Proceedings of the 2006 International Conference on Compilers, Architecture and Synthesis for Embedded Systems 2006
DOI: 10.1145/1176760.1176783
|View full text |Cite
|
Sign up to set email alerts
|

Reducing energy of virtual cache synonym lookup using bloom filters

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2007
2007
2024
2024

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 14 publications
(3 citation statements)
references
References 31 publications
0
3
0
Order By: Relevance
“…Woo et al [37] proposed using bloom filter to hold synonym addresses to save L1 cache lookup energy by allowing lower associativity. Ashok et al [1] proposed compiler directed static speculative address translation and cache access support to save energy.…”
Section: L1mentioning
confidence: 99%
“…Woo et al [37] proposed using bloom filter to hold synonym addresses to save L1 cache lookup energy by allowing lower associativity. Ashok et al [1] proposed compiler directed static speculative address translation and cache access support to save energy.…”
Section: L1mentioning
confidence: 99%
“…If virtual addresses only are used to access the cache, the resulting cache is referred to as virtually indexed and virtually tagged. The benefit of this cache architecture is that there is no need for address translation when accessing the cache, which results in fast access time and, even more importantly for embedded processors, low power consumption [Qiu and Dubois 2001;Kim et al 1995;Woo et al 2006]. Virtually indexed and tagged caches, however, exhibit severe drawbacks, namely cache aliasing and synonyms [Cekleov and Dubois 1997;Woo et al 2006].…”
Section: Zhou and P Petrovmentioning
confidence: 99%
“…This count or frequency is used to assign a priority value to each missing block. This is a novel application of counting Bloom filters, previously employed for implementing hierarchical store queues [1], coarse-grain coherence [11], snoop filters [12,19], prefetching and data speculation [13], low-energy synonym lookup [20], etc. A low power counting Bloom filter was proposed in [17].…”
Section: Scavenger Architecturementioning
confidence: 99%