Quote - ... The comparison that I did was at CPU level, the execution speed of the instruction assuming all the data you need is in level 1 cache.

 

Hm, but you normally cannot the determine the speed of the processor by measuring the speed of a single instruction. If 64- and 32-bit processors were the same in every aspect, except for the number of their registers, the 64 would still be faster on average (for any real program). When your measurements showed that both are the same, you either have discovered an effect you have not considered, or you have measured something that does not model the "speed" of a processor very well (that is my opinion, at least: "never believe computer benchmarks on the internet, unless they give good explanation" :-).