PACMan:  Prefetch-Aware Cache Management for High Performance Caching

         Carole-Jean Wu*, Aamer Jaleel, Margaret Martonosi, 
                   Simon Steely Jr., and Joel Emer

Hardware prefetching and last-level cache (LLC) management are two 
independent mechanisms to mitigate the growing latency to memory. 
However, the interaction between LLC management and hardware prefetching 
has received very little attention. This paper characterizes the 
performance of state-of-the-art LLC management policies with and without 
prefetching. Although prefetching improves performance by fetching 
useful data in advance, it introduces performance variability for 
applications under cache management policies. This variability stems 
from the fact that current replacement policies treat prefetch and 
demand requests identically.

In order to provide better and more predictable performance, we propose 
Prefetch-Aware Cache Management (PACMan). PACMan dynamically estimates 
and mitigates the degree of prefetch-induced cache interference by 
modifying the cache insertion and hit promotion policies to treat demand 
and prefetch requests differently. Across a variety of emerging 
workloads, we show that PACMan eliminates the performance variability in 
state-of-the-art replacement policies under the influence of 
prefetching. In fact, PACMan improves performance consistently across 
all multimedia, games, server, and SPEC CPU2006 workloads by an average 
of 23.4% over the baseline LRU policy. For multiprogrammed workloads, on 
a 4-core CMP, PACMan improves performance by 18.2% on average. Finally, 
PACMan leverages the existing hardware of the underlying replacement 
policy and has negligible hardware overhead.


========================================================================
* This work is done during Carole-Jean's internship with Intel VSSAD.