Re: Floating point on IBM PPC405 (266MHz)

From: Marius Groeger (bitbucket_at_invalid-domain-see-sig.nil)
Date: 09/19/03


Date: 19 Sep 2003 08:43:59 GMT

On Fri, 19 Sep 2003 06:44:39 GMT,
  Juergen Beisert <NOSPAMjbeisert@netscape.net> wrote:
> On 18 Sep 2003 06:56:34 -0700, s_popov@prosyst.bg (Alexander Popov)
> wrote:
>
> >Is anyone out there using linux on a board with IBM PPC405 (266MHz) CPU?
>
> Yes. PPC405GPr.
>
> >Are there any serious performance problems with the floating point
> >operations?
>
> Yes, because the PPC405 has no floating point support.

In any case, you should make sure you are using a proper toolchain that does
not generate floating point instructions (ie. implies a -fsoft-float). These
can be handled by the kernel's math emulation, but this will slow things
down even more.

Regards,
Marius.

--
Marius Groeger        SYSGO Real-Time Solutions GmbH    www.sysgo.de
Software Engineering  Embedded and Real-Time Software   www.osek.de
mgroeger @ sysgo de   Germany                           www.elinos.com


Relevant Pages

  • Re: Floating point on IBM PPC405 (266MHz)
    ... I'm asking because I have QNX running on this baby and it's extreamly slow ... (I'm trying to convice our client to switch to linux)... ... the integer ops are 50% faster and the floating point is 150 TIMES faster!!! ... >>Are there any serious performance problems with the floating point operations? ...
    (comp.os.linux.embedded)
  • Floating point on IBM PPC405 (266MHz)
    ... Is anyone out there using linux on a board with IBM PPC405 CPU? ... Are there any serious performance problems with the floating point operations? ... Best Regards, ...
    (comp.os.linux.embedded)