On 5/7/2010 12:34 AM, Dave McGuire wrote:
Well you've got to admit, it does depend on
how you look at it. The 8088
has an 8-bit data bus and it does two bus cycles to move a 16-bit value.
You know...just like an 8080. ;)
Well, the 8080 can't do a 16-bit by 16-bit multiply to get a 32-bit
product, so that's an obvious difference.
Actually just about any processor can multiply 2 arbitrarily-long
numbers. You just ahve to write a subroutine for it.
But I assume you mean 'as a single machine instruction'. So the bit-width
of a processor is the size of the multiplicand or multiplier reigster?
WHat if there are difference sizes? And what about processors with no
multiply instruciton? Do you consider the Z80 to be a 0-bit procressor?
-tony