Non-numeric optimizations focused on AIJ, MatFDColoring, and DMCreateMatrix_DA_*AIJ, looking to improve performance in GPU environments1) PetscCalloc*() now uses system calloc()2) Merged some Pets
Non-numeric optimizations focused on AIJ, MatFDColoring, and DMCreateMatrix_DA_*AIJ, looking to improve performance in GPU environments1) PetscCalloc*() now uses system calloc()2) Merged some PetscMalloc*()3) Eliminated unneeded PetscCalloc*()4) Removed some memory allocations and copies in MatFDColoringSetUp(), added local variables for better compiler optimization5) Added MatSetValues_SeqAIJ_SortedFull(), added MatSetOption(MAT_SORTED_FULL)6) Optimized DMCreateMatrix_DA_*AIJ for nonperiodic case to automatically have sorted columns (faster MatSetValues() times)7) Eliminated call to PetscMemzero() in PetscFree()Commit-type: style-fix, feature
show more ...
Update the use of Collective on in the manual pages to reflect the new styleCommit-type: style-fix, documentationThanks-to: Patrick Sanan <patrick.sanan@gmail.com>
Man pages: remove .keywords: fieldsThis field is recognized by doctext from Sowing (http://wgropp.cs.illinois.edu/projects/software/sowing/doctext/node20.htm#Node20),but it doesn't seem to be unif
Man pages: remove .keywords: fieldsThis field is recognized by doctext from Sowing (http://wgropp.cs.illinois.edu/projects/software/sowing/doctext/node20.htm#Node20),but it doesn't seem to be uniformly used or maintained.Thus, remove all .keywords: fields, and a following blank line, if present.This is accomplished with GNU sed (gsed on OS X), with the following commands.*Warning* that this type of command can corrupt a .git directory,so be cautious in reusing or modifying these commands. They first lookfor and delete matching lines with a following line consisting of only whitespace,and then delete any remaining matching lines. find src/ -type f -exec gsed -i '/keywords:/ {N; /\n\s*$/d}' {} + find src/ -type f -exec gsed -i '/keywords:/d' {} + find include/ -type f -exec gsed -i '/keywords:/ {N; /\n\s*$/d}' {} + find include/ -type f -exec gsed -i '/keywords:/d' {} +Hints on the sed command obtained from: https://unix.stackexchange.com/questions/100754/how-to-delete-a-specific-line-and-the-following-blank-line-using-gnu-sed
rm MatSetOption(*J,MAT_NEW_NONZERO_ALLOCATION_ERR,PETSC_TRUE) in line 1717 because DMCreateMatrix_Plex() already sets it.
Add error checking MatSetOption(*J,MAT_NEW_NONZERO_ALLOCATION_ERR,PETSC_TRUE) in DMCreateMatrix_Network()Add '-dm_view' runtime option to view dmnetwork edgelistCleanup
small fixes for tests on next
add parallel creation of DMNetwork in DMNetworkLayoutSetUp()change API for DMNetworkSetSizes()add DMNetworkGetSubnetworkCoupleInfo()implement DMView_Network()update DMNetworkGetGlobalXXXIndex()u
add parallel creation of DMNetwork in DMNetworkLayoutSetUp()change API for DMNetworkSetSizes()add DMNetworkGetSubnetworkCoupleInfo()implement DMView_Network()update DMNetworkGetGlobalXXXIndex()update/rewrite pipes1.c
dmnetwork: add xmin, xmax to DMNetworkMonitorAdd()add PETSC_VIEWER_DRAW_LG_XRANGE and update VecView_Seq_Draw_LG()Requested-by: "Betrie, Getnet" <gbetrie@anl.gov>Suggested-by: "Smith, Barry F."
dmnetwork: add xmin, xmax to DMNetworkMonitorAdd()add PETSC_VIEWER_DRAW_LG_XRANGE and update VecView_Seq_Draw_LG()Requested-by: "Betrie, Getnet" <gbetrie@anl.gov>Suggested-by: "Smith, Barry F." <bsmith@mcs.anl.gov>
doc fixes
Merge branch 'barry/clarify-dmplex-documentation' [PR #917]* barry/clarify-dmplex-documentation:Rename DM[GS]etDefault{Global}Section() to DM[GS]et{Global}Section().Add DMPlexComputeGeometryFEM()
Merge branch 'maint'
Fixes for annoying warnings from GNU (-Wmaybe-uninitialized)
Merge remote-tracking branch 'origin/hzhang/update-example-ts-pipes1'
DMPlex and DMNetwork should not need to know about DMDACommit-type: style-fixDevelopment Tools: Vim, Emacs, Eclipse
fixbug for DMNetworkHasJacobian() when nVertices=0;add cases of using user Jacobian elements to src/ts/examples/tutorials/network/wash/pipes1.c
Deprecate DMSet/GetDefaultSection() for DMSet/GetSection()Revert manual page change per Matt's preferenceCommit-type: style-fixThanks-to: Matthew Knepley
Fix last commit to properly pass int cell lists to DMPlex from DMNetworkNetwork examples now work with 64 bit indicesCommit-type: bug-fix
Git rid of int argument for edgelist with DMNetwork, replace with PetscIntThe DMNetwork examples now don't work with 64 bit indices probably due to some place inDMPlex that uses int instead of Pet
Git rid of int argument for edgelist with DMNetwork, replace with PetscIntThe DMNetwork examples now don't work with 64 bit indices probably due to some place inDMPlex that uses int instead of PetscInt. But this means that DMPlex needs to be fixed tonot have this one crazy location with int instead of PetscInt.Commit-type: style-fix, feature
fix warnings reported from regression tests
rm old DMNetworkLayoutSetUp()
change API of DMNetworkSetEdgeList() to DMNetworkSetEdgeList(DM dm,int *edgelist[],int *edgelistCouple[])
replace DMNetworkSetSizes() with DMNetworkSetSizesCoupled()
cleanup
implement DMNetworkSetSizesCoupled()
access coupling vertices
12345678910>>...13