3 Feb
2007
3 Feb
'07
8:53 p.m.
On 3 Feb 2007 at 22:38, Jim Leonard wrote:
Could you clarify which 808x CPUs in particular
you're referencing in
the above? There isn't a single case from 808x to 486 where that code
will beat rep movsb. Were you referring to Pentiums and higher?
Just so--when x86 went superscalar, there was a significant
difference in the execution rate of V-pipe instructions as compared
to the more complicated CISC-type ones such as MOVSB. Which is also
why the DEC/JNZ turns out ot faster than the LOOP.
I seem to recall a DDJ article around the time of the introduction of
the Pentium that warned about this.
Cheers,
Chuck