technologies, allowing the user, without expertise in
Dean E. Dauger, Viktor K. Decyk
openaire +1 more source
On the numerical sensitivity of computer simulations on hybrid and parallel computing systems
2011 International Conference on High Performance Computing & Simulation, 2011Simulation results depend not only on the precision of the floating point arithmetic with respect to the numerical accuracy of the results. They are also sensitive to differences of floating point arithmetic implementations of different hybrid and parallel computing systems such as CPUs, GPUs, dedicated processors like the Cell processor or the GRAPE ...
Wenbin Li 0001 +2 more
openaire +1 more source
The numerical solution of Fredholm integral equations on parallel computers
Parallel Computing, 1989Abstract In this paper algorithmic strategies for the Parallel solution of Fredholm Integral Equations of the first kind are presented. The solution which is obtained by the minimal least squares method uses the singular value decomposition procedure. The parallel computation of the singular value decomposition (SVD) algorithm is derived in 3 phases,
David J. Evans 0001 +1 more
openaire +1 more source
Parallel numerical computations of projectile flow fields
17th Applied Aerodynamics Conference, 1999Abstract : A time-marching, Navier-Stokes code, successfully used over a decade for projectile aerodynamics, was chosen as a test case and optimized to run on modern reduced instruction set computer (RISC)-based parallel computers. The parallelized version of the code has been used to compute the axisymmetric and three-dimensional (3-D) turbulent flow ...
Jubaraj Sahu +3 more
openaire +2 more sources
Numerical Libraries and Tools for Scalable Parallel Cluster Computing
The International Journal of High Performance Computing Applications, 2001For cluster computing to be effective within the scientific community it is essential that there are numerical libraries and programming tools available to application developers. Cluster computing may mean a cluster of heterogeneous components or hybrid architecture with some SMP nodes.
Jack J. Dongarra +2 more
openaire +1 more source
Non-numerical methods on parallel computers
Computer Physics Communications, 1982Abstract Analysis of computation on parallel computers reveals an interleaving of local (often numeric) processing and data re-organisation. The local processing is readily handled since it is contained within individual processors and easily expressed in terms of element-by-element operations on whole arrays.
openaire +1 more source