The HECToR Service is now closed and has been superceded by ARCHER.

CASTEP

This Distributed Computational Science and Engineering (dCSE) project was to improve the scaling of the density functional theory code Castep for more than 1000 cores.

  • Parallel efficiency for Castep now stands at around 42% for 1024 cores. This is nearly four times better than the original Castep 4.2.
The following improvements were successfully implemented :
  • Storage and workload of the dominant parts of a Castep calculation were split using basic band parallelism in addition to the existing parallelisation scheme.
  • Matrix Inversion and Diagonalisation was parallelised instead of being performed serially.
  • The original band optimiser required frequent, expensive orthonormalisation steps, so this was replaced with a Band-Independent Optimiser.
The parallel performance of Castep has been dramatically improved by this work.
  • The original parallel efficiency of Castep 4.2 reduced from 86% for 64 cores to around 12% for 1024 cores.

Please see PDF or HTML for a report which summarises this project. More detailed versions of the report are also available: PDF, HTML. There is still scope for further optimisation leading on from this work and this could be implemented in a future dCSE project.