<div dir="ltr">I've commented the autodect lines out and am waiting for a compute node.<div><br></div><div>Here is what you wanted.</div><div><br></div><div>Thanks,</div></div><div class="gmail_extra"><br><div class="gmail_quote">On Thu, May 14, 2015 at 11:27 AM, Satish Balay <span dir="ltr"><<a 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">You mention multiple failures here - but include log for only one case.<br>
<br>
Ideally lanugage compilers (c,c++,fortran) should interoperate with<br>
each other - but without it - one has to know the 'compatibility<br>
libraries' to use.<br>
<br>
-lstdc++ is a gnu/c++ library. For PGI - the library names could be<br>
diffferent.<br>
<br>
--with-cxxlib-autodetect=1 - which is configure default - tries to<br>
determine this list - but with cray modules - this causes multiple<br>
listing of all libraries that are setup via modules - sometimes<br>
causing grief - hence you are using --with-cxxlib-autodetect=0 on cray<br>
builds.<br>
<br>
Can you send me the following info?<br>
<br>
cd src/benchmarks<br>
cc -v sizeof.c<br>
CC -v sizeof.c<br>
<br>
Also you can try --with-cxxlib-autodetect=1 - and see if it works.<br>
<br>
Satish<br>
<span class=""><br>
On Thu, 14 May 2015, Mark Adams wrote:<br>
<br>
> We have Titan working but we have a problem that we need lstdc++ to get<br>
> PETSc to configure. Otherwise it fails to build fortran. This seems to<br>
> only be needed for GNU. This is for PGI. If we remove this C++ works,<br>
> otherwise there is a missing external. I guess I can just deploy two<br>
> version, on for fortran and one for C++ (I have a C++ and a fortran code<br>
> that I support).<br>
><br>
><br>
> On Tue, May 12, 2015 at 9:36 AM, Barry Smith <<a href="mailto:bsmith@mcs.anl.gov">bsmith@mcs.anl.gov</a>> wrote:<br>
><br>
> ><br>
> > Remind me again how much the US tax payers spend on this machine each<br>
> > year.<br>
> ><br>
> ><br>
> > Begin forwarded message:<br>
> ><br>
</span>> > *From: *Mark Adams <<a href="mailto:mfadams@lbl.gov">mfadams@lbl.gov</a>><br>
> > *Subject: **Re: [petsc-users] configure error on Titan with Intel*<br>
> > *Date: *May 12, 2015 at 11:12:55 AM CDT<br>
> > *To: *Barry Smith <<a href="mailto:bsmith@mcs.anl.gov">bsmith@mcs.anl.gov</a>><br>
> > *Cc: *Jed Brown <<a href="mailto:jed@jedbrown.org">jed@jedbrown.org</a>>, petsc-users <<a href="mailto:petsc-users@mcs.anl.gov">petsc-users@mcs.anl.gov</a>>,<br>
<div class="HOEnZb"><div class="h5">> > "David Trebotich" <<a href="mailto:treb@lbl.gov">treb@lbl.gov</a>>, "D'Azevedo, Ed F." <<a href="mailto:dazevedoef@ornl.gov">dazevedoef@ornl.gov</a>><br>
> ><br>
> ><br>
> ><br>
> >> Notes: ./configure ran fine and detected -lhwloc in some standard<br>
> >> system install location under normal circumstances it couldn't just<br>
> >> disappear for a different example.<br>
> >><br>
> >><br>
> > I configured in an interactive shell, so on a compute node. I tried to<br>
> > 'make ex56' on a login node, as usual. So I am guessing that it would have<br>
> > worked if I had made it a compute node. They have an inconstancy, I'm<br>
> > guessing. I can try it all on a compute node ....<br>
> ><br>
> > Mark<br>
> ><br>
> ><br>
> >><br>
> >> > /<br>
> >> ><br>
> >> > On Fri, May 8, 2015 at 5:51 PM, Jed Brown <<a href="mailto:jed@jedbrown.org">jed@jedbrown.org</a>> wrote:<br>
> >> > Satish Balay <<a href="mailto:balay@mcs.anl.gov">balay@mcs.anl.gov</a>> writes:<br>
> >> ><br>
> >> > > Also - Perhaps with intel compilers - the recommended blas is<br>
> >> > > something other than ACML? [like MKL?]. Something to check..<br>
> >> ><br>
> >> > MKL (and anything built using the Intel compiler) has the "run slower on<br>
> >> > AMD" feature. For any given operation, ACML won't necessarily be<br>
> >> > faster, but at least it's not intentionally crippled. For most of what<br>
> >> > PETSc does, any such MKL/ACML difference is irrelevant.<br>
> >> ><br>
> >> > <configure.log><make.log><br>
> >><br>
> >><br>
> ><br>
> ><br>
><br>
<br>
</div></div></blockquote></div><br></div>