I think it is only fair that someone quantify the performance hit
that
K7 and 32bit K8 users can expect versus the improvement that P4 users
will see before this is implemented.
The biggest change is NOT using a few forms of instructions (INC/DEC
hurt p4's while ADD/SUB by one are fast), AMD cpus seem to not care
really which form is chosen, it seens AMD optimizes in the cpu beyond
this level. You'll be *really* hard pressed to find (artificial)
examples where this would slow down AMD cpus even 0.1%....