Summary: Fast Cache for Your Text: Accelerating Exact
Pattern Matching with Feed-Forward Bloom
Iulian Moraru and David G. Andersen
School of Computer Science
Carnegie Mellon University
Pittsburgh, PA 15213
This paper presents an algorithm for exact pattern matching based on a new type of Bloom filter that
we call a feed-forward Bloom filter. Besides filtering the input corpus, a feed-forward Bloom filter
is also able to reduce the set of patterns needed for the exact matching phase. We show that this
technique, along with a CPU architecture aware design of the Bloom filter, can provide speedups
between 2× and 30×, and memory consumption reductions as large as 50× when compared with
grep, while the filtering speed can be as much as 5× higher than that of a normal Bloom filters.
This research was supported by grants from the National Science Foundation, Google, Network Appliance, Intel
Corporation and Carnegie Mellon Cylab.
Keywords: feed-forward Bloom filter, text scanning, cache efficient