Petascale turbulence simulation using a highly parallel fast multipole method on GPUs

TL;DR

This paper demonstrates petascale turbulence simulations on GPUs using a vortex particle method with a fast multipole method, achieving high performance and large-scale mesh size, surpassing previous vortex method calculations.

Contribution

Introduces a GPU-based vortex particle method with a fast multipole method for petascale turbulence simulation, matching spectral method results and significantly improving parallel efficiency.

Findings

Achieved 1.08 petaflop/s performance on GPU hardware.

Matched kinetic energy spectrum with spectral methods.

Achieved 74% parallel efficiency on 4096 GPUs.

Abstract

This paper reports large-scale direct numerical simulations of homogeneous-isotropic fluid turbulence, achieving sustained performance of 1.08 petaflop/s on gpu hardware using single precision. The simulations use a vortex particle method to solve the Navier-Stokes equations, with a highly parallel fast multipole method (FMM) as numerical engine, and match the current record in mesh size for this application, a cube of 4096^3 computational points solved with a spectral method. The standard numerical approach used in this field is the pseudo-spectral method, relying on the FFT algorithm as numerical engine. The particle-based simulations presented in this paper quantitatively match the kinetic energy spectrum obtained with a pseudo-spectral method, using a trusted code. In terms of parallel performance, weak scaling results show the fmm-based vortex method achieving 74% parallel efficiency on 4096 processes (one gpu per mpi process, 3 gpus per node of the TSUBAME-2.0 system). The FFT-based spectral method is able to achieve just 14% parallel efficiency on the same number of mpi processes (using only cpu cores), due to the all-to-all communication pattern of the FFT algorithm. The calculation time for one time step was 108 seconds for the vortex method and 154 seconds for the spectral method, under these conditions. Computing with 69 billion particles, this work exceeds by an order of magnitude the largest vortex method calculations to date.