Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/13/2016 05:54 PM, Satish Balay wrote: > On Thu, 13 Oct 2016, Antonio Trande wrote: > >> >> I guess, we can consider all tests successfully passed. > > Great! Thank you very much for your fundamental support. > > I'm sure there will be more issues to deal with [when folks start > using th

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Thu, 13 Oct 2016, Antonio Trande wrote: > > I guess, we can consider all tests successfully passed. Great! I'm sure there will be more issues to deal with [when folks start using these packages] For one - with our default build - one uses portable makefile [with PETSC_DIR/PETSC_ARCH] for de

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/13/2016 04:13 PM, Satish Balay wrote: > On Thu, 13 Oct 2016, Antonio Trande wrote: > > Latest builds: > http://copr-fe.cloud.fedoraproject.org/coprs/sagitter/petsc/build/464373/ >>> I'll try and see if I can reproduce this.. [in a 32bit VM].. >>> >>> To start off - I looked at a

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Thu, 13 Oct 2016, Antonio Trande wrote: > New builds: > > Without "/usr/lib/rpm/redhat/redhat-hardened-cc1" flags: > http://copr-fe.cloud.fedoraproject.org/coprs/sagitter/petsc/build/464687/ > > Same configuration for debugging: > http://copr-fe.cloud.fedoraproject.org/coprs/sagitter/petsc/bu

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Thu, 13 Oct 2016, Antonio Trande wrote: > >>> Latest builds: > >>> http://copr-fe.cloud.fedoraproject.org/coprs/sagitter/petsc/build/464373/ > > > >> I'll try and see if I can reproduce this.. [in a 32bit VM].. > > > > To start off - I looked at all the 5 32bit build logs in 464373 - and > >

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/13/2016 02:31 AM, Satish Balay wrote: > On Wed, 12 Oct 2016, Satish Balay wrote: > >> On Wed, 12 Oct 2016, Antonio Trande wrote: >> >>> Latest builds: >>> http://copr-fe.cloud.fedoraproject.org/coprs/sagitter/petsc/build/464373/ > >> I'll try and see if I can reproduce this.. [in a 32bit VM

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Wed, 12 Oct 2016, Satish Balay wrote: > On Wed, 12 Oct 2016, Antonio Trande wrote: > > > Latest builds: > > http://copr-fe.cloud.fedoraproject.org/coprs/sagitter/petsc/build/464373/ > I'll try and see if I can reproduce this.. [in a 32bit VM].. To start off - I looked at all the 5 32bit buil

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Wed, 12 Oct 2016, Antonio Trande wrote: > >> Latest builds: > >> http://copr-fe.cloud.fedoraproject.org/coprs/sagitter/petsc/build/464373/ > > > > I've mentioned this a few times - You haven't been able to run the > > sequntial test in valgrind? > > It was ran in valgrind: > https://copr-be.

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/12/2016 07:21 PM, Satish Balay wrote: > On Wed, 12 Oct 2016, Antonio Trande wrote: > >> On 10/11/2016 11:52 PM, Antonio Trande wrote: >>> On 10/11/2016 09:39 PM, Satish Balay wrote: On Tue, 11 Oct 2016, Antonio Trande wrote: > 'configure' does not recognize '-D_FORTIFY_SOURCE=2

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Wed, 12 Oct 2016, Antonio Trande wrote: > On 10/11/2016 11:52 PM, Antonio Trande wrote: > > On 10/11/2016 09:39 PM, Satish Balay wrote: > >> On Tue, 11 Oct 2016, Antonio Trande wrote: > >> > >>> 'configure' does not recognize '-D_FORTIFY_SOURCE=2' flag (it says that > >>> should be -D-FORTIFY-S

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/11/2016 11:52 PM, Antonio Trande wrote: > On 10/11/2016 09:39 PM, Satish Balay wrote: >> On Tue, 11 Oct 2016, Antonio Trande wrote: >> >>> 'configure' does not recognize '-D_FORTIFY_SOURCE=2' flag (it says that >>> should be -D-FORTIFY-SOURCE=2) that comes from default flags used on >>> Fedor

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/11/2016 09:39 PM, Satish Balay wrote: > On Tue, 11 Oct 2016, Antonio Trande wrote: > >> 'configure' does not recognize '-D_FORTIFY_SOURCE=2' flag (it says that >> should be -D-FORTIFY-SOURCE=2) that comes from default flags used on >> Fedora and automatically set when package is built. I'm f

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Tue, 11 Oct 2016, Antonio Trande wrote: > However, i don't understand why errors appear from 'make test' by > building on Fedora 32bit systems only. Only of the 32bit rawhide builds ? [as 32bit ones one f24, epel were fine?] This is very puzzling to me. > [0]PETSC ERROR: #1 PetscOptionsIns

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Tue, 11 Oct 2016, Antonio Trande wrote: > 'configure' does not recognize '-D_FORTIFY_SOURCE=2' flag (it says that > should be -D-FORTIFY-SOURCE=2) that comes from default flags used on > Fedora and automatically set when package is built. I'm forced to > exclude it with 'configure' and re-intro

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/11/2016 07:53 PM, Satish Balay wrote: > On Tue, 11 Oct 2016, Antonio Trande wrote: > >> On 10/11/2016 12:14 AM, Satish Balay wrote: >>> On Mon, 10 Oct 2016, Antonio Trande wrote: >>> On 10/10/2016 07:28 PM, Satish Balay wrote: > On Mon, 10 Oct 2016, Antonio Trande wrote: >>> >>

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Tue, 11 Oct 2016, Antonio Trande wrote: > On 10/11/2016 12:14 AM, Satish Balay wrote: > > On Mon, 10 Oct 2016, Antonio Trande wrote: > > > >> On 10/10/2016 07:28 PM, Satish Balay wrote: > >>> On Mon, 10 Oct 2016, Antonio Trande wrote: > > > >> > >> New builds: > >> > >> 32bit: > >> https://co

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/11/2016 12:14 AM, Satish Balay wrote: > On Mon, 10 Oct 2016, Antonio Trande wrote: > >> On 10/10/2016 07:28 PM, Satish Balay wrote: >>> On Mon, 10 Oct 2016, Antonio Trande wrote: > >> >> New builds: >> >> 32bit: >> https://copr-be.cloud.fedoraproject.org/results/sagitter/petsc/fedora-24-i38

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

Done in branch barry/remove-papi > On Oct 10, 2016, at 7:30 PM, Jed Brown wrote: > > Barry Smith writes: > >>> On Oct 10, 2016, at 7:09 PM, Jed Brown wrote: >>> >>> Barry Smith writes: >>> Funny, I thought Jed said I stripped out all the PAPI stuff? Maybe I should really strip

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

Barry Smith writes: >> On Oct 10, 2016, at 7:09 PM, Jed Brown wrote: >> >> Barry Smith writes: >> >>> Funny, I thought Jed said I stripped out all the PAPI stuff? Maybe I >>> should really strip it out, has not been used in years and as Jed >>> says it has Jack's slimeprints on it. >> >>

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

> On Oct 10, 2016, at 7:09 PM, Jed Brown wrote: > > Barry Smith writes: > >> Funny, I thought Jed said I stripped out all the PAPI stuff? Maybe I >> should really strip it out, has not been used in years and as Jed >> says it has Jack's slimeprints on it. > > I haven't touched it. I k

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

Barry Smith writes: > Funny, I thought Jed said I stripped out all the PAPI stuff? Maybe I > should really strip it out, has not been used in years and as Jed > says it has Jack's slimeprints on it. I haven't touched it. Looks like you added it in 2009. I think we had a mailing list thre

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Mon, 10 Oct 2016, Antonio Trande wrote: > On 10/10/2016 07:28 PM, Satish Balay wrote: > > On Mon, 10 Oct 2016, Antonio Trande wrote: > > New builds: > > 32bit: > https://copr-be.cloud.fedoraproject.org/results/sagitter/petsc/fedora-24-i386/00463215-petsc/build.log.gz > Section with errors: h

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Mon, 10 Oct 2016, Satish Balay wrote: > Removing superlu_fixed the previous error? Thats wierd.. > > You can try the attached patch - and see if that fixes this valgrind issue.. you can replace the previous progname.patch with the following two.. [these should be in the next patch update] h

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/10/2016 07:28 PM, Satish Balay wrote: > On Mon, 10 Oct 2016, Antonio Trande wrote: > >> This error is disappeared. > > Its strange that PetscStrncpy() issues comes up only on this one build. > >> >> Build on RHEL6 systems: >> https://copr-be.cloud.fedoraproject.org/results/sagitter/petsc/e

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Mon, 10 Oct 2016, Antonio Trande wrote: > This error is disappeared. Its strange that PetscStrncpy() issues comes up only on this one build. > > Build on RHEL6 systems: > https://copr-be.cloud.fedoraproject.org/results/sagitter/petsc/epel-6-i386/00463135-petsc/build.log.gz > > Build on Fedo

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/10/2016 04:08 PM, Satish Balay wrote: > Removing superlu_fixed the previous error? Thats wierd.. No; it was just an attempt. > > You can try the attached patch - and see if that fixes this valgrind issue.. > > Satish > > On Mon, 10 Oct 2016, Antonio Trande wrote: > >> This is the only e

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

Removing superlu_fixed the previous error? Thats wierd.. You can try the attached patch - and see if that fixes this valgrind issue.. Satish On Mon, 10 Oct 2016, Antonio Trande wrote: > This is the only explicit error that i see (just on serial 32bit libs). > I have disabled SuperLU support, to

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

This is the only explicit error that i see (just on serial 32bit libs). I have disabled SuperLU support, too. + cd petsc-3.7.4 + export LD_LIBRARY_PATH=/usr/lib:/builddir/build/BUILD/petsc-3.7.4/petsc-3.7.4/i386/lib + LD_LIBRARY_PATH=/usr/lib:/builddir/build/BUILD/petsc-3.7.4/petsc-3.7.4/i386/lib

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Sun, 9 Oct 2016, Satish Balay wrote: > On Sun, 9 Oct 2016, Antonio Trande wrote: > > > There is still a bad exit status of OpenMPI libs on *32bit architectures > > only*: > > > > make: Entering directory > > '/builddir/build/BUILD/petsc-3.7.4/buildopenmpi_dir' > > Running test examples to ver

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Sun, 9 Oct 2016, Antonio Trande wrote: > There is still a bad exit status of OpenMPI libs on *32bit architectures > only*: > > make: Entering directory > '/builddir/build/BUILD/petsc-3.7.4/buildopenmpi_dir' > Running test examples to verify correct installation > Using PETSC_DIR=/builddir/buil

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/09/2016 09:12 PM, Satish Balay wrote: > On Sun, 9 Oct 2016, Antonio Trande wrote: > >> On 10/09/2016 05:39 PM, Satish Balay wrote: >>> Perhaps chkopts also doesn't make sense anymore [esp with user >>> makefiles] - so you could use the attached patch [which diables >>> checkopts - and this a

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Sun, 9 Oct 2016, Antonio Trande wrote: > On 10/09/2016 05:39 PM, Satish Balay wrote: > > Perhaps chkopts also doesn't make sense anymore [esp with user > > makefiles] - so you could use the attached patch [which diables > > checkopts - and this also disables petscnagupgrade.py] > > > > Thank

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/09/2016 05:39 PM, Satish Balay wrote: > Perhaps chkopts also doesn't make sense anymore [esp with user > makefiles] - so you could use the attached patch [which diables > checkopts - and this also disables petscnagupgrade.py] > Thank you for the patch. I see error during testing of OpenMPI

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Sun, 9 Oct 2016, Satish Balay wrote: > On Sun, 9 Oct 2016, Antonio Trande wrote: > > > > > PAPI disabled. > > > > Please, see the result of testing at the bottom of this log: > > https://copr-be.cloud.fedoraproject.org/results/sagitter/petsc/fedora-rawhide-x86_64/00462741-petsc/build.log.gz

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Sun, 9 Oct 2016, Antonio Trande wrote: > > PAPI disabled. > > Please, see the result of testing at the bottom of this log: > https://copr-be.cloud.fedoraproject.org/results/sagitter/petsc/fedora-rawhide-x86_64/00462741-petsc/build.log.gz > Hm - the url is not working.. balay@asterix /home/

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

Perhaps chkopts also doesn't make sense anymore [esp with user makefiles] - so you could use the attached patch [which diables checkopts - and this also disables petscnagupgrade.py] Satish On Sun, 9 Oct 2016, Matthew Knepley wrote: > On Sun, Oct 9, 2016 at 7:11 AM, Antonio Trande > wrote: > >

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Sun, Oct 9, 2016 at 7:11 AM, Antonio Trande wrote: > On 10/09/2016 11:48 AM, Matthew Knepley wrote: > > On Sun, Oct 9, 2016 at 4:23 AM, Antonio Trande > > wrote: > > > > On 10/08/2016 11:50 PM, Satish Balay wrote: > > >> > > >> Do tests need internet

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/09/2016 11:48 AM, Matthew Knepley wrote: > On Sun, Oct 9, 2016 at 4:23 AM, Antonio Trande > wrote: > > On 10/08/2016 11:50 PM, Satish Balay wrote: > >> > >> Do tests need internet by chance? > > > > Nope - but you might want to disable petsc

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Sun, Oct 9, 2016 at 4:23 AM, Antonio Trande wrote: > On 10/08/2016 11:50 PM, Satish Balay wrote: > >> > >> Do tests need internet by chance? > > > > Nope - but you might want to disable petscnagupgrade.py in > lib/petsc/conf/rules > > > How? Change the action for the chk_upgrade target to 't

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/08/2016 11:50 PM, Satish Balay wrote: >> >> Do tests need internet by chance? > > Nope - but you might want to disable petscnagupgrade.py in > lib/petsc/conf/rules How? -- --- Antonio Trande mailto: sagitter 'at' fedoraproject 'dot' org http://fedoraos.wordpress.com/ https://fedoraproje

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

Funny, I thought Jed said I stripped out all the PAPI stuff? Maybe I should really strip it out, has not been used in years and as Jed says it has Jack's slimeprints on it. > On Oct 8, 2016, at 4:50 PM, Satish Balay wrote: > >> > > I was previously looking at wrong sources.. > > [0]

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Sat, 8 Oct 2016, Antonio Trande wrote: > On 10/08/2016 11:30 PM, Satish Balay wrote: > > >>> > >>> Previously you had a build where these errors didn't come up > >>> > >>> https://paste.fedoraproject.org/445643/ > >> > >> I seen that 'csh' tool was not found. > > > > Not sure what you mea

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/08/2016 11:30 PM, Satish Balay wrote: >>> >>> Previously you had a build where these errors didn't come up >>> >>> https://paste.fedoraproject.org/445643/ >> >> I seen that 'csh' tool was not found. > > Not sure what you mean. I don't see any 'csh' in either of the logs. > Same build

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Sat, 8 Oct 2016, Antonio Trande wrote: > On 10/08/2016 11:00 PM, Satish Balay wrote: > > On Sat, 8 Oct 2016, Antonio Trande wrote: > > > >> On 10/08/2016 05:57 PM, Antonio Trande wrote: > >>> This is a rebuild of OpenBlas outside Fedora repositories, so they're > >>> unofficial packages; i hav

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/08/2016 11:00 PM, Satish Balay wrote: > On Sat, 8 Oct 2016, Antonio Trande wrote: > >> On 10/08/2016 05:57 PM, Antonio Trande wrote: >>> This is a rebuild of OpenBlas outside Fedora repositories, so they're >>> unofficial packages; i have included optimization flags + >>> '-fdefault-integer-

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Sat, 8 Oct 2016, Antonio Trande wrote: > On 10/08/2016 05:57 PM, Antonio Trande wrote: > > This is a rebuild of OpenBlas outside Fedora repositories, so they're > > unofficial packages; i have included optimization flags + > > '-fdefault-integer-8' for 64bit-int libs: > > > > Fedora 24 package

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/08/2016 05:57 PM, Antonio Trande wrote: > This is a rebuild of OpenBlas outside Fedora repositories, so they're > unofficial packages; i have included optimization flags + > '-fdefault-integer-8' for 64bit-int libs: > > Fedora 24 packages: > https://copr-be.cloud.fedoraproject.org/results/sa

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

This is a rebuild of OpenBlas outside Fedora repositories, so they're unofficial packages; i have included optimization flags + '-fdefault-integer-8' for 64bit-int libs: Fedora 24 packages: https://copr-be.cloud.fedoraproject.org/results/sagitter/petsc/fedora-24-x86_64/00462441-openblas/ Build lo

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Sat, 8 Oct 2016, Antonio Trande wrote: > Okay; let me contact OpenBlas maintainer on Fedora and open a bug ticket. > > Just a question, is '-fdefault-integer-8' flag required even in PETSc? Nope. PETSc uses c-preprocessing in fortran sources - to get the correct datatypes. Satish

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/08/2016 12:42 AM, Satish Balay wrote: > On Fri, 7 Oct 2016, Antonio Trande wrote: > >> On 10/07/2016 08:29 PM, Satish Balay wrote: >>> When I build openblas from sources - I don't see this error. >>> > >>> balay@asterix /home/balay/petsc/src/snes/examples/tutorials (master=) >>> $ va

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Fri, 7 Oct 2016, Antonio Trande wrote: > On 10/07/2016 08:29 PM, Satish Balay wrote: > > When I build openblas from sources - I don't see this error. > > > >>> > > balay@asterix /home/balay/petsc/src/snes/examples/tutorials (master=) > > $ valgrind --tool=memcheck -q ./ex19 -da_refine 3 -p

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/07/2016 08:29 PM, Satish Balay wrote: > When I build openblas from sources - I don't see this error. > >>> > balay@asterix /home/balay/petsc/src/snes/examples/tutorials (master=) > $ valgrind --tool=memcheck -q ./ex19 -da_refine 3 -pc_type mg -ksp_type fgmres > lid velocity = 0.0016, pra

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

When I build openblas from sources - I don't see this error. >> balay@asterix /home/balay/petsc/src/snes/examples/tutorials (master=) $ valgrind --tool=memcheck -q ./ex19 -da_refine 3 -pc_type mg -ksp_type fgmres lid velocity = 0.0016, prandtl # = 1., grashof # = 1. Number of SNES iterations =

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On 10/07/2016 06:03 PM, Satish Balay wrote: > On Fri, 7 Oct 2016, Matthew Knepley wrote: > >> On Fri, Oct 7, 2016 at 10:54 AM, Antonio Trande >> wrote: >> >>> Hi all. >>> >>> This issue is related to discussion from dev-ML: >>> http://lists.mcs.anl.gov/pipermail/petsc-dev/2016-October/019827.ht

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

> > Hm --with-64-bit-indices=0 --with-64-bit-indices=1 > --with-blas-lib=-lopenblas64 --with-lapack-lib=-lopenblas64 > --known-64-bit-blas-indices=1 > > Hm - this --known-64-bit-blas-indices=1 was primarily tested with MKL - > assuming its not isssue with -lopenblas64 [thats triggering the SEG

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Fri, 7 Oct 2016, Antonio Trande wrote: > > They come out by testing serial PETSc libraries according to reported > configuration in following log, please, see > https://paste.fedoraproject.org/445643/ > + make -C petsc-3.7.3 PETSC_DIR=/builddir/build/BUILD/petsc-3.7.3/petsc-3.7.3 PETSC_ARCH

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Fri, 7 Oct 2016, Matthew Knepley wrote: > On Fri, Oct 7, 2016 at 10:54 AM, Antonio Trande > wrote: > > > Hi all. > > > > This issue is related to discussion from dev-ML: > > http://lists.mcs.anl.gov/pipermail/petsc-dev/2016-October/019827.html > > > > What do cause the errors: > > > > + make

Re: [petsc-dev] Possible error running C/C++ src/snes/examples/tutorials/ex19 with 1 MPI process

On Fri, Oct 7, 2016 at 10:54 AM, Antonio Trande wrote: > Hi all. > > This issue is related to discussion from dev-ML: > http://lists.mcs.anl.gov/pipermail/petsc-dev/2016-October/019827.html > > What do cause the errors: > > + make -C build64 test > make: Entering directory '/builddir/build/BUILD/