SOS: A Software-Oriented Distributed Shared Cache Management Approach for Chip Multiprocessors

TL;DR: SOS, the authors' software-oriented distributed shared cache management approach, infers a program’s data affinity hints through a novel machine learning based analysis of its L2 cache access behavior, and achieves an average speedup of 10% and up to 23% over the shared cache scheme.

Abstract: This paper proposes a new software-oriented approach for managing the distributed shared L2 caches of a chip multiprocessor (CMP) for latency-oriented multithreaded applications. The conventional shared cache scheme loses performance due to the blind distribution of data predominantly accessed by a single thread. SOS, our software-oriented distributed shared cache management approach, infers a program’s data affinity hints through a novel machine learning based analysis of its L2 cache access behavior. The OS utilizes the hints to guide proper data placement in the L2 cache with page coloring. The derived hints are independent of the program input and can be used for multiple runs. By off-loading the cache management task onto software, SOS deviates substantially from previously proposed hardwarebased strategies and opens up a new opportunity for the CMP cache optimization. Our experimental results demonstrate that SOS is very effective in reducing the number of remote cache accesses. By using the hints for guiding page coloring alone, SOS achieves an average speedup of 10% and up to 23% over the shared cache scheme. When hints are used to direct data replication, SOS secures an additional performance gain of 9%, performing 19% better than the shared cache scheme on average.