Re: Why VAX Was the Ultimate CISC and Not RISC

According to Anton Ertl <anton@mips.complang.tuwien.ac.at>:

I know ARM was pretty good but VAX
was fantastic since they sacrified everything else to compact instructions.

>
I don't think they did.  They spent encoding space on instructions
that were very rare, and AFAIK instructions can be encoded that do not
work (e.g., a consant as destination).  The major idea seems to have
been orthogonality, not compactness.

It certainly was orthogonal.  I was thinking that they had one-, two-, and four-
byte offset versions of all of the relative addressing modes, which made the
code smaller at the cost of forcing operands to be decoded one at a time since
you couldn't tell where the N+1st operand was until you'd looked at the Nth.

Nearly all opcodes were one byte other than the extended format floating point
instructions so it's hard to see how they could have made that much smaller
without making it a lot more complicated. On the other hand, we can compare it
to the S/360 instruction set which was fairly compact but a lot easier to
decode, e.g., you could tell from the high bits of the first opcode byte how
long each instruction was and where the operands were so you could decode the
rest and do address calculations in parallel.



--
Regards,
John Levine, johnl@taugh.com, Primary Perpetrator of "The Internet for Dummies",
Please consider the environment before reading this e-mail. https://jl.ly