Aggressive snoop reduction for synchronized producer-consumer communication in energy-efficient embedded multi-processors

Snoop-based cache coherence protocols are typically used when multiple processor cores share memory through a common bus. It is well known, however, that these coherence protocols introduce an excessive power overhead. To help alleviate this problem, we propose an application-driven customization technique where application knowledge regarding data sharing in producer-consumer relationships is used in order to aggressively eliminate unnecessary and predictable snoop-induced cache tag lookups even for references to shared data, thus, achieving significant power reduction with minimal hardware cost. Snoop-induced cache tag lookups for accesses to both shared and private data are eliminated when it is ensured that such lookups will not result in extra knowledge regarding the cache state in respect to the other caches and memories. The proposed methodology relies on the combined support from the compiler, the operating system, and the hardware architecture. Our experiments show average power reductions of more than 80% compared to a general-purpose snoop protocol.