Abstract

Modern processors contain large last level caches (LLCs) that consume substantial energy and area yet are impera-tive for high performance. Cache designs have improved dramatically by considering reference locality. Data val-ues are also a source of optimization. Compression and deduplication exploit data values to use cache storage more efficiently resulting in smaller caches without sac-rificing performance. In multi-megabyte LLCs, many identical or similar values may be cached across multi-ple blocks simultaneously. This redundancy effectively wastes cache capacity. We observe that a large fraction of cache values exhibit approximate similarity. More specifically, values across cache blocks are not identical but are similar. Coupled with approximate computing which observes that some applications can tolerate error or inexactness, we leverage approximate similarity to de-sign a novel LLC architecture: the Doppelgänger cache. The Doppelgänger cache associates the tags of multiple similar blocks with a single data array entry to reduce the amount of data stored. Our design achieves 1.55×, 2.55 × and 1.41 × reductions in LLC area, dynamic en-ergy and leakage energy without harming performance nor incurring high application error.