Re: [OT] fpu IRQ x86-ism

From: Thomas E. Dodd /CSDC (ted@cypress.com)
Date: Mon Mar 06 2000 - 18:06:43 EST


nathan.zook@amd.com wrote:
>
> > -----Original Message-----
> > From: hpa@transmeta.com [mailto:hpa@transmeta.com]
> > By author: "B. James Phillippe" <bryan@terran.org>
> > >
> > > Greetings,
> > >
> > > Sorry for this somewhat OT question - I'll try to be brief.
> > I have always
> > > noticed that on x86 Linux boxes, IRQ 13 is for the FPU and
> > is always "1" (I
> > > assume this is from probing or testing at bootup). This
> > value never seems
> > > to change, so again I will assume that it is only used to signal FPU
> > > errors. There is no "fpu IRQ" on my Alpha, obviously it
> > has an FPU as
> > > well. Is it's existance on the PC just some lame legacy issue?
> > >
> >
> > Yup. It isn't even used to signal FPU errors on 486+ PCs.
> >
> > -hpa
>
> It is in comaptibility mode. Which means we have to support it.

So is there a way to free that IRQ for something else
on newer CPU like the K7 and P6?
Does anything in the Linux world depend on it?

        -Thomas

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Tue Mar 07 2000 - 21:00:21 EST