<html>
<head>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<p>Thanks!</p>
<p>Bboth filename and #defines are ok now.</p>
<p>Eric</p>
<p><br>
</p>
<br>
<div class="moz-cite-prefix">Le 2016-12-31 à 16:18, Xiaoye S. Li a
écrit :<br>
</div>
<blockquote
cite="mid:CAFvbobXGkqDP2DR3k+eaq+f5KVkhNS=MhwQoZX6wD2m_cor-ZA@mail.gmail.com"
type="cite">
<div dir="ltr">I just updated version string in git repo and
tarball.
<div><br>
</div>
<div>Sherry</div>
</div>
<div class="gmail_extra"><br>
<div class="gmail_quote">On Sat, Dec 31, 2016 at 10:39 AM,
Satish Balay <span dir="ltr"><<a moz-do-not-send="true"
href="mailto:balay@mcs.anl.gov" target="_blank">balay@mcs.anl.gov</a>></span>
wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0
.8ex;border-left:1px #ccc solid;padding-left:1ex">Ok - one
more place superlu_dist stores version number - that needs
updating with every release.<br>
<br>
cc:ing Sherry<br>
<div class="HOEnZb">
<div class="h5"><br>
Satish<br>
<br>
On Sat, 31 Dec 2016, Eric Chamberland wrote:<br>
<br>
> I think there is definitly a problem.<br>
><br>
> After looking at the files installed either from
petsc-master tarball or the<br>
> manual configure I just did with
--download-superlu_dist-<wbr>commit=v5.1.3, the<br>
> file include/superlu_defs.h have these values:<br>
><br>
> #define SUPERLU_DIST_MAJOR_VERSION 5<br>
> #define SUPERLU_DIST_MINOR_VERSION 1<br>
> #define SUPERLU_DIST_PATCH_VERSION 0<br>
><br>
> What's wrong?<br>
><br>
> Eric<br>
><br>
><br>
> Le 2016-12-31 à 13:26, Eric Chamberland a écrit :<br>
> > Ah ok, I see! Here look at the file name in
the configure.log:<br>
> ><br>
> > Install the project...<br>
> > /usr/bin/cmake -P cmake_install.cmake<br>
> > -- Install configuration: "DEBUG"<br>
> > -- Installing: /opt/petsc-master_debug/lib/<wbr>libsuperlu_dist.so.5.1.0<br>
> > -- Installing: /opt/petsc-master_debug/lib/<wbr>libsuperlu_dist.so.5<br>
> ><br>
> > It is saying 5.1.0, but in fact you are right:
it is 5.1.3 that is<br>
> > downloaded!!! :)<br>
> ><br>
> > And FWIW, the nighlty automatic compilation of
PETSc starts within a brand<br>
> > new and empty directory each night...<br>
> ><br>
> > Thanks to both of you again! :)<br>
> ><br>
> > Eric<br>
> ><br>
> ><br>
> > Le 2016-12-31 à 13:17, Satish Balay a écrit :<br>
> > > ==============================<wbr>==============================<wbr>===================<br>
> > > Trying to
download<br>
> > > git://<a moz-do-not-send="true"
href="https://github.com/xiaoyeli/superlu_dist"
rel="noreferrer" target="_blank">https://github.com/<wbr>xiaoyeli/superlu_dist</a>
for SUPERLU_DIST<br>
> > > ==============================<wbr>==============================<wbr>===================<br>
> > > Executing: git clone<br>
> > > <a moz-do-not-send="true"
href="https://github.com/xiaoyeli/superlu_dist"
rel="noreferrer" target="_blank">https://github.com/xiaoyeli/<wbr>superlu_dist</a><br>
> > > /pmi/cmpbib/compilation_BIB_<wbr>gcc_redhat_petsc-master_debug/<wbr>COMPILE_AUTO/petsc-master-<wbr>debug/arch-linux2-c-debug/<wbr>externalpackages/git.superlu_<wbr>dist<br>
> > > stdout: Cloning into<br>
> > > '/pmi/cmpbib/compilation_BIB_<wbr>gcc_redhat_petsc-master_debug/<wbr>COMPILE_AUTO/petsc-master-<wbr>debug/arch-linux2-c-debug/<wbr>externalpackages/git.superlu_<wbr>dist'...<br>
> > > Looking for
SUPERLU_DIST at git.superlu_dist,<br>
> > > hg.superlu_dist or a directory starting
with ['superlu_dist']<br>
> > > Found a copy of
SUPERLU_DIST in git.superlu_dist<br>
> > > Executing: ['git', 'rev-parse',
'--git-dir']<br>
> > > stdout: .git<br>
> > > Executing: ['git', 'cat-file', '-e',
'v5.1.3^{commit}']<br>
> > > Executing: ['git', 'rev-parse', 'v5.1.3']<br>
> > > stdout: 7306f704c6c8d5113def649b76def3<wbr>c8eb607690<br>
> > > Executing: ['git', 'stash']<br>
> > > stdout: No local changes to save<br>
> > > Executing: ['git', 'clean', '-f', '-d',
'-x']<br>
> > > Executing: ['git', 'checkout', '-f',<br>
> > > '<wbr>7306f704c6c8d5113def649b76def3<wbr>c8eb607690']<br>
> > > <<<<<<<<<br>
> > ><br>
> > > Per log below - its using 5.1.3. Why did
you think you got 5.1.0?<br>
> > ><br>
> > > Satish<br>
> > ><br>
> > > On Sat, 31 Dec 2016, Eric Chamberland
wrote:<br>
> > ><br>
> > > > Hi,<br>
> > > ><br>
> > > > ok I will test with 5.1.3 with the
option you gave me<br>
> > > > (--download-superlu_dit-<wbr>commit=v5.1.3).<br>
> > > ><br>
> > > > But from what you and Matthew said,
I should have 5.1.3 with<br>
> > > > petsc-master, but<br>
> > > > the last night log shows me library
file name 5.1.0:<br>
> > > ><br>
> > > > <a moz-do-not-send="true"
href="http://www.giref.ulaval.ca/%7Ecmpgiref/petsc-master-debug/2016.12.31.02h00m01s_configure.log"
rel="noreferrer" target="_blank">http://www.giref.ulaval.ca/~<wbr>cmpgiref/petsc-master-debug/<wbr>2016.12.31.02h00m01s_<wbr>configure.log</a><br>
> > > ><br>
> > > ><br>
> > > > So I am a bit confused: Why did I
got 5.1.0 last night? (I use the<br>
> > > > petsc-master tarball, is it the
reason?)<br>
> > > ><br>
> > > > Thanks,<br>
> > > ><br>
> > > > Eric<br>
> > > ><br>
> > > ><br>
> > > > Le 2016-12-31 à 11:52, Satish Balay
a écrit :<br>
> > > > > On Sat, 31 Dec 2016, Eric
Chamberland wrote:<br>
> > > > ><br>
> > > > > > Hi,<br>
> > > > > ><br>
> > > > > > I am just starting to
debug a bug encountered with and only with<br>
> > > > > > SuperLU_Dist<br>
> > > > > > combined with MKL on a 2
processes validation test.<br>
> > > > > ><br>
> > > > > > (the same test works fine
with MUMPS on 2 processes).<br>
> > > > > ><br>
> > > > > > I just noticed that the
SuperLU_Dist version installed by PETSc<br>
> > > > > > configure<br>
> > > > > > script is 5.1.0 and the
latest SuperLU_DIST is 5.1.3.<br>
> > > > > If you use petsc-master - it
will install 5.1.3 by default.<br>
> > > > > > Before going further, I
just want to ask:<br>
> > > > > ><br>
> > > > > > Is there any specific
reason to stick to 5.1.0?<br>
> > > > > We don't usually upgrade
externalpackage version in PETSc releases<br>
> > > > > [unless its tested to work and
fixes known bugs]. There could be API<br>
> > > > > changes - or build changes that
can potentially conflict.<br>
> > > > ><br>
> > > > > >From what I know - 5.1.3
should work with petsc-3.7 [it fixes a<br>
> > > > > couple of<br>
> > > > > bugs].<br>
> > > > ><br>
> > > > > You might be able to do the
following with petsc-3.7 [with git<br>
> > > > > externalpackage repos]<br>
> > > > ><br>
> > > > > --download-superlu_dist
--download-superlu_dit-commit=<wbr>v5.1.3<br>
> > > > ><br>
> > > > > Satish<br>
> > > > ><br>
> > > > > > Here is some more
information:<br>
> > > > > ><br>
> > > > > > On process 2 I have this
printed in stdout:<br>
> > > > > ><br>
> > > > > > Intel MKL ERROR: Parameter
6 was incorrect on entry to DTRSM .<br>
> > > > > ><br>
> > > > > > and in stderr:<br>
> > > > > ><br>
> > > > > > Test.ProblemeEFGen.opt:
malloc.c:2369: sysmalloc: Assertion<br>
> > > > > > `(old_top ==<br>
> > > > > > (((mbinptr) (((char *)
&((av)->bins[((1) - 1) * 2])) -<br>
> > > > > > __builtin_offsetof<br>
> > > > > > (struct malloc_chunk,
fd)))) && old_size == 0) || ((unsigned long)<br>
> > > > > > (old_size)<br>
> > > > > > > = (unsigned
long)((((__builtin_offsetof (struct malloc_chunk,<br>
> > > > > > fd_nextsize))+((2
*(sizeof(size_t))) - 1)) & ~((2 *(sizeof(size_t)))<br>
> > > > > > -<br>
> > > > > > 1))) &&<br>
> > > > > > ((old_top)->size &
0x1) && ((unsigned long) old_end & pagemask)
==<br>
> > > > > > 0)'<br>
> > > > > > failed.<br>
> > > > > > [saruman:15771] ***
Process received signal ***<br>
> > > > > ><br>
> > > > > > This is the 7th call to
KSPSolve in the same execution. Here is the<br>
> > > > > > last<br>
> > > > > > KSPView:<br>
> > > > > ><br>
> > > > > > KSP Object:(o_slin) 2 MPI
processes<br>
> > > > > > type: preonly<br>
> > > > > > maximum
iterations=10000, initial guess is zero<br>
> > > > > > tolerances:
relative=1e-05, absolute=1e-50, divergence=10000.<br>
> > > > > > left preconditioning<br>
> > > > > > using NONE norm type
for convergence test<br>
> > > > > > PC Object:(o_slin) 2 MPI
processes<br>
> > > > > > type: lu<br>
> > > > > > LU: out-of-place
factorization<br>
> > > > > > tolerance for zero
pivot 2.22045e-14<br>
> > > > > > matrix ordering:
natural<br>
> > > > > > factor fill ratio
given 0., needed 0.<br>
> > > > > > Factored matrix
follows:<br>
> > > > > > Mat Object:
2 MPI processes<br>
> > > > > > type: mpiaij<br>
> > > > > > rows=382,
cols=382<br>
> > > > > > package used
to perform factorization: superlu_dist<br>
> > > > > > total:
nonzeros=0, allocated nonzeros=0<br>
> > > > > > total number
of mallocs used during MatSetValues calls<br>
> > > > > > =0<br>
> > > > > > SuperLU_DIST
run parameters:<br>
> > > > > > Process
grid nprow 2 x npcol 1<br>
> > > > > >
Equilibrate matrix TRUE<br>
> > > > > > Matrix
input mode 1<br>
> > > > > > Replace
tiny pivots FALSE<br>
> > > > > > Use
iterative refinement FALSE<br>
> > > > > > Processors
in row 2 col partition 1<br>
> > > > > > Row
permutation LargeDiag<br>
> > > > > > Column
permutation METIS_AT_PLUS_A<br>
> > > > > > Parallel
symbolic factorization FALSE<br>
> > > > > > Repeated
factorization SamePattern<br>
> > > > > > linear system matrix =
precond matrix:<br>
> > > > > > Mat Object: (o_slin)
2 MPI processes<br>
> > > > > > type: mpiaij<br>
> > > > > > rows=382, cols=382<br>
> > > > > > total:
nonzeros=4458, allocated nonzeros=4458<br>
> > > > > > total number of
mallocs used during MatSetValues calls =0<br>
> > > > > > using I-node (on
process 0) routines: found 109 nodes, limit<br>
> > > > > > used<br>
> > > > > > is 5<br>
> > > > > ><br>
> > > > > > I know this information is
not enough to help debug, but I would<br>
> > > > > > like to<br>
> > > > > > know<br>
> > > > > > if PETSc guys will upgrade
to 5.1.3 before trying to debug anything.<br>
> > > > > ><br>
> > > > > > Thanks,<br>
> > > > > > Eric<br>
> > > > > ><br>
> > > > > ><br>
> > > ><br>
><br>
><br>
><br>
</div>
</div>
</blockquote>
</div>
<br>
</div>
</blockquote>
<br>
</body>
</html>