13 Jan
2017
13 Jan
'17
6:15 p.m.
On 01/13/2017 06:42 PM, Antonio Carlini wrote:
On 14/01/17 00:06, Jon Elson wrote:
Right, I am misremembering. The 780 and the KA650 had caches.
The KA630 did real well, then, without a cache. So, I never
understood why the Nat Semi 32016 performed so poorly. I
did build a multiprocessor using the 32016 WITHOUT the MMU,
and it looked to be around 300KIPS (roughly 1/3 of a VAX
780). So, maybe it was the MMU that really hurt the
performance.
Jon
I eventually got a MicroVAX-II to replace it,
and, yes,
that DID have a cache to speed up the memory, but it was
quite a difference.
I'm reasonably sure that the uVAX II did not have a memory
cache. It did have a translation lookaside buffer and some
(small) amount
of instruction pre-fetch though.