Space-charge-dominated beam dynamics simulations using the massively parallel processors (MPPs) of the Cray T3D

Abstract

Computer simulations using the multi-particle code PARMELA with a three-dimensional point-by-point space charge algorithm have turned out to be very helpful in supporting injector commissioning and operations at Thomas Jefferson National Accelerator Facility (Jefferson Lab, formerly called CEBAF). However, this algorithm, which defines a typical N{sup 2} problem in CPU time scaling, is very time-consuming when N, the number of macro-particles, is large. Therefore, it is attractive to use massively parallel processors (MPPs) to speed up the simulations. Motivated by this, the authors modified the space charge subroutine for using the MPPs of the Cray T3D. The techniques used to parallelize and optimize the code on the T3D are discussed in this paper. The performance of the code on the T3D is examined in comparison with a Parallel Vector Processing supercomputer of the Cray C90 and an HP 735/15 high-end workstation.

Related Papers

• → Exploiting the Performance of 32 bit Floating Point Arithmetic in Obtaining 64 bit Accuracy (Revisiting Iterative Refinement for Linear Systems)(2006)81 cited
• Exploiting the Performance of 32 bit Floating Point Arithmetic in Obtaining 64 bit Accuracy(2006)
• → Floating Point Arithmetic Unit with Multi-Precision for DSP Applications(2021)4 cited
• → Parallel floating-point expansions for extended-precision GPU computations(2016)2 cited
• → Performance comparison of double, triple and quadruple precision real and complex BLAS subroutines on GPUs(2005)3 cited