Hi Everyone,

I have been trying to compile Sage to run on my new system running Ubuntu Linux 
but have some questions about some of the default (automatically chosen) 
compile flags.  Now, Sage does compile correctly, but performance seems to 
suffer.

What tipped me off to this anomaly is when I compared the time to run 
"a=n(pi,10^7)" on my new Xeon 3.5ghz workstation to the time on my old 
workstation with a Core 2 Duo 3.0ghz.  I expected the Xeon to be considerably 
faster, but it turned out it was 40% slower!  Looking into the compile logs on 
my new workstation, I noticed some programs (like mpfr) were using (safe?) 
compile flags of "-mtune=k8 -march=k8".  On the old workstation it used the 
appropriate "-mtune=core2 -march=core2"  

I've tried globally setting the CFLAGS parameter, but it doesn't seem to make 
any difference in the compiled program.  Moreover, if I copy the compiled 
program (from the Core2 system to the new Xeon workstation) it runs 
considerably faster.  The new workstation is 50% faster than the Core2 system.

Is there any way to more appropriately set the compile flags to optimize the 
code for the Xeon workstation without compiling on the old machine then 
transferring over?

Thank you for your help!

Brian

-- 
You received this message because you are subscribed to the Google Groups 
"sage-support" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
To post to this group, send email to [email protected].
Visit this group at http://groups.google.com/group/sage-support.
For more options, visit https://groups.google.com/d/optout.

Reply via email to