Polyhedron benchmark results on AMD64

Diego Novillo dnovillo@redhat.com
Fri Feb 9 16:37:00 GMT 2007


François-Xavier Coudert wrote on 02/09/07 11:31:

> http://www.eleves.ens.fr/home/coudert/benchmark2.pdf

So, we seem to have quite a bit of trouble with aermod and even more 
with gas_dyn.

By chance, do you know if the aermod problem may be caused by the 
mem-ssa changes?  I have some fixing to do in that area.  gas_dyn is 
already mentioned in PR 30175, I wonder if this is also related to the 
SPEC 2006 regression in PR 30735.


Thanks.



More information about the Fortran mailing list