Isn't it clear, you linked the data.
You don't need to see the code for the data, if the FSB is a problem, then why if I double it it has no effect? you keep going back to this code thing, what is it in the code that makes you think you are going to find an answer?
So again, if per your hypothesis, the FSB is saturating at high resolutions ... why at high resolutions can I effectively double (or 1/2) the effective FSB BW and not change the result?







Bookmarks