Question: If the processor accesses A many times (I'm assuming B is not accessed), shouldn't B be the one evicted by the L1 Cache in this example? (if the cache is using an LRU policy) But for the L2 Cache since A was the least recently used address (the L1 hits avoided the need for L2 checks), shouldn't A be evicted instead?
Question: If the processor accesses A many times (I'm assuming B is not accessed), shouldn't B be the one evicted by the L1 Cache in this example? (if the cache is using an LRU policy) But for the L2 Cache since A was the least recently used address (the L1 hits avoided the need for L2 checks), shouldn't A be evicted instead?
This comment was marked helpful 0 times.
@markwongsk: Yes. Good catch. Thanks.
This comment was marked helpful 0 times.