This is the mail archive of the
mailing list for the GCC project.
Re: -mno-sse and -mno-sse2 broken on opteron?
- From: Andi Kleen <ak at muc dot de>
- To: Marcin Dalecki <martin at dalecki dot de>
- Cc: <joel dot sherrill at OARcorp dot com>,"'Andrew Pinski'" <pinskia at physics dot uc dot edu>, <gcc at gcc dot gnu dot org>,"'Richard Henderson'" <rth at redhat dot com>,"'Steve Kargl'" <sgk at troutmask dot apl dot washington dot edu>,"'Andreas Jaeger'" <aj at suse dot de>
- Date: Fri, 07 Jan 2005 17:58:34 +0100
- Subject: Re: -mno-sse and -mno-sse2 broken on opteron?
- References: <NUTMEGndzW1D4WzT2XJ00000d67@NUTMEG.CAM.ARTIMI.COM><B64E3294-60CC-11D9-A4C0-000A95E3BCE4@dalecki.de>
Marcin Dalecki <email@example.com> writes:
> As far as I can see the linux-2.6 kernel already does the lazy trick
> on the i387 registers for AMD64.
Hmm? It does lazy FP saving, but always for both SSE and x87 registers
together. There are plans to split it, but it hasn't been done so far.
-Andi (who won't write more on this because it's clearly off-topic)