PROJECT TITLE :

A High-Performance Double-Layer Counting Bloom Filter for Multicore Systems

ABSTRACT:

The snoopy-primarily based protocol is a widely used cache coherence mechanism for a symmetric multiprocessor (SMP) system. However, this broadcast-primarily based protocol blindly disseminates information sharing data across the system, and introduces several unnecessary information operations. This paper proposes a unique design of double-layer counting Bloom filter (DLCBF) to cut back the unnecessary knowledge lookups on the local cache and redundant knowledge transactions on the shared interconnection of an SMP system. By adding an further filtering layer, the DLCBF effectively exploits the info locality of applications. The two-layer hierarchy reduces the storage size of DLCBF by 18.75p.c, and achieves eighty one.99% and thirty one.thirty sixp.c better filtering rates when put next with a classic Bloom filter (BF) and original counting BF, respectively. When applied on the segmented shared bus of an SMP system, the DLCBF outperforms the previous work by 58p.c for In-filters and $1.86times $ for Out-filters. This paper also comprehensively explores the key style parameters of DLCBF, including the sizes of high-layer, bottom-layer, and multilayer design. The results show that enlarging the layer filters enhance the filtering rates of DLCBF, while adding an additional filter layer only provides slight benefit.