Talk:Cache inclusion policy

In "comparison" section (https://en.wikipedia.org/w/index.php?title=Cache_inclusion_policy&action=edit&section=4) There appears to be an error: "the exclusive cache has more unique memory capacity, it uses more bandwidth since it suffers from a higher rate of filling of new blocks (equal to the rate of higher level cache's misses) as compared to NINE cache which is filled with a new block only when it suffers a miss"

This reasoning is incorrect -- an exclusive cache will have the lowest miss rate of all variants, because it has the most total capacity -- not all L1 misses result in a fill. Only L1 misses that also miss in L2 result in a fill. All other things being equal (IE same number of ways in all 3 cases), the exclusive will have the fewest cases where it misses in both L1 and L2, because miss rate depends _only_ on capacity when all other things are equal. — Preceding unsigned comment added by Seanhalle (talk • contribs) 00:43, 8 April 2018 (UTC)