Author: King, J.R.
Paper Title Page
MOPME035 Current Status of the GPU-Accelerated ELEGANT 454
 
  • I.V. Pogorelov, K.M. Amyx, J.R. King
    Tech-X, Boulder, Colorado, USA
  • M. Borland, R. Soliday
    ANL, Argonne, Illinois, USA
 
  Funding: Work supported by the DOE Office of Science, Office of Basic Energy Sciences grant No. DE-SC0004585, and in part by Tech-X Corporation.
Efficient implementation of general-purpose particle tracking on GPUs can result in significant performance benefits to large-scale tracking simulations. This presentation is an update on the current status of our work on accelerating Argonne National Lab’s particle accelerator simulation code ELEGANT using CUDA-enabled GPU. We summarize the performance of beamline elements ported to GPU, and discuss optimization techniques for some important collective effects kernels, in particular our methods of avoiding costly thread contention. We also present preliminary results of a scaling study of the GPU-accelerated version of the code.
 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2014-MOPME035  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)