Serious performance regression -- some tree optimizer questions

[Steven Bosscher]

On Friday 17 December 2004 22:24, Ulrich Weigand wrote:
> Hello,
>
> we've started to do some performance analysis of current GCC mainline
> on zSeries, and while in general results are promising, we've found a
> couple of serious performance regressions.  The most extreme one was
> the SPECfp2000 test case mgrid -- on s390x optimized for z990, this
> test case takes about *twice* the run time with current mainline as
> it did with GCC 3.4 ...

When I last looked at mgrid for AMD64, I found -fno-tree-pre to
be very helpful.

Gr.
Steven