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]
Other format:	[Raw text]

Re: [patch] require sse3 for fisttp

From: Andrew Pinski <pinskia at physics dot uc dot edu>
To: Eric Christopher <echristo at apple dot com>
Cc: "gcc-patches at gcc dot gnu dot org Patches" <gcc-patches at gcc dot gnu dot org>
Date: Fri, 15 Sep 2006 22:42:29 -0700
Subject: Re: [patch] require sse3 for fisttp
References: <450B8A9E.7070103@apple.com> <450B8C52.6040106@apple.com> <1158384857.25064.16.camel@celery.andrew.com> <450B8D6F.50908@apple.com>

On Fri, 2006-09-15 at 22:36 -0700, Eric Christopher wrote:
> No, I didn't. I was wrong.

But I still don't understand why you think a new x87 instruction should
be treated like any other SSE instruction.  Maybe a new option should be
added for that.  -mno-sse will disable it even though you want to use
the new x87 instruction but not SSE at all. This is why RTH was saying
it should not be disabled by -mno-sse3.

Thanks,
Andrew Pinski

Follow-Ups:
- Re: [patch] require sse3 for fisttp
  - From: Eric Christopher

References:
- [patch] require sse3 for fisttp
  - From: Eric Christopher
- Re: [patch] require sse3 for fisttp
  - From: Eric Christopher
- Re: [patch] require sse3 for fisttp
  - From: Andrew Pinski
- Re: [patch] require sse3 for fisttp
  - From: Eric Christopher

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