Proceedings.Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies
DOI: 10.1109/infcom.2002.1019301
|View full text |Cite
|
Sign up to set email alerts
|

Scalable IP lookup for programmable routers

Abstract: Continuing growth in optical link speeds places increasing demands on the performance of Internet routers, while deployment of embedded and distributed network services imposes new demands for flexibility and programmability. IP adress lookup has become a significant performance bottleneck for the highest performance routers. New commercial products utilize dedicated Content Addressable Memory (CAM) devides to achieve high lookup speeds. This paper describes an efficient, scalable lookup engine design, able to… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
32
0
1

Publication Types

Select...
4
2
2

Relationship

0
8

Authors

Journals

citations
Cited by 45 publications
(33 citation statements)
references
References 7 publications
0
32
0
1
Order By: Relevance
“…Accesses to SRAM and SDRAM can take a significant amount of time which can increase the overall processing cost of TSA. We have used a multibit trie implementation [22] to reduce the number of memory accesses necessary to traverse the anonymization tree. Our current prototype runs on an Intel IXP 2400 network processor [7] and requires 4 accesses to the anonymization data structures instead of 26.…”
Section: Methodsmentioning
confidence: 99%
“…Accesses to SRAM and SDRAM can take a significant amount of time which can increase the overall processing cost of TSA. We have used a multibit trie implementation [22] to reduce the number of memory accesses necessary to traverse the anonymization tree. Our current prototype runs on an Intel IXP 2400 network processor [7] and requires 4 accesses to the anonymization data structures instead of 26.…”
Section: Methodsmentioning
confidence: 99%
“…Previously published hardware implementations based on the Tree Bitmap algorithm are the reference implementation of [5] and the low-cost oriented solution of [9]. The former implementation achieves 25 million lookups per second using a four times replicated forwarding table stored in external DRAM and an Application-Specific Integrated Circuit (ASIC) to implement the required logic.…”
Section: Fig 2 Ip Lookup Table In Tree Bitmap Representationmentioning
confidence: 99%
“…In order to investigate whether and with what effort algorithmic IP lookup modules can be realized in hardware for future line speeds of 100 Gbps and beyond, we clearly focused on maximum throughput and resource efficiency, as opposed to other published Tree Bitmap implementations [5,9]. By processing all packets in a pipeline, our design effectively performs one IP address lookup in each clock cycle.…”
Section: Introductionmentioning
confidence: 99%
“…Although TCAMbased engines can retrieve IP lookup results in just one clock cycle, their throughput is limited by the relatively low speed of TCAMs. They are expensive and offer little flexibility for adapting to new addressing and routing protocols [4]. As shown in Table I, SRAM outperforms TCAM with respect to speed, density and power consumption.…”
Section: Introductionmentioning
confidence: 99%