A GPU implementation for improved granular simulations with LAMMPS

EMMANUEL N. MILLÁN; CHRISTIAN RINGL; CARLOS S. BEDERIÁN; MARÍA FABIANA PICCOLI; CARLOS GARCÍA GARINO; HERBERT M. URBASSEK; EDUARDO M. BRINGA

Mendoza

Simposio; IV Latin American Symposium on High Performance Computing; 2013

Granular mechanics plays an important role in many branches of science and engineering, from astrophysics applications in planetary and interstellar dust clouds, to processing of industrial mixtures and pow- ders. In this context, a granular simulation model with improved adhe- sion and friction, is implemented within the open source code LAMMPS (lammps.sandia.gov). The performance of this model is tested in both CPU and GPU (Graphics Processing Unit) clusters, comparing with performance for the LAMMPS implementation of another often used interaction model, the Lennard-Jones potential. Timing shows accelera- tions of ∼4-10x for GPUs versus CPUs, with good parallel scaling in a hybrid GPU-CPU cluster.