Contributed by Mattijs Janssens.
1. Any non-blocking data exchange needs to know in advance the sizes to
receive so it can size the buffer. For "halo" exchanges this is not
a problem since the sizes are known in advance but or all other data
exchanges these sizes need to be exchanged in advance.
This was previously done by having all processors send the sizes of data to
send to the master and send it back such that all processors
- had the same information
- all could work out who was sending what to where and hence what needed to
be received.
This is now changed such that we only send the size to the
destination processor (instead of to all as previously). This means
that
- the list of sizes to send is now of size nProcs v.s. nProcs*nProcs before
- we cut out the route to the master and back by using a native MPI
call
It causes a small change to the API of exchange and PstreamBuffers -
they now return the sizes of the local buffers only (a labelList) and
not the sizes of the buffers on all processors (labelListList)
2. Reversing the order of the way in which the sending is done when
scattering information from the master processor to the other
processors. This is done in a tree like fashion. Each processor has a
set of processors to receive from/ send to. When receiving it will
first receive from the processors with the least amount of
sub-processors (i.e. the ones which return first). When sending it
needs to do the opposite: start sending to the processor with the
most amount of sub-tree since this is the critical path.
Patch contributed by Bruno Santos:
- "etc/config.sh/CGAL":
- Indented the contents of the recently added if block.
- Added comment about using system versions.
- Library paths are now only added if the respective version is not "boost-system" and "cgal-system".
- "src/renumber/Allwmake":
It now relies on the previous file to get the version for
Boost (the same way as in "makeCGAL"). This is so that it will also
build "SloanRenumber" if "boost_version" is set to "boost-system".
- "applications/utilities/mesh/generation/Allwmake":
It now also relies on the script "config.sh/CGAL" to get the
version for CGAL. If "cgal_version" is set to "cgal-system", it
will now also build "foamy*Mesh" utilities and respective
libraries.
Resolves report http://www.openfoam.org/mantisbt/view.php?id=1232
The deprecated non-const tmp functionality is now on the compiler switch
NON_CONST_TMP which can be enabled by adding -DNON_CONST_TMP to EXE_INC
in the Make/options file. However, it is recommended to upgrade all
code to the new safer tmp by using the '.ref()' member function rather
than the non-const '()' dereference operator when non-const access to
the temporary object is required.
Please report any problems on Mantis.
Henry G. Weller
CFD Direct.
Moved file path handling to regIOobject and made it type specific so
now every object can have its own rules. Examples:
- faceZones are now processor local (and don't search up anymore)
- timeStampMaster is now no longer hardcoded inside IOdictionary
(e.g. uniformDimensionedFields support it as well)
- the distributedTriSurfaceMesh is properly processor-local; no need
for fileModificationChecking manipulation.
- shm: have displacementMotionSolver as alternative mesh shrinker
(instead of medialAxis).
- updated iglooWithFridges tutorial to use displacementLaplacian
- selectable interpolation from cells to points in the motion solvers
using the 'interpolation' keyword:
interpolation volPointInterpolation; // default
or
interpolation patchCorrected (lowerWall upperWall);
- wrapped up mesh shrinkers (see above) for use as a displacementMotionSolver
(i.e. the opposite of the displacementMotionSolver mesh shrinker)
1. multi-ray shooting. It now shoots rays in all the 3 coordinate directions
from the cell centre. Before it would shoot just a single ray from the
nearest point on the surface, going through the cell centre.
There is a cost overhead in that now it shoots 6 rays (+-x, +-y, +-z)
instead of just 1.
2. bleeding of refinement. It marks the cells inside a gap and walks out
the gap-size to neighbouring cells (which are just outside the gap). This
should make for a smoother refinement pattern.
Refinement:
-----------
// Optionally avoid patch merging - keeps hexahedral cells
// (to be used with automatic refinement/unrefinement)
//mergePatchFaces off;
// Optional multiple locationsInMesh with corresponding optional cellZone
// (automatically generates faceZones inbetween)
locationsInMesh
(
((-0.09 -0.039 -0.049) bottomAir) // cellZone bottomAir
((-0.09 0.009 -0.049) topAir) // cellZone topAir
);
// Optional faceType and patchType specification for these faceZones
faceZoneControls
{
bottomAir_to_topAir
{
faceType baffle;
}
}
/ Optional checking of 'bleeding' of mesh through a specifying a locations
// outside the mesh
locationsOutsideMesh ((0 0 0)(12.3 101.17 3.98));
// Improved refinement: refine all cells with all (or all but one) sides refined
// Improved refinement: refine all cells with opposing faces with different
// refinement level. These cells can happen on multiply curved surfaces.
// Default on, can be switched off with
//interfaceRefine false;
Snapping
--------
// Optional smoothing of points at refinement interfaces. This will reduce
// the non-orthogonality at refinement interfaces.
//nSmoothInternal $nSmoothPatch;
Layering
--------
// Layers can be added to patches or to any side of a faceZone.
// (Any faceZone internally gets represented as two patches)
// The angle to merge patch faces can be set independently of the
// featureAngle. This is especially useful for large feature angles
// Default is the same as the featureAngle.
//mergePatchFacesAngle 45;
// Optional mesh shrinking type 'displacementMotionSolver'. It uses any
// displacementMotionSolver, e.g. displacementSBRStress
// (default is the medial-axis algorithm, 'displacementMedialAxis')
//meshShrinker displacementMotionSolver;
