[RULE] Is it worth rebuilding from source RPMs for a specific CPU type?

[C David Rigby]

Above and beyond the issue of the lack of an "i386" kernel in later
versions of RedHat, I am wondering if there is any significant
performance advantage to compiling the source RPMs (SRPMS) for a
specific processor.  In other words, would it be worth the trouble to
install RH using slinky on, say, a Pentium Pro (i686) system, then
recompile the source RPMs, to create "i686" RPMs, then perform the
installation again, but use the RPMs compiled from source?

I am assuming that the rpm "--rebuild" option or rpmbuild, depending on
the version of rpm used, actually cares about and optimizes for a
particular Intel CPU family, depending on the CPU installed in the
computer.  If this is not the case (i.e., everything
is compiled using only the i386 instructions) then it is a moot point.

Hopefully someone more experienced than I knows if this is possible
and/or worth the effort.  I am interested in this question for the
non-profit that I am working with to convert some or all of their
donated machines to Linux.  It would be worth doing something like this
for multiple machines, if the performance improvement was noticeable.

Thanks
C David Rigby



_______________________________________________
Original home page of the RULE project: www.rule-project.org
Original Rule Development Site http://savannah.gnu.org/projects/rule/
Original RULE mailing list: Rule-list at nongnu.org, hosted at http://mail.nongnu.org/mailman/listinfo/rule-list