AFEC: An analytical framework for evaluating cache performance in out-of-order processors

An Empirical Study for Multilevel Cache Associativity

“…It was observed that average throughput was increased by 29.9% for shared cache levels and 27.9% for private cache levels. Kecheng et al [11] discussed cache performance, specifically of out-of-order processors. They examine non-blocking cache, which merges different cache misses with the same cache-line address and overlaps multiple outstanding memory requests into one memory request to reduce the average cache miss penalty.…”