v2406: New and improved parallel operation

GAMG : fix processorAgglomeration

TOP

In addition to local agglomeration, the GAMG solver supports combining matrices across processors using processor agglomeration. This has been shown to be particularly effective at larger core counts due to:

  • lowering the number of cores acting on the coarsest level---where most of the global reductions happen.
  • increasing the amount of implicitness for all operations, e.g. smoothing and preconditioning.

In the previous release (v2312) the mechanism was rewritten to allow any kind of coupled boundary condition to be included. However, this broke the existing, processor-boundary-only, processor agglomeration. This has been fixed in this release.

The following image shows the performance benefit for an external aerodynamics investigation:

Source code

Tutorial

Gitlab

cyclicAMI : fix cyclicAMI in linear solver on large core counts

TOP