16 Jul
2014
16 Jul
'14
3:39 p.m.
Well, my goal is an 11/780. As others have pointed out, it appears to be
the most well documented. A side benefit might be that it provides a
convenient benchmark and launching point for further implementations since
it kind of is the distilled essence of what a VAX is.
As for your points about the 68k, I think you are being a little
optimistic. 5000 LEs is a lot. For example, if I am remembering my numbers
correctly, I believe the LEON3, which is a FOSS version of the SPARCv8,
uses something like 3500, and that has all kinds of incredibly complex
stuff to deal with. Moreover, an NVAX is more akin to a 68040 in terms of
complexity. In any case, my goal here is to get something running, not
create the world's best VAX. For this to be of any use whatsoever, it would
need to fit on boards that cost no more than $150 or so. I don't think that
the LEON3 can fit on the Spartan-6 LX9 that the Papilio Pro board uses.
Anyway, this certainly warrants more research. Thanks for the links.
On 16 July 2014 15:53, Peter Corlett <abuse at cabal.org.uk> wrote:
On Wed, Jul 16, 2014 at 02:11:26PM -0600, emanuel
stiebler wrote:
--
Thanks,
Kevin
On 2014-07-16 12:04, David Riley wrote:
> Making a wild-ass guess, with careful design, you could probably run
> something at least as fast as a KA650 (CVAX) on even a cheap modern
FPGA.
> But that's a wholly uninformed guess; it
could be either way faster or
way
> slower.
It should be possible to catch up to a NVAX, but
it probably is on
really modern low cost FPGAs.
Thar Interwebs tells me that the KA650 has roughly 2.5 VUPs, with a VUP
equvalent to the bog standard 1977-vintage VAX 11/780, and further that the
11/780 ran at 5MHz and the superficial design elements seem similar to a
CPU I
am more familiar with, the 68000. The VAX has paging hardware -- the
giveaway
is in the acronym! -- which makes it a bit more complex, but we're still
in the
same sort of ballpark.
So, here's a soft 68000: https://github.com/alfikpl/ao68000
The README.md notes that it has similar IPC to the 68000, is good for up to
about 82MHz, and uses roughly 5,000 LEs and 46kb of memory. I reckon this
means
you could get four VAX cores onto the relatively low-specced Cyclone IV
that
comes on the dirt cheap DE0-Nano FPGA dev kit.
The NVAX is 80-90MHz which is pleasingly similar to the maximum speed of
that
68000 core. Did you fancy a cluster of four NVAXen that runs on a chip that
costs something like $15 in bulk and can be powered by a lemon with a
couple of
nails banged into it?