16 Jul
2014
16 Jul
'14
2:04 p.m.
On Jul 16, 2014, at 1:49 PM, Kevin Keith <krfkeith at gmail.com> wrote:
Basically, my question is what are the major obstacles
(besides the breadth
of the project) to implementing the VAX in an FPGA, as compared to any
other ISA?
I would think breadth alone is enough. Not so much to make it infeasible,
but enough to take a long time to get there. VAX is an extremely complex
instruction set, but a lot of it is accomplished through microcode. The
CPU design is actually pretty cleanly divided up into boxes that fulfill
various architectural features; I'd suggest reading the Digital Technical
Journal articles on the design and implementation of NVAX as a primer.
If you're interested in starting a project, I'm somewhat interested in
contributing, as it's something I've had on my mind for a long time. I
don't have a lot of free time these days, but I may in the not-too-distant
future.
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.
- Dave