Memory subsystems in high-end routers

Feng Wang; Mounir Hamdi

doi:10.1109/MM.2009.45

Memory subsystems in high-end routers

Feng Wang^*, Mounir Hamdi

^*Corresponding author for this work

Hong Kong University of Science and Technology

Research output: Contribution to journal › Article › peer-review

4 Citations (Scopus)

Abstract

As Internet routers scale to support next-generation networks, their memory subsystems must also scale. Several solutions combine static RAM and dynamic RAM buffering but still have major scaling limitations. Using a parallel architecture and distributed memory-management algorithms with hybrid SRAM/DRAM improves buffering performance. The parallel hybrid SRAM/DRAM memory system is also work conserving, which is particularly important under light traffic conditions.

Original language	English
Pages (from-to)	52-61
Number of pages	10
Journal	IEEE Micro
Volume	29
Issue number	3
DOIs	https://doi.org/10.1109/MM.2009.45
Publication status	Published - 2009
Externally published	Yes

Keywords

Bandwidth
Buffer storage
Data mining
Delay
Parallel distributed memory management
Per-flow queues
Probability density function
Random access memory
Routing protocols
SRAM/DRAM

Access to Document

10.1109/MM.2009.45

Cite this

@article{220817f5c0564cfa9428e882657aa6dd,

title = "Memory subsystems in high-end routers",

abstract = "As Internet routers scale to support next-generation networks, their memory subsystems must also scale. Several solutions combine static RAM and dynamic RAM buffering but still have major scaling limitations. Using a parallel architecture and distributed memory-management algorithms with hybrid SRAM/DRAM improves buffering performance. The parallel hybrid SRAM/DRAM memory system is also work conserving, which is particularly important under light traffic conditions.",

keywords = "Bandwidth, Buffer storage, Data mining, Delay, Parallel distributed memory management, Per-flow queues, Probability density function, Random access memory, Routing protocols, SRAM/DRAM",

author = "Feng Wang and Mounir Hamdi",

year = "2009",

doi = "10.1109/MM.2009.45",

language = "English",

volume = "29",

pages = "52--61",

journal = "IEEE Micro",

issn = "0272-1732",

publisher = "IEEE Computer Society",

number = "3",

}

TY - JOUR

T1 - Memory subsystems in high-end routers

AU - Wang, Feng

AU - Hamdi, Mounir

PY - 2009

Y1 - 2009

N2 - As Internet routers scale to support next-generation networks, their memory subsystems must also scale. Several solutions combine static RAM and dynamic RAM buffering but still have major scaling limitations. Using a parallel architecture and distributed memory-management algorithms with hybrid SRAM/DRAM improves buffering performance. The parallel hybrid SRAM/DRAM memory system is also work conserving, which is particularly important under light traffic conditions.

AB - As Internet routers scale to support next-generation networks, their memory subsystems must also scale. Several solutions combine static RAM and dynamic RAM buffering but still have major scaling limitations. Using a parallel architecture and distributed memory-management algorithms with hybrid SRAM/DRAM improves buffering performance. The parallel hybrid SRAM/DRAM memory system is also work conserving, which is particularly important under light traffic conditions.

KW - Bandwidth

KW - Buffer storage

KW - Data mining

KW - Delay

KW - Parallel distributed memory management

KW - Per-flow queues

KW - Probability density function

KW - Random access memory

KW - Routing protocols

KW - SRAM/DRAM

UR - http://www.scopus.com/inward/record.url?scp=67650489174&partnerID=8YFLogxK

U2 - 10.1109/MM.2009.45

DO - 10.1109/MM.2009.45

M3 - Article

AN - SCOPUS:67650489174

SN - 0272-1732

VL - 29

SP - 52

EP - 61

JO - IEEE Micro

JF - IEEE Micro

IS - 3

ER -

Memory subsystems in high-end routers

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this