Highly accelerated simulations of glassy dynamics using GPUs: Caveats on limited floating-point precision

  title={Highly accelerated simulations of glassy dynamics using GPUs: Caveats on limited floating-point precision},
  author={Peter H. Colberg and Felix H{\"o}fling},
  journal={Comput. Phys. Commun.},

Figures and Tables from this paper

Massively parallel Monte Carlo for many-particle simulations on GPUs

Classical molecular dynamics on graphics processing unit architectures

Focusing on published works in the field of classical MD, the chosen implementation methods and algorithmic techniques used for porting to GPU are described, as well as how recent advances of GPU architectures will provide even more optimization possibilities in the future.

Parallel execution of a parameter sweep for molecular dynamics simulations in a hybrid GPU/CPU environment

This work takes advantage of the software LAMMPS (lammps.sandia.gov), which is already prepared to run in a hybrid environment, in order to do an efficient parameter sweep, and presents one example: the collision of two clusters is sampled over a multivariate space to obtain information on the resulting structural properties.

A comparison between parallelization approaches in molecular dynamics simulations on GPUs

It is predicted that, if the current trend of increasing the number of processing cores—as opposed to their computing power—remains, the “edge‐based” approach will gradually become the most efficient choice in an increasing number of cases.

Design and Implementation of Particle Systems for Meshfree Methods with High Performance

GPUSPH, the first implementation of SPH to run completely on GPU, and currently supporting multi-GPU clusters, uniform precision independent of domain size, and multiple SPH formulations.



Accelerating molecular modeling applications with graphics processors

An overview of recent advances in programmable GPUs is presented, with an emphasis on their application to molecular mechanics simulations and the programming techniques required to obtain optimal performance in these cases.

GPU accelerated Monte Carlo simulation of the 2D and 3D Ising model

Harvesting graphics power for MD simulations

An implementation of molecular dynamics simulations on a graphic processing unit (GPU) in the NVIDIA CUDA language and results for two MD algorithms suitable for short-ranged and long-ranged interactions, and a congruential shift random number generator are presented.

General purpose molecular dynamics simulations fully implemented on graphics processing units

Accelerating molecular dynamics simulation using graphics processing unit

CUDA-enabled version of a general purpose molecular dynamics simulation code for GPU, focused on the non-bonded force calculation, is developed and timing results suggest that GPU could be a useful hardware for Molecular dynamics simulation.

ACEMD: Accelerating Biomolecular Dynamics in the Microsecond Time Scale.

This work provides a validation and performance evaluation of the code and runs a microsecond-long trajectory for an all-atom molecular system in explicit TIP3P water on a single workstation computer equipped with just 3 GPUs, believing that microsecond time scale molecular dynamics on cost-effective hardware will have important methodological and scientific implications.

Fast parallel algorithms for short-range molecular dynamics

Comparing the results to the fastest reported vectorized Cray Y-MP and C90 algorithm shows that the current generation of parallel machines is competitive with conventional vector supercomputers even for small problems.