Optimization of Multi-Phase Compressible Lattice Boltzmann Codes on Massively Parallel Multi-Core Systems

AbstractWe 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