>That's fair enough as far as it goes, but would I be completely wrong in
>thinking that when the FPU gives up on an instruction, it will look to
>software exactly as if the instruction was never even started and the FPEM
>will do it's job normally on it?
Very possibly, but the support code still needs to be taught how to figure out
which instruction was bounced. Since the FPA is asynchronous you can't
just use the ARM's program counter.
It probably wouldn't be that hard for somebody with an FPA to write the code
to do this, it's just that the hardware isn't common enough for anyone to have
bothered yet. If 7500FE machines become popular then that might be more of an
incentive to do the work.
p.
unsubscribe: body of `unsubscribe linux-arm' to [EMAIL PROTECTED]
