Summary We are concerned with the mapping on high performance hybrid architectures of a parallel software implementing a two level overlapping domain decomposition, that is, along space and time directions, of the four dimensional variational data assimilation model. The reference architecture belongs to the SCoPE (Sistema Cooperativo Per Elaborazioni scientifiche multidisciplinari) data center, located at University of Naples Federico II. We consider the initial boundary problem of the shallow water equation and analyse both strong and weak scaling. Keeping the efficiency always greater than and about in most cases, we experimentally find that the isoefficiency function grows a little more than linearly with respect to the number of processes. Results, obtained by using the parallel computing toolbox of MATLABR2013a, are in agreement with the algorithm's performance prevision based on the scale up factor, confirming the appropriate mapping of the algorithm on the hybrid architecture.

Summary Kalman filter (KF) is one of the most important and common estimation algorithms. We introduce an innovative designing of Kalman filter algorithm based on domain decomposition (we call it DD‐KF). DD‐KF involves decomposition of the whole computational problem, partitioning of the solution and a slight modification of KF algorithm allowing a correction at run‐time of local solutions. The resulted parallel algorithm consists of concurrent copies of KF algorithm, each one requiring the same amount of computations on each subdomain and an exchange of boundary conditions between adjacent subdomains. Main advantage of this approach is that it can be potentially applied in a moderately nonintrusive manner to existing codes for tracking and controlling systems in location, navigation, in computer graphics and in much more state estimation problems. To highlight the capability of DD‐KF of exploiting the computing power provided by future designs of microprocessors based on multi/many‐cores CPU/GPU technologies, we consider DD both at physical core level and at microprocessor level and we discuss scalability of DD‐KF algorithm at coarse and fine grained level. Throughout the present work, we derive and discuss DD‐KF algorithm for solving constrained least square model, which underlies any data sampling and estimation problem.

Summary In this work, we perform the feasibility analysis of a multi‐grained parallel version of the Zielonka Recursive (ZR) algorithm exploiting the coarse‐ and fine‐ grained concurrency. Coarse‐grained parallelism relies on a suitable splitting of the problem, that is, a graph decomposition based on its Strongly Connected Components (SCC) or a splitting of the formula generating the game, while fine‐grained parallelism is introduced inside the Attractor which is the most intensive computational kernel. This configuration is new and addressed for the first time in this article. Innovation goes from the introduction of properly defined metrics for the strong and weak scaling of the algorithm. These metrics conduct to an analysis of the values of these metrics for the fine grained algorithm, we can infer the expected performance of the multi‐grained parallel algorithm running in a distributed and hybrid computing environment. Results confirm that while a fine‐grained parallelism have a clear performance limitation, the performance gain we can expect to get by employing a multilevel parallelism is significant.

Summary We address the development of a modular implementation of the MGRIT (MultiGrid‐In‐Time) algorithm to solve linear and nonlinear systems that arise from the discretization of evolutionary models with a parallel‐in‐time approach in the context of the PETSc (the Portable, Extensible Toolkit for Scientific computing) library. Our aim is to give the opportunity of predicting the performance gain achievable when using the MGRIT approach instead of the Time Stepping integrator (TS). To this end, we analyze the performance parameters of the algorithm that provide a‐priori the best number of processing elements and grid levels to use to address the scaling of MGRIT, regarded as a parallel iterative algorithm proceeding along the time dimension.

Algorithm 662 of the ACM TOMS library is a software package, based on the Weeks method, which is used for calculating function values of the inverse Laplace transform. The software requires transform values at arbitrary points in the complex plane. We developed a software package, called ReLIADiff, which is a modification of Algorithm 662 using transform values at arbitrary points on real axis. ReLIADiff, implemented in C++, relies on TADIFF software package designed for Algorithmic Differentiation. In this article, we present ReLIADiff focusing on its design principles, performance, and use.

Abstract The Block Conjugate Gradient algorithm (Block‐CG) was developed to solve sparse linear systems of equations that have multiple right‐hand sides. We have adapted it for use in heterogeneous, geographically distributed, parallel architectures. Once the main operations of the Block‐CG (Tasks) have been collected into smaller groups (subjobs), each subjob is matched by the middleware MJMS (MPI Jobs Management System) with a suitable resource selected among those which are available. Moreover, within each subjob, concurrency is introduced at two different levels and with two different granularities: the coarse‐grained parallelism to perform independent tasks and the fine‐grained parallelism within the execution of a task. We refer to this algorithm as to multi‐grained distributed implementation of the parallel Block‐CG. We compare the performance of a parallel implementation with the one of the distributed implementation running on a variety of Grid computing environments. The middleware MJMS—developed by some of the authors and built on top of Globus Toolkit and Condor‐G—was used for co‐allocation, synchronization, scheduling and resource selection. Copyright © 2010 John Wiley & Sons, Ltd.

In this paper we are concerned with improvements and enhancements of a medical imaging grid-enabled infrastructure, named MedIGrid, oriented to the transparent use of resource-intensive applications for managing, processing and visualizing biomedical images. We describe an implementation of the MedIGrid PSE in an LCG/gLite environment. We’ll mainly focus on how to exploit the features of the new middleware environment to improve the efficiency and the services reliability of the PSE; further, some comments will be devoted to how to modify, extend and/or improve the underlying numerical components.

Our method is based on the numerical evaluation of the integral which occurs in the Riemann Inversion formula. The trapezoidal rule approximation to this integral reduces to a Fourier series. We analyze the corresponding discretization error and demonstrate how this expression can be used in the development of an automatic routine , one in which the user needs to specify only the required accuracy.

A software package for the numerical inversion of a Laplace Transform function is described. Besides function values of F ( z ) for complex and real z , the user has only to provide the numerical value of the Laplace convergence abscissa σ 0 or, failing this, an upper bound to this quantity, and the accuracy he or she requires in the computed value of the inverse Transform. The method implemented is based on a Fourier series expansion of the inverse transform, and it is especially suitable when such inverse Laplace Transform is sectionally continuous.

The problem of removing or minimizing degradations in a blurred and noisy image is known as image restoration. The computational kernel of many image restoration problems is the solution of the following inverse problem: Hf=g+/spl eta/ where where the n/sup 2/-vectors f and g represent the real and the observed image, respectively. The n/sup 2/ vector /spl eta/ is an additive noise which is usually unknown. The n/sup 2//spl times/ n/sup 2/-matrix H is the point spread function matrix and it represents the blurring process. The inverse problem consists in the computation of an approximation to the original image vector f, from known values of g and H. In such cases the restoration problem typically leads to a discrete ill-posed inverse problem. The classical way to compute a reasonable solution is to regularize the discrete problem. We explore the possible use of the fast wavelet transform-based preconditioners for the efficient solution of image restoration problems.