This is the mail archive of the gcc@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: -mno-sse and -mno-sse2 broken on opteron?

From: Andreas Jaeger <aj at suse dot de>
To: Andrew Pinski <pinskia at physics dot uc dot edu>
Cc: Steve Kargl <sgk at troutmask dot apl dot washington dot edu>, gcc at gcc dot gnu dot org
Date: Thu, 06 Jan 2005 07:43:49 +0100
Subject: Re: -mno-sse and -mno-sse2 broken on opteron?
References: <20050105200441.GA5246@troutmask.apl.washington.edu><4DF7355D-5F55-11D9-A9D4-000A95D692F4@physics.uc.edu>

Andrew Pinski <pinskia@physics.uc.edu> writes:

> On Jan 5, 2005, at 3:04 PM, Steve Kargl wrote:
>
>> gfc -c -O -pipe -mfpmath=387 -mno-sse -mno-sse2 boxmuller.f90
>> boxmuller.f90: In function 'dbox_muller_array':
>> boxmuller.f90:70: error: SSE register return with SSE disabled
>> *** Error code 1
>>
>> troutmask:kargl[127] gfc --version
>> GNU Fortran 95 (GCC 4.0.0 20050104 (experimental))
>> Copyright (C) 2004 Free Software Foundation, Inc.
>
> Is this on x86_64, if so you cannot do that.

Let's say it this way: You can only do it if your application never
uses SSE registers - and a floating point return uses SSE registers
according to the ABI,

Andreas
-- 
 Andreas Jaeger, aj@suse.de, http://www.suse.de/~aj
  SUSE Linux Products GmbH, Maxfeldstr. 5, 90409 NÃrnberg, Germany
   GPG fingerprint = 93A3 365E CE47 B889 DF7F  FED1 389A 563C C272 A126

Attachment: pgp00000.pgp
Description: PGP signature

Follow-Ups:
- Re: -mno-sse and -mno-sse2 broken on opteron?
  - From: Steve Kargl

References:
- -mno-sse and -mno-sse2 broken on opteron?
  - From: Steve Kargl
- Re: -mno-sse and -mno-sse2 broken on opteron?
  - From: Andrew Pinski

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