Parallel Processing in Network Processor Architectures

Rainer Hagenau; Carsten Albrecht; Erik Maehle; Andreas C. Döring

doi:10.1524/itit.47.3.123.65608

Parallel Processing in Network Processor Architectures

Rainer Hagenau, Carsten Albrecht, Erik Maehle, Andreas C. Döring

Institute of Computer Engineering

IBM Zurich Research Laboratory

3 Citations (Scopus)

Abstract

Parallel processing is well established in high-performance computing. Currently, network processors as new emerging, special-purpose processors are targeted at the exploitation of parallelism to meet the requirements in data-plane processing with wire-speed. The achievable level of parallelism is determined by decisions in the architecture design and by the characteristics of the data-plane applications executed. We discuss two basic approaches in parallel processing, namely pipelining and concurrency, which establish basic models for parallel network processor organization. The features and constraints of these models are studied. Using this background some existing network processor architectures are reviewed and characterized regarding their potential in parallel data-plane processing.

Translated title of the contribution	Parallelverarbeitung in Netzwerkprozessorarchitekturen
Original language	English
Journal	it - Information Technology
Volume	47
Issue number	3
Pages (from-to)	123-131
Number of pages	9
ISSN	2196-7032
DOIs	https://doi.org/10.1524/itit.47.3.123.65608
Publication status	Published - 25.09.2005

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.1524/itit.47.3.123.65608

Cite this

@article{22685d237fa949b0b9d39e5fcd0d176e,

title = "Parallel Processing in Network Processor Architectures",

abstract = "Parallel processing is well established in high-performance computing. Currently, network processors as new emerging, special-purpose processors are targeted at the exploitation of parallelism to meet the requirements in data-plane processing with wire-speed. The achievable level of parallelism is determined by decisions in the architecture design and by the characteristics of the data-plane applications executed. We discuss two basic approaches in parallel processing, namely pipelining and concurrency, which establish basic models for parallel network processor organization. The features and constraints of these models are studied. Using this background some existing network processor architectures are reviewed and characterized regarding their potential in parallel data-plane processing. ",

author = "Rainer Hagenau and Carsten Albrecht and Erik Maehle and D{\"o}ring, \{Andreas C.\}",

year = "2005",

month = sep,

day = "25",

doi = "10.1524/itit.47.3.123.65608",

language = "English",

volume = "47",

pages = "123--131",

journal = "it - Information Technology",

issn = "2196-7032",

publisher = "Walter de Gruyter GmbH",

number = "3",

}

TY - JOUR

T1 - Parallel Processing in Network Processor Architectures

AU - Hagenau, Rainer

AU - Albrecht, Carsten

AU - Maehle, Erik

AU - Döring, Andreas C.

PY - 2005/9/25

Y1 - 2005/9/25

N2 - Parallel processing is well established in high-performance computing. Currently, network processors as new emerging, special-purpose processors are targeted at the exploitation of parallelism to meet the requirements in data-plane processing with wire-speed. The achievable level of parallelism is determined by decisions in the architecture design and by the characteristics of the data-plane applications executed. We discuss two basic approaches in parallel processing, namely pipelining and concurrency, which establish basic models for parallel network processor organization. The features and constraints of these models are studied. Using this background some existing network processor architectures are reviewed and characterized regarding their potential in parallel data-plane processing.

AB - Parallel processing is well established in high-performance computing. Currently, network processors as new emerging, special-purpose processors are targeted at the exploitation of parallelism to meet the requirements in data-plane processing with wire-speed. The achievable level of parallelism is determined by decisions in the architecture design and by the characteristics of the data-plane applications executed. We discuss two basic approaches in parallel processing, namely pipelining and concurrency, which establish basic models for parallel network processor organization. The features and constraints of these models are studied. Using this background some existing network processor architectures are reviewed and characterized regarding their potential in parallel data-plane processing.

UR - https://www.semanticscholar.org/paper/Parallel-Processing-in-Network-Processor-in-Hagenau-Albrecht/aba1b60862a46ed8f26e18439429a91d50959189

U2 - 10.1524/itit.47.3.123.65608

DO - 10.1524/itit.47.3.123.65608

M3 - Journal articles

SN - 2196-7032

VL - 47

SP - 123

EP - 131

JO - it - Information Technology

JF - it - Information Technology

IS - 3

ER -

Parallel Processing in Network Processor Architectures

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this