There's memory bandwidth and there's memory transaction thruput

Joachim Durchholz joachim.durchholz at munich.netsurf.de
Sun Feb 14 12:32:44 UTC 1999


Some additions/corrections.

sqrmax at cvtci.com.ar wrote:
> 
> The 68K has much more registers than the intel processors.

And much more general ones. Most Intel registers must be freed for
certain operations (like you need EAX and EDX if you want to multiply).
So while modern flavors of Intel machines have lots of registers, you're
usually stuck with one or two (sometimes four) to select from.

> These last registers have limited arithmetic capabilities, especially
> the ones ending in S (for segment).

In fact the segment registers have no arithmetic capability at all. They
are just there to hold the "segment" part of addresses, so they are
essential for addressing and useless for anything else.

> I think the 68K with its variants lacks the raw speed of the Intels,
> although it's much more maneuverable.

Actually the 86K processors always had a release date somewhat behind
that of the same-generation Intel proessor, always had fewer bugs (if
any). Ironically, the 68K processors were always as fast as the Intel
processor of the *next* generation, so Motorola processors were faster
than their Intel counterparts.
However, 68Ks didn't run DOS, so Motorola lost that race, and sometime
after the 68030 they decided to leave the field to Intel and didn't tune
the clock speed to the levels that Intel uses today.

> I'd like to see intel processors with some of the 68K characteristics
> (like asynchronous IO for instance, why do you think intel machines
> need FIFOs everywhere?).

Hmm... that's a feature that I didn't see in my 68K specs. What do you
mean with this?

> I feel that Intel machines are like a non-turn-off-able rocket in a
> twisted road, [...] 68Ks are like a Ferrari, [...]

Nice image :))

Regards,
Joachim
-- 
Please don't send unsolicited ads.





More information about the Squeak-dev mailing list