Symplectic multi-particle tracking on GPUs

Abstract

A symplectic multi-particle tracking model is implemented on the Graphic Processing Units (GPUs) using the Compute Unified Device Architecture (CUDA) language. The symplectic tracking model can preserve phase space structure and reduce non-physical effects in long term simulation, which is important for beam property evaluation in particle accelerators. Though this model is computationally expensive, it is very suitable for parallelization and can be accelerated significantly by using GPUs. In this paper, we optimized the implementation of the symplectic tracking model on both single GPU and multiple GPUs. Using a single GPU processor, the code achieves a factor of 2-10 speedup for a range of problem sizes compared with the time on a single state-of-the-art Central Processing Unit (CPU) node with similar power consumption and semiconductor technology. It also shows good scalability on a multi-GPU cluster at Oak Ridge Leadership Computing Facility. In an application to beam dynamics simulation, the GPU implementation helps save more than a factor of two total computing time in comparison to the CPU implementation.

Symplectic particle-in-cell model for space-charge beam dynamics simulation

“…The symplectic gridless particle model has a regular data structure for a perfect work load balance and a small amount of communication associated with the space-charge solver. It scales well on both multiple processor central processing unit computers and multiple graphic processing unit computers [36].…”

Multi-Particle Simulation Techniques

“…The symplectic gridless particle model has regular data structure for perfect work load balance and small amount of communication associated with the space-charge solver. It scales well on both multiple processor Central Processing Unit (CPU) computers and multiple Graphic Processing Unit (GPU) computers [43].…”