8 Mar
2011
8 Mar
'11
2:19 p.m.
Tony Duell wrote:
Whatever instructions were exposed to a programmer of the machine, I suppose.
I'm trying to build up a rough idea of how common is was though in systems
as supplied by a vendor - so I think that user-written microcode doesn't
count as such (but it's still nice to hear of systems where the user could
have done it if they wanted and achieved better performance than via
software routines).
background: I'm revisiting a homebrew microcoded CPU that I started
thinking about a few years ago (with the intention of making it
predominantly from LS-TTL if I can get enough parts together). I hadn't
considered hardware multiply or divide before (the intention was just to
have library routines in software), but if it was relatively common on
systems between the mid-70s and early-80s then maybe I'll include
something. Simple shift-add multiply with unsigned integers is simple
enough, but I'm thinking that if I do it at all it'd be nice for it to work
with signed integers, too, so I've got some head-scratching to do :-)
cheers
Jules
Tony Duell
wrote:
What do you mean by 'instruction set'. In particular, what do you do
about machines (PERQ, for example) that load their microocde at power-on
and thus don't have a fixed machine code instrcution set. What do you mean by 'hardware' multiply
and divide? A number of machines,
I suspect the 6809 is amongst them, had no particualrl hardware for
multiply or divide, but they did have multiply and maybe divide
instrucitons in the instruction setc. These instrucitons were implemented
by microcode using the normal registers and ALU. Does that count?
Yes, anything
that includes a dedicated multiply or divide instruction as part
of the instruction set; I suspect a lot of the early implementations fall into
the "simple shift-add" that I mentioned due to the lack/cost of silicon.