Abstract

This work investigates the accuracy and performance of a FE2 multi-scale implementation used to predict the behavior of composite materials. The equations are formulated assuming the small deformations solid mechanics approach in non-linear material models with hardening plasticity. The uniform strain boundary conditions are applied for the macro-to-micro transitions. A parallel algorithm was implemented in order to solve large engineering problems. The scheme proposed takes advantage of the domain decomposition method at the macro-scale and the coupling between each subdomain with a micro-scale model. The precision of the method is validated with a composite material problem and scalability tests are performed for showing the efficiency.

Abstract

Abstract

The numerical simulation of modern engineering problems via finite elements requires the solution of sparse linear systems of millions or even billions of unknowns. The algebraic multigrid (AMG) methods are the most common choice as linear solvers because of their fast convergence even for large-size problems. In this communication, we propose Chronos, a massively parallel implementation of a novel AMG framework, specifically designed to address complex problems by adapting its components, from the smoother, to the coarse grid correction and prolongation to the problem at hand. This work demonstrates not only the numerical performance of the proposed library, but also its robustness and adaptability to very challenging matrices, arising from different fields of application.

Abstract

Simulating coupled problems using a multiphysics framework is different from the classical approach using dedicated coupling tools. It can have several advantages such as reduced memory footprint or more efficient communication between the involved solvers. The realization of coupled simulations with a multiphysics framework is presented together with important details of the software design such as data management, data communication, mapping, and distributed computing. Several examples from different physical disciplines with coupling internal and external solvers are shown.

Abstract

Applications to solve large and complex partial derivative equation systems often rely nowadays on frameworks like Arcane, Dune, Feel++. Linear solver packages like PETSc or Trilinos are used to manage linear systems and provide access to a wide range of algorithms. With the evolution of High-Performance Computing, the variety of the hardware features available in new architectures has considerably increased. ARM processors, AMD, Intel and Nvidia GP-GPUs, TPU and FPGA devices are now common. To handle the induced complexity, different strategies are adopted in each linear solver framework. One of them consists in introducing a new layer that provides abstractions to manage the performance portability and to enable several parallel programming models. In this paper, we evaluate the performance of linear solver packages that rely on tools like SYCL [16], Kokkos [8] or HARTS [11] to handle runtime systems like OpenMP, TBB, CUDA,. . . . A simulator to solve advection-diffusion problems has been developed with ALIEN, a C++ framework that provides a high level and unified API to handle large distributed matrices and vectors. We have benchmarked different solver algorithms, and have evaluated the efficiency of their implementations, and their capability to perform on different architectures, for instance, large number of cores, GP-GPU accelerators, or processors with large SIMD instructions.

Abstract

Particle-In-Cell (PIC) methods such as the Material Point Method (MPM) can be cast in formulations suitable to the requirements of data locality and fine-grained parallelism of modern hardware accelerators such as Graphics Processing Units (GPUs). While continuum mechanics simulations have already shown the capabilities of MPM on a wide range of phenomena, the use of the method in compressible gas dynamics is less frequent. This contribution aims to show the potential of a GPU-based MPM parallel implementation for compressible fluid dynamics, as well as to assess the reliability of this approach in reproducing supersonic gas flows against solid obstacles. The results in the paper represent a stepping stone towards a highly parallel, Multi-GPU, MPM-base solver for M ach > 1 Fluid-Structure Interaction problems.