Do we need this junk?

[Nikolas Britton]

On 4/6/07, Ed Schouten <ed at fxq.nl> wrote:
> * Nikolas Britton <nikolas.britton at gmail.com> wrote:
> > The legacy bits don't upset me, what upsets me is sacrificing
> > performance so we can  support a minority of legacy systems. IIRC? we
> > could recode the Kernel for SSE2 math if the processor was guaranteed
> > to have that SSE2. SSE2 adds 214 new instructions to the existing x86
> > instruction set.
>
> But SSE2 isn't even used in kernel space, not even on AMD64. As far as I
> can see, the only exception I can see is pagezero. Just take a look at
> src/sys/conf/kern.mk. If it's not even possible to use SSE2 in
> kernelspace on amd64, why would it be possible to do so on i386?
>

Doesn't Apple use SSE2/3 in the kernel? IIRC Mac OS X (Darwin) running
on a white box PC won't even boot if it's missing.