------- Comment #18 from nbenoit at tuxfamily dot org 2009-12-17 09:34 ------- (In reply to comment #17) > (In reply to comment #16) > > Created an attachment (id=19332) --> (http://gcc.gnu.org/bugzilla/attachment.cgi?id=19332&action=view) [edit] > > Real fix > > > > Now, before I blow it again, would you be so kind to test this patch (on top > > of some recent trunk, doesn't have to be the newest one, you don't need to > > bootstrap) if it fixes the performance problem. For me it does now, I swear > > :-) > > > > Tested with trunk revision 155304, the regression is gone. > > * Intel Xeon E5320 (x86_64 arch but gcc machine is i686-pc-linux-gnu), with > -O1 > flag > GCC-4.4.2 7364 ms > GCC-trunk-r155286 7360 ms > > * Intel Xeon 5160 (x86_64 arch and gcc machine is x86_64-linux-gnu), with -O1 > flag > GCC-4.4.1 5968 ms > GCC-trunk-r155286 5963 ms >
Oups, copy-pasted the GCC versions for the timings. The correct versions are: * Intel Xeon E5320 (x86_64 arch but gcc machine is i686-pc-linux-gnu), with -O1 flag GCC-4.4.2 7364 ms GCC-trunk-r155304-patched 7360 ms * Intel Xeon 5160 (x86_64 arch and gcc machine is x86_64-linux-gnu), with -O1 flag GCC-4.4.1 5968 ms GCC-trunk-r155304-patched 5963 ms -- http://gcc.gnu.org/bugzilla/show_bug.cgi?id=42027
