patch to improve x86_adjust_cost
Jan Hubicka
hubicka@atrey.karlin.mff.cuni.cz
Wed Apr 14 01:06:00 GMT 1999
> On Tue, Apr 13, 1999 at 04:00:48PM +0200, Jan Hubicka wrote:
> > * i386.c (x86_adjust_cost): Agi stall takes 1 cycle on Pentium, fst
> > requires value to be ready one extra cycle.
>
> > ! return 3;
> > --- 5594,5600 ----
> > ! return 2;
>
> How can I tell? Shouldn't this just be cost+1 then?
I think cost can be 0, and AGI stall have to be at least 2, so
it can be
if (!cost) return 2; else return cost+1;
but cost is always 0 or 1 for integer instructions or not?
Honza
>
>
> r~
--
OK. Lets make a signature file.
+-------------------------------------------------------------------------+
| Jan Hubicka (Jan Hubi\v{c}ka in TeX) hubicka@freesoft.cz |
| Czech free software foundation: http://www.freesoft.cz |
|AA project - the new way for computer graphics - http://www.ta.jcu.cz/aa |
| homepage: http://www.paru.cas.cz/~hubicka/ , games koules, Xonix, fast |
| fractal zoomer XaoS, index of Czech GNU/Linux/UN*X documentation etc. |
+-------------------------------------------------------------------------+
More information about the Gcc-patches
mailing list