We develop a Lattice Boltzmann code for computational fluid-dynamics and optimize it for massively parallel systems based on multi-core processors. Our code describes 2D multi-phase compressible flows. We analyze the performance bottlenecks that we find as we gradually expose a larger fraction of the available parallelism, and derive appropriate solutions. We obtain a sustained performance for this ready-for-physics code that is a large fraction of peak. Our results can be easily applied to most present (or planned) HPC architectures, based on latest generation multi-core Intel processor architectures.
Keywords: Computational fluid-dynamics; Lattice Boltzmann methods; multi-core processors
|Title of host publication||Proceedings of the International Conference on Computational Science (ICCS 2011, Singapore, June 1-3, 2011)|
|Publication status||Published - 2011|
|Name||Procedia Computer Science|