Acceleration of Crack Growth Prediction in Metamaterials by Distributed Multi-XPU Computing

• ETH Zurich
• Mechanics and Materials

Predicting the failure mechanisms of low-density cellular solids, from random fiber networks to periodic architected materials (or metamaterials), remains a challenge for computational mechanics. One fundamental distinction between beam-based architected materials and classical homogeneous solids lies in the nature of their failure. Unlike classical materials, beam-based architected materials fail through the discrete breaking of individual beams. This results in complex patterns of crack initiation and propagation, that are significantly different from those observed in classical materials. As computational models for large-scale, manufacturable metamaterials often involve millions or even billions of unknowns, we are developing an open-source C++ library for scalable finite element simulations. Currently, this library leverages distributed computing on CPUs via Open MPI, utilizing ETH Zurich’s Euler cluster. The goal of this project is to improve simulation performance for predicting failure in large-scale beam networks. A key focus will be integrating Nvidia’s GPU accelerators to achieve significantly enhanced computational efficiency beyond what distributed CPU computing alone can provide. Throughout this project, the student will contribute to an open-source project, conduct in-depth performance studies, and utilize the developed software to predict fracture behavior in novel materials with different (multi-)material properties, including both linear elastic and plastic regimes.

• Mechanical Engineering, Numerical Analysis
• ETH Zurich (ETHZ), Master Thesis, Semester Project