Added the stub code for ADIOS VecView() and VecLoad()

Fails link examples due to "missing libadios2_atl.dylib on my Mac. Posted issue on github

Commit-type: feature

Remove unneeded storage of vecname_n with array global dimension when storing Vec with ADIOS viewer

Commit-type: style-fix, feature
Thanks-to: Norbert Podhorszki <pnorbert@ornl.gov>

Able to write and then read a parallel vector with ADIOS viewer

Commit-type: bug-fix
Thanks-to: Norbert Podhorszki <pnorbert@ornl.gov>

IS: Move IS utilities out of SNES

Merge branch 'jczhang/optimize-vecscatter-with-memcpy' [PR #1022]

* jczhang/optimize-vecscatter-with-memcpy:
To improve vecscatter performance, this branch adds optimizations to pack data to the sen

Merge branch 'jczhang/optimize-vecscatter-with-memcpy' [PR #1022]

* jczhang/optimize-vecscatter-with-memcpy:
To improve vecscatter performance, this branch adds optimizations to pack data to the send buffer (and unpack data from the recv buffer) efficiently.
- Optimize pack/unpack in vecscatter with memcpy
- Print memcpy optimization in vescatter viewer
- Add MAX_VALUES to vecscatter memcpy plan
- Optimization when vecscatter is actually a strided copy

show more ...

Fix the memory leak in vecscatter destroy

cannot use CHKERR macros after PetscFinalize()

Do optimization when vecscatter is actually a strided copy

Add MAX_VALUES to vecscatter memcpy plan

Print memcpy optimization in vescatter viewer

Optimize pack/unpack in vecscatter with memcpy

In vecscatter, we pack/unpack vector entries to/from send/recv buffers or shared memory buffers.
Old code used something like y[idy[i]] = x[idx[i]] in

Optimize pack/unpack in vecscatter with memcpy

In vecscatter, we pack/unpack vector entries to/from send/recv buffers or shared memory buffers.
Old code used something like y[idy[i]] = x[idx[i]] in pack/unpack. When indices are clusterred
in a small number of contiguous groups, we could replace these individual operations with
contiguous memory operations like memcpy

show more ...

Merge branch 'master' into knepley/feature-pc-patch

* master: (226 commits)
fix bib
type in bibtex entry
copy edits to bibtex items
Hypre matrix: small fix
Hypre matrix: fixed compiler war

Merge branch 'master' into knepley/feature-pc-patch

* master: (226 commits)
fix bib
type in bibtex entry
copy edits to bibtex items
Hypre matrix: small fix
Hypre matrix: fixed compiler warnings
Plex: Fixed missing PetscRealPart() in partition balance.
Added MatZeroEntries_HYPRE
Removed outdated mention of cusp and thrust from installations instructions; remove cusp from example configurations
Remove another location where fshift was used with -1 to indicate handling of error condition which was never handled
Generate an immediate error, if requested, if CG detects indefinite PC or Mat
Remove hack of using special fshift value of -1 to indicate error handling, was broken for MatSOR_SeqAIJ and did nothing constructive in the other cases
Options: Fix sys_tests-ex6 to not print options
PetscOptionsDestroy: Add missing free() call
Configure: Pragmatic now requires Cxx11
Error check that the communicator in the IS matches that in the matrix otherwise ISAllGather() produces incorrect results.
Options: Code reorganization and faster option lookup
fix compile warning
Doc: Fixed manpage for PCFieldSplitSetSchurPre()
mpiuni: build somempifort.o after mpiuni.mod
Remove use of common block from MPIUNI code
...

Conflicts:
include/petscdm.h
include/petscpc.h
include/petscpctypes.h
src/dm/impls/plex/plexcreate.c
src/dm/impls/plex/plexdistribute.c
src/ksp/pc/impls/makefile
src/ksp/pc/interface/pcregis.c

show more ...

ISColoring: Add support for computing numbering and count through interface

Merge remote-tracking branch 'origin/stefano_zampini/feature-ptatin3d-support'

Merge branch 'master' into denera/lmvm-mat-and-pc

ISLocalToGlobalMapping: add ISLocalToGlobalMapping{Get|Restore}NodeInfo to avoid code duplication

ISView_General: added PETSC_VIEWER_ASCII_INDEX format case

ISInvertPermutation_General: support for PETSC_DECIDE

Merge remote-tracking branch 'origin/maint'

Merge branch 'stefano_zampini/fix-tabs/maint' into maint

DOC: minor fix

IS: use same comm in ISExpandIndicesGeneral ISCompressIndicesGeneral

Array pointer was mistakenly listed as PetscScalar in manual pages

Commit-type: documentation
Thanks-to: Seung-Hoe Ku <in.the.rain@gmail.com>

Merge branch 'master' into knepley/feature-pc-patch

* master: (107 commits)
cast in GAMG_HASH so that it works for PetscInt32 near PETSC_INT_MAX without overflow to negative numbers
Add link for

Merge branch 'master' into knepley/feature-pc-patch

* master: (107 commits)
cast in GAMG_HASH so that it works for PetscInt32 near PETSC_INT_MAX without overflow to negative numbers
Add link for DrMemory which may serve as an alternative to valgrind on Windows
Finish Gail's copyedits for developers manual.
openmpi: fix namespace conflict [with static build on ppc64le]
two pages of Gail's edits to developers guide
Another chapter of Gail's copyedits for the developers guide
Gail's copyedits on two more chapters of the developers guide
Fix more %d to %D in GAMG code. Fix code style in GAMG code
DMPlexVTK: vertices is int! need to use %d instead of %D
TS ex18: update outputs (reported by nightly tests)
Use %D in error messages for GAMG hash; fix style issues with GAMG hash
config: Update petsc4py git commit
Fix bad plain extern declaration.
Add Gail's copyedits for the initial portion of the developers guide
Add missing common block to subroutine
fix mpiuni tests with xl compilers
Copy & paste the change on PetscSparseDensePlusDot
Fix a wrong macro
PetscInfo: Add missing errorchecking
Log: various fixes and cleanups
...

Conflicts:
src/dm/impls/plex/plex.c

show more ...

Vec: update relevant output after running the testuite with DIFF=diff