🚀 go-pugleaf

On 13 Dec 92 05:00:19 GMT, johnl@iecc.cambridge.ma.us (John R. Levine) said:

(somebody)> NeXTStep is said to not run on the Cyrix 486 chips because
(somebody)> "they are not real 486's".  No one has come up with a
(somebody)> reliable reason _why_ NeXT doesn't think they are "real
(somebody)> 486's" or why NeXTStep won't run on them.

The most probable reason seen so far is that there are some small
supervisor state differences between the Cyrix and the Intel part.  If
so, I would venture that it is about enabling (and then flushing at the
right moment) the cache on the Cyrix.  It is not necessary to do so, but
if one does not (and one has to do so on most old 386-like motherboards
on which the Cyrix part is usually mounted) then performance is little
better than with a 386.

johnl> I don't have any real data, but I expect the problem is that the
johnl> Cyrix chip doesn't have a floating point unit.

No, this cannot be the reason. As a rule the Cyrix 486DLC CPU chip is
sold with the Cyrix Fasmath (a 387) coprocessor, the combo being touted
quite reasonably as a 486DX equivalent.

Moreover NeXTStep is said to run on the 486SX Intel chips, and those
don't have a corprocessor either.

FUD, FUD. Ah Intel, Intel. :-)
--
Piercarlo Grandi, Dept of CS, PC/UW@Aberystwyth <pcg@aber.ac.uk>
  E l'italiano cantava, cantava. E le sue disperate invocazioni giunsero
  alle orecchie del suo divino protettore, il dio della barzelletta