git: switch default branch from 'master' to 'main'
Convert MPI error type to PETSc error with string message for all MPI callsNow PETSc examples will ONLY return PETSc error codes and never MPI error codes directly so we can understand and post-pro
Convert MPI error type to PETSc error with string message for all MPI callsNow PETSc examples will ONLY return PETSc error codes and never MPI error codes directly so we can understand and post-process their errors better.The test harness will now automatically retry tests that fail with MPI, this may help with Intel MPI that produces seemingly random failures.Commit-type: error-checking/spend 30m
show more ...
checkbadSource: apply rules to *.cu *.cpp sources, and expand CHKERRQ check to CHKERR(Q|MPI|CUDA|CUBLAS|CUSPARSE)
Docs: Fix broken linksFix broken links and other formatting errors expose by"make linkcheck" in the Sphinx docs root.This includes updating links in the .rst files, adding missing examples to EX
Docs: Fix broken linksFix broken links and other formatting errors expose by"make linkcheck" in the Sphinx docs root.This includes updating links in the .rst files, adding missing examples to EXAMPLESCsections in makefiles, and fixing entries in BibTeX files.
Single petscdir.mk
Provide support for not setting PETSC_DIR when gnumake is being used; this will prevent some petsc-maint/petsc-users email threadsCommit-type: error-checking, testing-fix, feature, exampleThanks-t
Provide support for not setting PETSC_DIR when gnumake is being used; this will prevent some petsc-maint/petsc-users email threadsCommit-type: error-checking, testing-fix, feature, exampleThanks-to: Jed Brown <jed@jedbrown.org>Thanks-to: Lisandro Dalcin <dalcinl@gmail.com>
Promote examples/{tests,tutorials}/ to {tests,tutorials}/This shortens paths and improves consistency between test target namesand paths to the source and output files. Most of the work wascompl
Promote examples/{tests,tutorials}/ to {tests,tutorials}/This shortens paths and improves consistency between test target namesand paths to the source and output files. Most of the work wascompleted by this script, followed by mild cleanup of nonconformingcases.for makefile in `git ls-files 'src/*makefile'`; do if rg -q 'DIRS.*\bexamples\b' $makefile; then base=$(dirname $makefile) dirs=$(cd $base/examples && ls -d tests tutorials 2>/dev/null | xargs echo) perl -pi -e "s#^(DIRS.*)\bexamples\b#\1${dirs}#" $makefile git rm $base/examples/makefile for t in $dirs; do git mv $base/examples/$t $base/ perl -pi -e "s#^(LOCDIR[[:space:]]*=).*#\1 $base/$t/#" $base/$t done fidonegit grep -l -E -z 'examples/(tutorials|tests)' | xargs -0 perl -pi -e 's#examples/(tutorials|tests)#\1#g'git checkout @ \ src/docs/website/documentation/changes/ \ src/benchmarks/results/
added CUDA option for STREAMS
Improve streams benchmark usage, now both MPI and OpenMP produce similar output and both can use process.pyAdded make rules openmpstreams, openmpstreams and changed streams and stream to mpistreams
Improve streams benchmark usage, now both MPI and OpenMP produce similar output and both can use process.pyAdded make rules openmpstreams, openmpstreams and changed streams and stream to mpistreams and mpistreamCommit-type: feature, benchmarking
Benchmark: Add the --plotOnly flag
Added PetscOptionsBoundInt(), error if value below bound, and PetscOptionsRangeInt(), error if out of rangeReplaced a small amount of the usage in the source code. Easy, slightly boring process to
Added PetscOptionsBoundInt(), error if value below bound, and PetscOptionsRangeInt(), error if out of rangeReplaced a small amount of the usage in the source code. Easy, slightly boring process to replace the restCommit-type: error checking
Merge remote-tracking branch 'origin/barry/add-petscarrayxxx-ops' [PR #1771]
Merged in barry/rm-cmake-legacy (pull request #1714)Remove legacy and cmake compile systemsApproved-by: BarryFSmith <bsmith@mcs.anl.gov>
Add PetscArraycmp(), PetscArraycpy(), PetscArrayzero(), PetscArraymove(), update code to use new formsReplace a couple multi-mallocs with a single mallocReplace backwards loops in MatSetValues_*()
Add PetscArraycmp(), PetscArraycpy(), PetscArrayzero(), PetscArraymove(), update code to use new formsReplace a couple multi-mallocs with a single mallocReplace backwards loops in MatSetValues_*() with PetscArraymove()Commit-type: style-fix, feature
Benchmark: Rework script to do plots for new logging format- Get rid of some specialized GPU stuff- Now support CSV logging- Some examples for tutorials at bottom
Remove legacy and cmake compile systems- Remove legacy and cmake compile systems from makefiles and config- Clean out various dead code from makefile and lib/petsc/conf/rules- Update lib/petsc/co
Remove legacy and cmake compile systems- Remove legacy and cmake compile systems from makefiles and config- Clean out various dead code from makefile and lib/petsc/conf/rules- Update lib/petsc/conf/test to build all examples, not just those beginning with ex, update examples makefiles to remove now unneeded rules- Deprecated make gnumake, replaced with make libsNote: retained clean-legacy since it is used by clean in rulesCommit-type: style-fix, featureThanks-to: Jed Brown <jed@jedbrown.org> and Satish Balay <balay@mcs.anl.gov>
Fixed out-dated URLS using make checkbadURLS REPLACE=1One manual fix of https://en.wikipedia.org/wiki/Buckingham_π_theorem since the automatic tool dropped the first _ for some reasonManual fix of
Fixed out-dated URLS using make checkbadURLS REPLACE=1One manual fix of https://en.wikipedia.org/wiki/Buckingham_π_theorem since the automatic tool dropped the first _ for some reasonManual fix of //faq.html since the automatic tool incorrectly replaced /faq.html to //faq.html in some locationsThese are largely updates of http to https but have a variety of other website location changesOnce this branch is in master individual developers can run make checkbadURLS and fix URLs related to their projects manuallyCommit-type: bug-fix, documentation
config: eschew dict.iteritems() for dict.items()Fast enough in Python-2 and the only way in Python-3.
Include <petsc/mpiuni/mpi.h> instead of requiring extra -I on command-lineThis makes a PETSc --with-mpi=0 behave more predictably for people whodo not want to know about MPI.
python: futurize stage 1 (modernize python-2 code)This should have no behavioral change. It was generated by running futurize -1 -nw config lib setup.py src systemsfollowed by reverting some
python: futurize stage 1 (modernize python-2 code)This should have no behavioral change. It was generated by running futurize -1 -nw config lib setup.py src systemsfollowed by reverting some "from . import" relative imports (PEP 328without 366) and fixing up RDict.py __contains__ to not cause recursion.
dashboard: date -R is not portable :( [ aka 10.11.6 petsc-mini]. So explicitly specify format
dashboard: use consistant date format across builds. i.e rfc-email/RFC-5322
Complete benchark example with display of logging communication time for VecScatterDocumented binding options for Intel mpirunFunded-by: P-ECPTime: 4
Add PetscProccessManagementView() and -process_view to use hwloc to display location of PETSc MPI processes on coresThis is to allow users and developers to know if the correct binding and mapping o
Add PetscProccessManagementView() and -process_view to use hwloc to display location of PETSc MPI processes on coresThis is to allow users and developers to know if the correct binding and mapping of processes to coreson multicore systems is done as expected. Without this benchmarking to develop optimized code is not possibleAllow -process_view to be used with streams, determined optimal binding for streams on Intel 4 numa thing systemFunded-by: P-ECPTime: 4
Scripts: Moved the location of examples we run and added a build phase
12345678910>>...16