Re: Stealing a Great Idea from the 6600

Kent writes an interesting thesis on why OoO overtook IO wrt
scheduling.
One can add other scheduling effects::
a) change in latency on some FUs but not on others
b) change is register ports per instruction
c) branch prediction changes
d) cache timing wrt prefetch
Having gone through the transition (1-wide IO, 2-wide IO, 6-wide OoO)
the OoO machine was simply less complexity--or to say it a different way--the complexity was more orderly (and more easily verified).