On 5/23/2012 11:20 PM, Jeff Squyres wrote:
On May 23, 2012, at 9:53 AM, marco atzeri wrote:
experience says that autoreconf is a good approach on cygwin,
it is almost standard on our package build procedure.
I'm still curious: why? (I'm *assuming* that you're building from an official
Open MPI tarball -- is that incorrect?)
I ask because we've already run autoreconf, meaning that official Open MPI
tarballs are fully bootstrapped and do not need to have autogen (i.e.,
ultimately autoreconf) re-run on them.
Specifically: I'm unaware of a reason why you should need to re-run autogen
(autoreconf) on an otherwise-unaltered Open MPI that was freshly extracted from
a tarball. Does something happen differently if you *don't* re-run autogen
(autoreconf)?
Re-running autogen shouldn't be causing you any problems, of course -- this is
just my curiosity asserting itself...
Hi Jeff,
~ 90% of the time we have mismatch problems between upstream and
cygwin on autoconf/automake/libtool versions that are not cygwin
aware or updated.
As safe approuch, we prefer apply "autoreconf -i -f" as default when
building binary packages.
see cygautoreconf on
http://cygwin-ports.svn.sourceforge.net/viewvc/cygwin-ports/cygport/trunk/README
Regards
Marco
