This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]

Re: [patches] Re: SSE min/max instruction support


> On Sat, Feb 24, 2001 at 11:34:42PM +0100, Jan Hubicka wrote:
> > Don't seems to be ready for floats.
Just unrelated idea - it seems to me that we don't recognize many possibilities
for the smin/max and friends anyway.  This is because we try to emit
equivalent conditional moves but if the expander fails, we just bail out.
So I've started to play with idea, that probably emit_conditional_move should
be pretty aggresive and should try such special cases first - min,max,
store flags and similar before doing the conditional move expander.
Going futher, he should try to use setcc if it fails - i386 
emit_conditonal_move contains lots of relevant code - what do you think
about idea of moving it to generic part of emit_conditional_mvoe too?

Honza


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]