GPU-based Polynomial Finite Element Matrix Assembly for Simplex Meshes

Received: 10 November 2019; Accepted: 22 January 2020; Published: 30 January 2020 Abstract: This paper presents a numerical algorithm used together with a Finite-Element

The internal and global overturning failure modes obtained during the physical model tests performed by Sas et al. The cracks did however occur suddenly due to the low fracture

Thus deformation of the top domain is not as computationally expensive as deforming the full domain in a traditional finite element method with similar mesh

So long as graphics architectures continue to provide a low bandwidth connection between arithmetic units and nearby local memories, such algorithms will continue to suffer

For this GPU, a multifunction unit is proposed based on the hybrid number system of floating-point and logarithmic numbers and the matrix, vector, and elementary functions are

meshes generated from the initial Kuhn-subdivided domain through regular simplex bisection, while a diamond-based one encodes only the conforming nested RSB meshes with the same

While most existing commercial and specialised FE systems consider only a single material per element, our system is optimised for simulation of com- plex, multi-layer

We present a closed-form solution to this concept, reformulating the hierarchical optimization problem into the optimization of a non-hierarchical finite element model1. This allows