On Mon, Mar 06, 2000 at 11:14:13AM -0800, B. James Phillippe wrote:
> 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?
Yep: back in the glorious AT times IBM did a lot of stupid things like
using interrupts Intel had reserved for future hardware for BIOS irqs
(IIRC Intel originally had reserved all IRQs below 32 for the PIC) and
decided to use IRQ 13 for floating point error reporting instead of
exception 16. We are obviously smarter than IBM because we use the
exception, but unfortunately IRQ 13 is hardwired to the FPU for
compatibility, so we can not use it for other purposes...
Yours,
Dominik Kubla
--
Looking for information about professional american football in Europe?
Then visit the independant "NFL@Europe Fan Site" at:
http://www-klinik.uni-mainz.de/staff/kubla/NFLE/
-
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 - 21:00:20 EST