| #
3c124016
|
| 24-May-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'barry/2021-04-12/support-for-nvhpc' into 'main'
These are fixes needed for clean builds with NVIDIA's HPC software toolkit
See merge request petsc/petsc!3882
|
| #
5162e2cf
|
| 24-May-2021 |
Barry Smith <bsmith@mcs.anl.gov> |
Various fixes for NVIDIA's nvhpc toolkit
The nvhpc systems separates the CUDA math libaries and includes from the regular CUDA material
thus cuda.py has to detect and manage this separation automati
Various fixes for NVIDIA's nvhpc toolkit
The nvhpc systems separates the CUDA math libaries and includes from the regular CUDA material
thus cuda.py has to detect and manage this separation automatically.
Note also the nvhpc includes the MPI compilers in another directory which should be used with MPI.
Do not use outer C++ compiler as Kokkos compiler as that may not match the compiler used by nvcc, instead use the C++ compiler that nvcc uses. This is tricky because this compiler has to have access to the MPI headers since it sees all of the PETSc headers.
/spend 14h
show more ...
|
| #
c5d9febf
|
| 07-May-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/release'
|
| #
8f858f2b
|
| 06-May-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'jed/testing-ergonomics/release' into 'release'
Documentation and read-only testing
See merge request petsc/petsc!3885
|
| #
6c53c5f5
|
| 29-Apr-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'jczhang/fix-kokkos-compile' into 'main'
Config: compile *.kokkos.cxx with CUDA flags if enabled
See merge request petsc/petsc!3923
|
| #
d4147d5d
|
| 27-Apr-2021 |
Junchao Zhang <jczhang@mcs.anl.gov> |
Config: compile *.kokkos.cxx with nvcc flags if enabled
|
| #
4f08eaf7
|
| 17-Apr-2021 |
Jed Brown <jed@jedbrown.org> |
gmakefile: do not generate files for make info
It's convenient to use `make -C $PETSC_DIR info` for diagnostics, but
this would fail if $PETSC_DIR is not writable. We don't need generated
targets fo
gmakefile: do not generate files for make info
It's convenient to use `make -C $PETSC_DIR info` for diagnostics, but
this would fail if $PETSC_DIR is not writable. We don't need generated
targets for this.
show more ...
|
| #
ebcb266d
|
| 04-Apr-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/release'
|
| #
ecd65b60
|
| 03-Apr-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'jczhang/fix-cuda-vecmdot' into 'release'
VecCUDA: do not use variable sized arrays
See merge request petsc/petsc!3800
|
| #
0d8a85bb
|
| 02-Apr-2021 |
Junchao Zhang <jczhang@mcs.anl.gov> |
Config: add back CUDACPPFLAGS
|
| #
3469f230
|
| 17-Mar-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'jed/hip-kokkos' into 'main'
HIP and Kokkos
See merge request petsc/petsc!3509
|
| #
600dc890
|
| 13-Mar-2021 |
Junchao Zhang <jczhang@anl.gov> |
config: compile kokkos with host compiler
|
| #
694a2f0e
|
| 13-Mar-2021 |
Junchao Zhang <jczhang@anl.gov> |
config: change HIPCC to HIPC, and HIPCCFLAGS to HIPFLAGS
|
| #
1ed128d8
|
| 25-Dec-2020 |
Jed Brown <jed@jedbrown.org> |
test: use hipcc to compile and link *.kokkos.cxx
MPI wrappers are a curse.
|
| #
b6b6604c
|
| 28-Jan-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/release'
|
| #
c66ed491
|
| 28-Jan-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'scott/test-fixreport' into 'release'
Scott/test fixreport
See merge request petsc/petsc!3589
|
| #
c9625024
|
| 26-Jan-2021 |
Scott Kruger <scott.e.kruger@gmail.com> |
Improvements in test summarizing logic
Moving logic on when to print out the full summary
allows more fine-grained control of the report_tests.py
logic (always generate a echofailures.sh) and remove
Improvements in test summarizing logic
Moving logic on when to print out the full summary
allows more fine-grained control of the report_tests.py
logic (always generate a echofailures.sh) and remove
bashisms and null dependenciess in gmakefile.test
Thanks to @stefanozampini and @jedbrown for report
show more ...
|
| #
5714cc27
|
| 25-Jan-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/jolivet/cherry-pick-MR-3577' into release
Cherry-pick relevant commits from #3577 for release
See merge request petsc/petsc!3584
|
| #
023a9274
|
| 20-Jan-2021 |
Pierre Jolivet <pierre@joliv.et> |
check-test-errors: fix test: false: unexpected op
|
| #
b1364e53
|
| 23-Jan-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'jolivet/feature-hpddm-actions' into 'master'
Portability fixes
See merge request petsc/petsc!3577
|
| #
29fc8cae
|
| 20-Jan-2021 |
Pierre Jolivet <pierre@joliv.et> |
check-test-errors: fix test: false: unexpected op
|
| #
232fde81
|
| 17-Jan-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/release'
|
| #
1a55b9de
|
| 15-Jan-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'scott/test-harness-tweaks' into 'release'
Scott/test harness tweaks
See merge request petsc/petsc!3525
|
| #
50315b07
|
| 09-Jan-2021 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'barry/2020-12-31/fix-cuda-ccbin-wrong-arguments' into 'master'
The previous code passed options for the PETSc C, C preprocessor and CXX compiler to the
See merge request petsc/petsc!3
Merge branch 'barry/2020-12-31/fix-cuda-ccbin-wrong-arguments' into 'master'
The previous code passed options for the PETSc C, C preprocessor and CXX compiler to the
See merge request petsc/petsc!3530
show more ...
|
| #
7ba7a817
|
| 31-Dec-2020 |
Barry Smith <bsmith@mcs.anl.gov> |
The previous code passed options for the PETSc C, C preprocessor and CXX compiler to the
ccbin compiler used by nvcc even if it was a completely different compiler and the arguments
caused the compil
The previous code passed options for the PETSc C, C preprocessor and CXX compiler to the
ccbin compiler used by nvcc even if it was a completely different compiler and the arguments
caused the compiler to error with unknown arguments.
This has been an outstanding problem for years, this is the first crude attempt to fix it by
not passing the arguments unless the compiler is identical to the PETSc compiler
TODO: have a better check that the compilers are the same
TODO: provide a systematic way for the user to provide the compiler used by nvcc, perhaps default to the compiler used by PETSc?
/spend 3.5h
Thanks-to: Jose E. Roman <jroman@dsic.upv.es>
Fix typo in list of c99 flags
Add error message regarding Intel compilers breaking Gnu compilers when c99 test fails with gcc.
Eventually we may want more systematic checks of Intel compilers breaking Gnu compilers
/spend 15m
show more ...
|