Search

The main computing phases of numerical methods for solving partial differential equations are the algebraic system assembly and the iterative solver. This work focuses on the first task, in the context of a hybrid MPI+X paradigm. The matrix assembly consists of a loop over the elements, faces, edges or nodes of the MPI partitions to compute element matrices and vectors and then of their assemblies. In a MPI+X hybrid parallelism context, X has consisted traditionally of loop parallelism using OpenMP, with different techniques to avoid the race condition, but presenting efficiency or implementation drawbacks. We propose an alternative, based on task parallelism using some extensions to the OpenMP programming model. In addition, dynamic load balance will be applied, especially efficient in the presence of hybrid meshes. This paper presents the proposed methodology, its implementation and its validation through the solution of large computational mechanics problems up to 16k cores. [ABSTRACT FROM AUTHOR]

This work presents a parallel numerical strategy to transport Lagrangian particles in a fluid using a dynamic load balance strategy. Both fluid and particle solvers are parallel, with two levels of parallelism. The first level is based on a substructuring technique and uses message passing interface (MPI) as the communication library; the second level consists of OpenMP pragmas for loop parallelisation at the node level. When dealing with transient flows, there exist two main alternatives to address the coupling of these solvers. On the one hand, a single-code approach consists in solving the particle equations once the fluid solution has been obtained at the end of a time step, using the same instance of the same code. On the other hand, a multi-code approach enables one to overlap the transport of the particles with the next time-step solution of the fluid equations, and thus obtain asynchronism. In this case, different codes or two instances of the same code can be used. Both approaches will be presented. In addition, a dynamic load balancing library is used on the top of OpenMP pragmas in order to continuously exploit all the resources available at the node level, thus increasing the load balance and the efficiency of the parallelisation and uses the MPI. [ABSTRACT FROM AUTHOR]

Numerous tsunami numerical models have been proposed, but their prediction accuracies have not been directly compared. For quantifying the modeling uncertainties, the authors statistically analyzed the prediction results submitted by participants in the tsunami blind contest held at the 17th World Conference on Earthquake Engineering. The reproducibility of offshore water level generated due to the tsunami with soliton fission significantly decreased when the nonlinear shallow water equation models (NSWE) was used compared to three-dimensional (3D) models. The inundation depth was reproduced well in 3D models. However, the reproducibility of wave forces acting on the structure and velocities over land was lower in 3D models than that in NSWE models. For cases where the impulsive tsunami wave pressure generated could not be calculated based on the hydrostatic assumption, the prediction accuracy of the NSWE models was higher than that of the 3D models. The prediction accuracies of both models were not improved at small grid-cell sizes. The NSWE model cannot simulate the short-wave component and vertical pressure distribution. Therefore, further developments in 3D models and smoothed particle hydrodynamics methods (SPH) are needed. The presented results contribute to the future development of tsunami numerical simulation tools. [ABSTRACT FROM AUTHOR]

For complex engineering and scientific applications, Computational Fluid Dynamics (CFD) simulations require a huge amount of computational power. As such, it is of paramount importance to carefully assess the performance of CFD codes and to study them in depth for enabling optimisation and portability. In this paper, we study three complex CFD codes, OpenFOAM, Alya and CHORUS representing two numerical methods, namely the finite volume and finite-element methods, on both structured and unstructured meshes. To all codes, we apply a generic performance analysis method based on a set of metrics helping the code developer in spotting the critical points that can potentially limit the scalability of a parallel application. We show the root cause of the performance bottlenecks studying the three applications on the MareNostrum4 supercomputer. We conclude providing hints for improving the performance and the scalability of each application. [ABSTRACT FROM AUTHOR]