Title | ||
---|---|---|
Way guard: a segmented counting bloom filter approach to reducing energy for set-associative caches |
Abstract | ||
---|---|---|
The design trend of caches in modern processors continues to increase their capacity with higher associativity to cope with large data footprint and take advantage of feature size shrink, which, unfortunately, also leads to higher energy consumption. This paper presents a technique using segmented counting Bloom filters called "Way Guard" to reduce the number of redundant way lookups in large set-associative caches to achieve dynamic energy savings. Our Way Guard mechanism only looks up an average of 25-30% of the cache ways and saved up to 65% of the L2 energy and up to 70% of the L1 cache energy. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1145/1594233.1594276 | ISLPED |
Keywords | Field | DocType |
design trend,large set-associative cache,l2 energy,higher associativity,large data footprint,cache way,l1 cache energy,guard mechanism,dynamic energy saving,bloom filter approach,higher energy consumption,bloom filter | Bloom filter,Associative property,CPU cache,Computer science,Cache,Parallel computing,Real-time computing,Footprint,Dynamic energy,Guard (information security),Computer hardware,Energy consumption | Conference |
Citations | PageRank | References |
19 | 0.79 | 18 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mrinmoy Ghosh | 1 | 367 | 22.39 |
Emre Özer | 2 | 204 | 18.20 |
Simon Ford | 3 | 19 | 0.79 |
Stuart Biles | 4 | 153 | 7.89 |
Hsien-Hsin Sean Lee | 5 | 1657 | 102.66 |