Juergen Fuhrmann <fuhrmann(a)wias-berlin.de> writes:
> Hi,
>
>
> I am posting to this list as I suppose that people interested in IA64
> are not that far from being interested in OpenMP stuff, and I did not
> find any other suse list somehow specific on this issue.
>
> The issue ist the following: we try to run the intel compiler 6.0 on a
> Pentium4 with Suse7.3 and 2.4.18 kernel. When switching over to
> OpenMP, we get segfaults in the startup phase. The intel guys told us
> that we would need a glibc with FLOATING_STACKS enabled, and gave us a
> version. However just replacing the lib leads to a complete crash of
> all other tools.
>
> So I suppose the issue is more complex. Do you have any suggestion
> (at least the RTFM thing -- where I can find out more) ? Could the
> problem be resolved by compiling glibc by ourselves ?
You shouldn't mix a glibc compiled for Red Hat with one for SuSE.
SuSE 8.0 comes in unsorted with a glibc that uses floating stacks and
that one should work.
A glibc compiled from sources for i686-linux-gnu with the configure
flag --enable-kernel=2.4.0 gives you a glibc with floatings stacks.
Andreas
--
Andreas Jaeger
SuSE Labs aj(a)suse.de
private aj(a)arthur.inka.de
http://www.suse.de/~aj
Hi,
I am posting to this list as I suppose that people interested in IA64
are not that far from being interested in OpenMP stuff, and I did not
find any other suse list somehow specific on this issue.
The issue ist the following: we try to run the intel compiler 6.0 on a
Pentium4 with Suse7.3 and 2.4.18 kernel. When switching over to
OpenMP, we get segfaults in the startup phase. The intel guys told us
that we would need a glibc with FLOATING_STACKS enabled, and gave us a
version. However just replacing the lib leads to a complete crash of
all other tools.
So I suppose the issue is more complex. Do you have any suggestion
(at least the RTFM thing -- where I can find out more) ? Could the
problem be resolved by compiling glibc by ourselves ?
Juergen
Juergen Fuhrmann
Numerical Mathematics & Scientific Computing
Weierstrass Institute for Applied Analysis and Stochastics
Mohrenstr. 39 10117 Berlin fon:+49 30 20372560 fax:+49 30 2044975
http://www.wias-berlin.de/~fuhrmann mailto:fuhrmann@wias-berlin.de
