[petsc-dev] SuperLU link error on BGP FEN
Xiaoye S. Li
xsli at lbl.gov
Wed Dec 22 17:39:22 CST 2010
I have incorporated this patch in superlu_dist_2.5 tarball:
http://crd.lbl.gov/~xiaoye/SuperLU/superlu_dist_2.5.tar.gz
Thanks!
Sherry
On Tue, Dec 21, 2010 at 12:23 PM, Satish Balay <balay at mcs.anl.gov> wrote:
> Sherry,
>
> One of the patches which we still have in our superlu_dist taball is:
>
>
> http://petsc.cs.iit.edu/petsc/externalpackages/SuperLU_DIST_2.4/raw-diff/ddb59df1a8a5/SRC/superlu_grid.c
>
> could you add this to your tarball?
>
> thanks,
> Satish
>
> On Fri, 3 Dec 2010, Barry Smith wrote:
>
> >
> > Sherry,
> >
> > Thanks, we'll upgrade to use those versions with petsc-dev.
> >
> > Hong and Satish,
> >
> > Could you please update petsc-dev with these newest versions of
> superlu[_dist]
> >
> > Thanks
> >
> > Barry
> >
> > On Dec 3, 2010, at 6:31 PM, Xiaoye S. Li wrote:
> >
> > > Sorry, but just got around to look at this.
> > >
> > > In SuperLU_4.0, we introduced ILU preconditioner, which works better
> with MC64 permutation (which is written in f77). But I forgot to include
> this in slu_Cnames.h, to handle the name mangling issue.
> > >
> > > In SuperLU_4.1, I converted MC64 from f77 to C using f2c. Therefore,
> there is no such name mangling problem. The C version is now also used in
> SuperLU_DIST_2.5.
> > >
> > > In summary, SuperLU_4.1 and SuperLU_DIST_2.5 upward versions should not
> need this name mangling for MC64.
> > >
> > > Sherry
> > >
> > > On Thu, Dec 2, 2010 at 1:40 PM, Satish Balay <balay at mcs.anl.gov>
> wrote:
> > > Looks like a bug in superlu. [this bug doesn't exist in superlu_dist].
> > >
> > > I suspect we've always used superlu with superlu_dist on bgp - so
> > > didn't see this before. [symbols from -lsuperlu_dist must have been
> > > picked up by the linker (before superlu symbols) - and these symbols
> > > resolved without errors]
> > >
> > > The following fixes the issue.
> > >
> > > login2.surveyor:SuperLU_4.0/SRC > diff -Nru slu_Cnames.h~ slu_Cnames.h
> > > --- slu_Cnames.h~ 2009-07-05 00:55:49.000000000 -0500
> > > +++ slu_Cnames.h 2010-12-02 15:19:30.005247114 -0600
> > > @@ -251,6 +251,9 @@
> > > #define izmax1_ IZMAX1
> > > #define zlacon_ ZLACON
> > >
> > > +#define mc64id_ MC64ID
> > > +#define mc64ad_ MC64AD
> > > +
> > > /* Fortran interface */
> > > #define c_bridge_dgssv_ C_BRIDGE_DGSSV
> > > #define c_fortran_sgssv_ C_FORTRAN_SGSSV
> > > @@ -350,6 +353,9 @@
> > > #define izmax1_ izmax1
> > > #define zlacon_ zlacon
> > >
> > > +#define mc64id_ mc64id
> > > +#define mc64ad_ mc64ad
> > > +
> > > /* Fortran interface */
> > > #define c_bridge_dgssv_ c_bridge_dgssv
> > > #define c_fortran_sgssv_ c_fortran_sgssv
> > > login2.surveyor:SuperLU_4.0/SRC >
> > >
> > >
> > > I've respun the superlu download tarball with this fix..
> > >
> > >
> > > Note: Looks like Superlu_4.1 tarball has this bug..
> > >
> > > Satish
> > >
> > > On Thu, 2 Dec 2010, Satish Balay wrote:
> > >
> > > > I'll attempt a build and see how it goes..
> > > >
> > > > satish
> > > >
> > > > On Thu, 2 Dec 2010, Matthew Knepley wrote:
> > > >
> > > > > We always always always always need configure.log.
> > > > >
> > > > > Matt
> > > > >
> > > > > On Thu, Dec 2, 2010 at 8:41 AM, John R. Cary <cary at txcorp.com>
> wrote:
> > > > >
> > > > > > I am trying to link facets on a FEN of surveyor.alcf.anl.gov.
> It ends
> > > > > > with the error,
> > > > > >
> > > > > >
> /gpfs/home/projects/facets/surveyor/contrib-xlc-9.0/petsc-3.1-p4-ser/lib/libsuperlu_4.0.a(dldperm.o):
> > > > > > In function `dldperm':
> > > > > >
> /gpfs/home/cary/facetspkgs/builds/petsc-3.1-p4/ser/externalpackages/SuperLU_4.0/SRC/dldperm.c:127:
> > > > > > undefined reference to `mc64id_'
> > > > > >
> /gpfs/home/cary/facetspkgs/builds/petsc-3.1-p4/ser/externalpackages/SuperLU_4.0/SRC/dldperm.c:134:
> > > > > > undefined reference to `mc64ad_'
> > > > > >
> > > > > > which indicates that the SuperLU compiled with PETSc did
> > > > > > not get the fortran underscoring flag correct (which should
> > > > > > be no underscore with xlf). nm shows
> > > > > >
> > > > > > login1.surveyor$ nm
> > > > > >
> /gpfs/home/projects/facets/surveyor/contrib-xlc-9.0/petsc-3.1-p4-ser/lib/libsuperlu_4.0.a
> > > > > > | grep mc64
> > > > > > U mc64ad_
> > > > > > U mc64id_
> > > > > > mc64ad.o:
> > > > > > 0000000000000018 D mc64ad
> > > > > > 0000000000000030 D mc64bd
> > > > > > 0000000000000048 D mc64dd
> > > > > > 0000000000000060 D mc64ed
> > > > > > 0000000000000078 D mc64fd
> > > > > > 0000000000000000 D mc64id
> > > > > > 00000000000000c0 D mc64qd
> > > > > > 0000000000000090 D mc64rd
> > > > > > 00000000000000a8 D mc64sd
> > > > > > 00000000000000d8 D mc64ud
> > > > > > 00000000000000f0 D mc64wd
> > > > > > U mc64ad_
> > > > > > U mc64id_
> > > > > >
> > > > > > that the underscored symbol is being called, but the
> > > > > > underscore-free symbol is what was defined.
> > > > > >
> > > > > > My PETSc configure line was
> > > > > >
> > > > > > #!/bin/sh
> > > > > >
> /gpfs/home/cary/facetspkgs/builds-surveyor-xlc/facetspkgs/petsc-3.1-p4/ser/configure
> > > > > > \
> > > > > >
> --prefix=/gpfs/home/projects/facets/surveyor/contrib-xlc-9.0/petsc-3.1-p4-ser
> > > > > > \
> > > > > > --with-mpi=0 \
> > > > > > --with-debugging=0 \
> > > > > > --with-x=0 \
> > > > > > --with-cc='xlc_r' \
> > > > > > --with-cxx='xlC_r' \
> > > > > > --with-fc='xlf_r' \
> > > > > > --COPTFLAGS='-O2 -g' \
> > > > > > --download-superlu \
> > > > > >
> --with-lapack-lib=/home/projects/facets/intrepid/contrib/lapack-ser/lib/liblapack.a
> > > > > > \
> > > > > >
> --with-blas-lib=/home/projects/facets/intrepid/contrib/lapack-ser/lib/libblas.a
> > > > > > \
> > > > > >
> PETSC_DIR=/gpfs/home/cary/facetspkgs/builds-surveyor-xlc/facetspkgs/petsc-3.1-p4/ser
> > > > > > \
> > > > > > PETSC_ARCH=facets-ser \
> > > > > > --CFLAGS='-q64 -qlanglvl=redefmac' \
> > > > > > --CXXFLAGS='-q64 -qlanglvl=redefmac' \
> > > > > > --FFLAGS='-q64 -qextname=flush' \
> > > > > > --with-shared=1
> > > > > >
> > > > > > so I think that PETSc had enough info to figure out the
> underscoring.
> > > > > > Perhaps this is a bug.
> > > > > >
> > > > > > But regardless, is there a workaround?
> > > > > >
> > > > > > Thx....John
> > > > > >
> > > > >
> > > > >
> > > > >
> > > > >
> > > >
> > > >
> > >
> > >
> >
> >
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20101222/5745867f/attachment.html>
More information about the petsc-dev
mailing list