I don't think a ticket or PR was filed for this. I was able to reproduce on a Power8 machine, and filed the issue below: https://github.com/open-mpi/ompi/issues/1854
Nathan I added you to the ticket since it sounded like you had an idea where the problem was. On Thu, Jul 7, 2016 at 12:48 PM, Paul Hargrove <phhargr...@lbl.gov> wrote: > Josh, > > Big-endian Power7: > > $ xlc -qversion > IBM XL C/C++ for Linux, V13.1 > Version: 13.01.0000.0000 > > $ export OBJECT_MODE=64 > > $ [...]/configure -prefix=[....] --enable-debug \ > CC=xlc CFLAGS="-q64" --with-wrapper-cflags="-q64" \ > CXX=xlC CXXFLAGS="-q64" --with-wrapper-cxxflags="-q64" \ > FC=xlf FCFLAGS="-q64" --with-wrapper-fcflags="-q64" \ > --disable-oshmem-fortran --with-hwloc=$HOME/hwloc-1.11.3 > > > Note the --with-hwloc is there because this is the xlc version that was > crashing building the embedded hwloc. > Am retesting now without that flag, but don't expect it has any relation > to the SEGV in the patcher code. > > Little-endian Power8: > > $ xlc -qversion > IBM XL C/C++ for Linux, V13.1.2 (5725-C73, 5765-J08) > Version: 13.01.0002.0000 > > $ [...]/configure -prefix=[....] --enable-debug \ > CC=xlc CXX=xlC FC=xlf --disable-mpi-fortran > > > There is no xlf installation on this system. > > -Paul > > > On Thu, Jul 7, 2016 at 8:39 AM, Josh Hursey <jjhur...@open-mpi.org> wrote: > >> Paul, >> >> What was the configure string you used for this? >> >> We have a Jenkins CI mechanism for XL, but it is using XLC 13.1.3 on that >> system and we haven't been runing 'make check'. I have another system that >> has XLC 13.1.2 that I can test on as well. I'm not sure if I'll be able to >> fix without Nathan's help, but I can at least try to reproduce. >> >> Thanks, >> Josh >> >> >> On Wed, Jul 6, 2016 at 4:58 PM, Paul Hargrove <phhargr...@lbl.gov> wrote: >> >>> The issue reported in >>> https://www.open-mpi.org/community/lists/devel/2016/06/19107.php is >>> still present on both my little-endian Power8 and big-endian Power7 systems. >>> I know Nathan had been working on this, but I've lost track of the issue >>> and/or pr number(s). >>> >>> -Paul >>> >>> -- >>> Paul H. Hargrove phhargr...@lbl.gov >>> Computer Languages & Systems Software (CLaSS) Group >>> Computer Science Department Tel: +1-510-495-2352 >>> Lawrence Berkeley National Laboratory Fax: +1-510-486-6900 >>> >>> _______________________________________________ >>> devel mailing list >>> de...@open-mpi.org >>> Subscription: https://www.open-mpi.org/mailman/listinfo.cgi/devel >>> Link to this post: >>> http://www.open-mpi.org/community/lists/devel/2016/07/19156.php >>> >> >> >> _______________________________________________ >> devel mailing list >> de...@open-mpi.org >> Subscription: https://www.open-mpi.org/mailman/listinfo.cgi/devel >> Link to this post: >> http://www.open-mpi.org/community/lists/devel/2016/07/19163.php >> > > > > -- > Paul H. Hargrove phhargr...@lbl.gov > Computer Languages & Systems Software (CLaSS) Group > Computer Science Department Tel: +1-510-495-2352 > Lawrence Berkeley National Laboratory Fax: +1-510-486-6900 > > _______________________________________________ > devel mailing list > de...@open-mpi.org > Subscription: https://www.open-mpi.org/mailman/listinfo.cgi/devel > Link to this post: > http://www.open-mpi.org/community/lists/devel/2016/07/19164.php >
