On Wed, 27 Mar 2002, Todd Vierling wrote:

> On Wed, 27 Mar 2002, Frederick Bruckman wrote:
>
> : We do, on m68k. Actually, we seem to be currently building
> : for *only* 68020 -- "-m68020", and not "-m68020-40" as I said
> : before. The compiled code won't necessarily work on 68040...
>
> Well, it should work, so long as the trap-based emulation of the missing
> insns works.  If emulation doesn't work....  8-)

Of course. I forgot.

> : I believe that should be '|MASK_68040'?
>
> Yes, that is the correct way to switch to -m68040-20.  (-m68040 also adds
> MASK_68040_ONLY, which starts to use the new opcodes not on the '020.)
>
> The performance hit of *this* change shouldn't be earth-shattering, and I
> would support adding it by default.

OK, so here's a question for performance testers: Is SSHv2 really faster
with "-m68020-40" than with "-m68020" on boxes with m680{20,30}+m68881?
Or at least, no slower? I count 9 fmovecr's alone in libcrypto.a, let
alone the other m68881-only instructions, so if there is a difference,
"ssh" is where people are going to see it.

Frederick