|
Well, that's true as far as it goes, but it doesn't take into account (1) caching or (2) sequential streaming (I'm rusty on this stuff, so I don't even remember if that's the right term), both of which are significantly faster with sequential memory reads, which reads are more common in a defragmented environment.
Now my point is a qualitative one--the precise quantity of speed improvements will vary with the memory architecture and software being used, and may range from practically no difference to a very significant overall speed improvement.
|