Search Results for "parallel computing"

This software computes Gauss-Legendre quadrature nodes and weights using the formulas developed in "Iteration-Free Computation of Gauss-Legendre Quadrature Nodes and Weights", I. Bogaert, published in the SIAM Journal of Scientific Computing (Permalink: http://dx.doi.org/10.1137/140954969). The key features are: - Speed: due to the simplified formulas and the O(1) complexity computation of individual Gauss-Legendre quadrature nodes and weights. The latter also makes this software perfectly compatible with parallel computing paradigms. - Accuracy: the error on the nodes and weights is smaller than a few ulps (see the paper for details).

SimKernel controls parameter scans and iterations for any given C++ code / scientific simulation. Parameters, iteration ranges, settings and dependencies are specified in Mathematica syntax. Parallel processing of parameter scanning via MPI.

CPPScaLapack is a C++ class wrapper for PBLAS and ScaLAPACK with MPI. CPPScaLapack provides a user-friendly interface of high-speed parallel matrix calculation with BLAS and LAPACK techonologies for programers concerning with large-scale computing.

In many parallel scientific applications the process of grid generation, decomposition, message passing, and performance measurements are of similar stucture. The projects intention is to develop a generic function library that will contain all these.

PPAT, or Parallel Path following Algorithm using Triangles, is a reliable parallel tool to trace the level curves of any continuous, not necessarily smooth, function f(z): C → R.