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: x86_64 merger part 39 - vardic functions..

To: Richard Henderson <rth at redhat dot com>, Jan Hubicka <jh at suse dot cz>, gcc-patches at gcc dot gnu dot org, patches at x86-64 dot org
Subject: Re: x86_64 merger part 39 - vardic functions..
From: Jan Hubicka <jh at suse dot cz>
Date: Sat, 22 Sep 2001 17:05:28 +0200
References: <20010920144930.A32741@atrey.karlin.mff.cuni.cz> <20010920145716.D884@redhat.com> <20010921132257.B5940@atrey.karlin.mff.cuni.cz> <20010921131303.C1816@redhat.com>

> In that case, you might consider a simple predicted-taken conditional
> branch across all of the SSE stores for the normal case of only integer
> arguments.  But I'll leave that decision up to you.

This is something I want to try once the hardware is ready...
(originaly we had 16 SSE arguments, that made the computed jump more meningfull)
> 
> The patch is ok.
Thanks

Honza

> 
> 
> r~

References:
- x86_64 merger part 39 - vardic functions..
  - From: Jan Hubicka
- Re: x86_64 merger part 39 - vardic functions..
  - From: Richard Henderson
- Re: x86_64 merger part 39 - vardic functions..
  - From: Jan Hubicka
- Re: x86_64 merger part 39 - vardic functions..
  - From: Richard Henderson

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