1. 06 Feb, 2019 2 commits
  2. 21 Jan, 2019 1 commit
  3. 27 Sep, 2018 1 commit
    • Mark OLESEN's avatar
      STYLE: add nBoundaryFaces() method to primitiveMesh · 0d94a97f
      Mark OLESEN authored
      - nBoundaryFaces() is often used and is identical to
        (nFaces() - nInternalFaces()).
      - forward the mesh nInternalFaces() and nBoundaryFaces() to
        polyBoundaryMesh as nFaces() and start() respectively,
        for use when operating on a polyBoundaryMesh.
      - use identity() function with starting offset when creating boundary maps.
           labelList map
               identity(mesh.nBoundaryFaces(), mesh.nInternalFaces())
           labelList map(mesh.nBoundaryFaces());
           forAll(map, i)
               map[i] = mesh.nInternalFaces() + i;
  4. 30 Apr, 2018 1 commit
  5. 27 Apr, 2018 1 commit
    • Mark OLESEN's avatar
      ENH: revert regionSplit to older algorithm (issue #805) · 413a6618
      Mark OLESEN authored
      - the algorithm was last used in OpenFOAM-2.4, after which it was
        replaced with a FaceCellWave version.
        Whereas the original (2.4.x) version exhibited performance
        degradation on very large meshes (with explicit constraints), the
        FaceCellWave version exhibited performance issues with large numbers
        of blocked faces.
        With large numbers of blocked faces, the FaceCellWave regionSplit
        could take between 10 to 100 times longer due to the slow
        propagation speed through blocked faces.
        The 2.4 regionSplit has been revamped to avoid local memory
        allocations, which appears to have been the source of the original
        performance issues on large meshes.
        For additional performance, intermediate renumbering is also avoided
        during the consolidation of regions over processor domains.
  6. 24 Apr, 2018 1 commit
    • Mark OLESEN's avatar
      ENH: new bitSet class and improved PackedList class (closes #751) · 430d0f62
      Mark OLESEN authored
      - The bitSet class replaces the old PackedBoolList class.
        The redesign provides better block-wise access and reduced method
        calls. This helps both in cases where the bitSet may be relatively
        sparse, and in cases where advantage of contiguous operations can be
        made. This makes it easier to work with a bitSet as top-level object.
        In addition to the previously available count() method to determine
        if a bitSet is being used, now have simpler queries:
          - all()  - true if all bits in the addressable range are empty
          - any()  - true if any bits are set at all.
          - none() - true if no bits are set.
        These are faster than count() and allow early termination.
        The new test() method tests the value of a single bit position and
        returns a bool without any ambiguity caused by the return type
        (like the get() method), nor the const/non-const access (like
        operator[] has). The name corresponds to what std::bitset uses.
        The new find_first(), find_last(), find_next() methods provide a faster
        means of searching for bits that are set.
        This can be especially useful when using a bitSet to control an
        OLD (with macro):
            forAll(selected, celli)
                if (selected[celli])
                    sumVol += mesh_.cellVolumes()[celli];
        NEW (with const_iterator):
            for (const label celli : selected)
                sumVol += mesh_.cellVolumes()[celli];
            or manually
                label celli = selected.find_first();
                celli != -1;
                celli = selected.find_next()
                sumVol += mesh_.cellVolumes()[celli];
      - When marking up contiguous parts of a bitset, an interval can be
        represented more efficiently as a labelRange of start/size.
        For example,
            if (isA<processorPolyPatch>(pp))
                forAll(pp, i)
            if (isA<processorPolyPatch>(pp))
  7. 19 Apr, 2018 1 commit
  8. 14 Mar, 2018 1 commit
  9. 07 Mar, 2018 1 commit
  10. 22 Feb, 2018 1 commit
  11. 17 Jul, 2017 1 commit
  12. 22 Jul, 2016 1 commit
  13. 25 Apr, 2016 4 commits
  14. 02 Apr, 2016 1 commit
    • Henry Weller's avatar
      Pstream: optimisation of data exchange · 56668b24
      Henry Weller authored
      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
         - 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
         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.
  15. 04 Jan, 2016 1 commit
  16. 08 Dec, 2015 1 commit
  17. 26 Nov, 2015 1 commit
    • mattijs's avatar
      ENH: regionSplit: improve algorithm order · ffddf4e5
      mattijs authored
      The old version of regionSplit would hand out regions one by one. This
      is a big problem when there are lots of regions - the extreme being
      in the decompositionMethods, where it is used to cluster cells and most clusters
      being only one cell. This rewrite uses a mesh wave to determine disconnected
      regions in one go. This produced non-compact numbering which is then compacted
      in a second phase.
      On a 14M cell case with cyclic constraints this reduced decompose
      time from 40 mins down to 5.
  18. 11 Nov, 2015 1 commit
  19. 10 Dec, 2014 1 commit