A Systematic Comparison of Dynamic Load Balancing Algorithms for Massively Parallel Rigid Particle Dynamics

08/02/2018
by   Sebastian Eibl, et al.
0

As compute power increases with time, more involved and larger simulations become possible. However, it gets increasingly difficult to efficiently use the provided computational resources. Especially in particle-based simulations with a spatial domain partitioning large load imbalances can occur due to the simulation being dynamic. Then a static domain partitioning may not be suitable. This can deteriorate the overall runtime of the simulation significantly. Sophisticated load balancing strategies must be designed to alleviate this problem. In this paper we conduct a systematic evaluation of the performance of six different load balancing algorithms. Our tests cover a wide range of simulation sizes, and employ one of the largest supercomputers available. In particular we study the runtime and memory complexity of all components of the simulation carefully. When progressing to extreme scale simulations it is essential to identify bottlenecks and to predict the scaling behaviour. Scaling experiments are shown for up to over one million processes. The performance of each algorithm is analyzed with respect to the quality of the load balancing and its runtime costs. For all tests, the waLBerla multiphysics framework is employed.

READ FULL TEXT
research
11/30/2018

Dynamic Load Balancing Techniques for Particulate Flow Simulations

Parallel multiphysics simulations often suffer from load imbalances orig...
research
07/06/2018

Dynamic Load Balancing for Compressible Multiphase Turbulence

CMT-nek is a new scientific application for performing high fidelity pre...
research
08/03/2020

Hardware locality-aware partitioning and dynamic load-balancing of unstructured meshes for large-scale scientific applications

We present an open-source topology-aware hierarchical unstructured mesh ...
research
07/03/2018

SWIFT: Maintaining weak-scalability with a dynamic range of 10^4 in time-step size to harness extreme adaptivity

Cosmological simulations require the use of a multiple time-stepping sch...
research
05/20/2019

Exploiting Parallelism on Shared Memory in the QED Particle-in-Cell Code PICADOR with Greedy Load Balancing

State-of-the-art numerical simulations of laser plasma by means of the P...
research
07/02/2018

Dynamic load balancing strategies for hierarchical p-FEM solvers

Equation systems resulting from a p-version FEM discretisation typically...
research
05/03/2018

Work Stealing with latency

We study in this paper the impact of communication latency on the classi...

Please sign up or login with your details

Forgot password? Click here to reset