OhHelp

Abstract

This paper proposes a new method for Particle-in-Cell (PIC) simulations which aims at achieving both good load balancing and scalability so as to be efficiently executed on distributed memory systems. This method, named OhHelp, simply and equally partitions the space domain where charged particles reside and assigns each partitioned subdomain to each computation node for scalable simulation with respect to the size of the domain. Load balancing and thus the scalability in terms of the number of particles are accomplished by making each node help another heavily loaded node which deputes a part of particles in its subdomain and replicated subdomain field data to its helpers. The OhHelp load balancer monitors particle movements through subdomain boundaries to check if the helpand-helpers configuration keeps good load balancing and, when unacceptable imbalance is found, dynamically reconfigures it to regain perfect balancing. The efficiency and scalability of OhHelp are confirmed through our experiment with a production-level full-3D plasma simulator and with uniform and non-uniform particle distributions. As a result, we found 256-core parallel simulations, including an extremely imbalanced setting to pack all the particles in a small region, exert 159-190 speedup compared to sequential execution. * Currently with ACCMS, Kyoto U. † Currently with Grad. School of Engineering, Kobe U.

Effects of the guard electrode on the photoelectron distribution around an electric field sensor

“…Further improvement of the sensor structure modeling is required in the self-consistent PIC simulation for the quantitative evaluation of the electric coupling among multiple conducting elements due to photoelectron currents. Such a quantitative evaluation should be tackled by applying more sophisticated numerical algorithms and largerscale supercomputing techniques, such as a local mesh refinement algorithm and a load-balancing technique for a massively parallel computation [e.g., Nakashima et al, 2009], respectively. We can also use some quasi-analytical models for describing local field variation around the extremely small sensor structure.…”

Unconventional Surface Charging Within Deep Cavities on Airless Planetary Bodies: Particle‐In‐Cell Plasma Simulations

“…The computational kernel of EMSES is parallelized with the Message Passing Interface (MPI) based on the block domain decomposition. To avoid possible computational efficiency degradation, EMSES adopts a dynamic load‐balancing algorithm referred to as OhHelp (Nakashima et al., 2009). With the OhHelp algorithm, a simulation space is divided into as many subdomains as the number of MPI processes, but up to two decomposed subdomains are assigned to each process.…”

Unconventional Surface Charging within Deep Cavities on Airless Planetary Bodies: Particle-in-Cell Plasma Simulations

“…The computational kernel of EMSES is parallelized with the Message Passing Interface (MPI) based on the block domain decomposition. To avoid possible computational efficiency degradation, EMSES adopts a dynamic load-balancing algorithm referred to as OhHelp (Nakashima et al, 2009). With the OhHelp algorithm, a simulation space is divided into as many subdomains as the number of MPI processes, but up to two decomposed subdomains are assigned to each process.…”