Concurrent round-robin-based dispatching schemes for clos-network switches

Eiji Oki, Zhigang Jing, Roberto Rojas-Cessa, H. Jonathan Chao

Research output: Contribution to journalArticle

Abstract

A Clos-network switch architecture is attractive because of its scalability. Previously proposed implementable dispatching schemes from the first stage to the second stage, such as random dispatching (RD), are not able to achieve high throughput unless the internal bandwidth is expanded. This paper presents two round-robin-based dispatching schemes to overcome the throughput limitation of the RD scheme. First, we introduce a concurrent round-robin dispatching (CRRD) scheme for the Clos-network switch. The CRRD scheme provides high switch throughput without expanding internal bandwidth. CRRD implementation is very simple because only simple round-robin arbiters are adopted. We show via simulation that CRRD achieves 100% throughput under uniform traffic. When the offered load reaches 1.0, the pointers of round-robin arbiters at the first- and second-stage modules are completely desynchronized and contention is avoided. Second, we introduce a concurrent master-slave round-robin dispatching (CMSD) scheme as an improved version of CRRD to make it more scalable. CMSD uses hierarchical round-robin arbitration. We show that CMSD preserves the advantages of CRRD, reduces the scheduling time by 30% or more when arbitration time is significant and has a dramatically reduced number of crosspoints of the interconnection wires between round-robin arbiters in the dispatching scheduler with a ratio of 1/√N, where N is the switch size. This makes CMSD easier to implement than CRRD when the switch size becomes large.

Original languageEnglish (US)
Pages (from-to)830-844
Number of pages15
JournalIEEE/ACM Transactions on Networking
Volume10
Issue number6
DOIs
StatePublished - Dec 2002

Fingerprint

Switches
Throughput
Bandwidth
Scalability
Scheduling
Wire

Keywords

  • Arbitration
  • Clos-network switch
  • Dispatching
  • Packet switch
  • Throughput

ASJC Scopus subject areas

  • Hardware and Architecture
  • Information Systems
  • Electrical and Electronic Engineering

Cite this

Concurrent round-robin-based dispatching schemes for clos-network switches. / Oki, Eiji; Jing, Zhigang; Rojas-Cessa, Roberto; Chao, H. Jonathan.

In: IEEE/ACM Transactions on Networking, Vol. 10, No. 6, 12.2002, p. 830-844.

Research output: Contribution to journalArticle

Oki, Eiji ; Jing, Zhigang ; Rojas-Cessa, Roberto ; Chao, H. Jonathan. / Concurrent round-robin-based dispatching schemes for clos-network switches. In: IEEE/ACM Transactions on Networking. 2002 ; Vol. 10, No. 6. pp. 830-844.
@article{d5c1ad6b20934ef1a2ba33a643458ded,
title = "Concurrent round-robin-based dispatching schemes for clos-network switches",
abstract = "A Clos-network switch architecture is attractive because of its scalability. Previously proposed implementable dispatching schemes from the first stage to the second stage, such as random dispatching (RD), are not able to achieve high throughput unless the internal bandwidth is expanded. This paper presents two round-robin-based dispatching schemes to overcome the throughput limitation of the RD scheme. First, we introduce a concurrent round-robin dispatching (CRRD) scheme for the Clos-network switch. The CRRD scheme provides high switch throughput without expanding internal bandwidth. CRRD implementation is very simple because only simple round-robin arbiters are adopted. We show via simulation that CRRD achieves 100{\%} throughput under uniform traffic. When the offered load reaches 1.0, the pointers of round-robin arbiters at the first- and second-stage modules are completely desynchronized and contention is avoided. Second, we introduce a concurrent master-slave round-robin dispatching (CMSD) scheme as an improved version of CRRD to make it more scalable. CMSD uses hierarchical round-robin arbitration. We show that CMSD preserves the advantages of CRRD, reduces the scheduling time by 30{\%} or more when arbitration time is significant and has a dramatically reduced number of crosspoints of the interconnection wires between round-robin arbiters in the dispatching scheduler with a ratio of 1/√N, where N is the switch size. This makes CMSD easier to implement than CRRD when the switch size becomes large.",
keywords = "Arbitration, Clos-network switch, Dispatching, Packet switch, Throughput",
author = "Eiji Oki and Zhigang Jing and Roberto Rojas-Cessa and Chao, {H. Jonathan}",
year = "2002",
month = "12",
doi = "10.1109/TNET.2002.804823",
language = "English (US)",
volume = "10",
pages = "830--844",
journal = "IEEE/ACM Transactions on Networking",
issn = "1063-6692",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Concurrent round-robin-based dispatching schemes for clos-network switches

AU - Oki, Eiji

AU - Jing, Zhigang

AU - Rojas-Cessa, Roberto

AU - Chao, H. Jonathan

PY - 2002/12

Y1 - 2002/12

N2 - A Clos-network switch architecture is attractive because of its scalability. Previously proposed implementable dispatching schemes from the first stage to the second stage, such as random dispatching (RD), are not able to achieve high throughput unless the internal bandwidth is expanded. This paper presents two round-robin-based dispatching schemes to overcome the throughput limitation of the RD scheme. First, we introduce a concurrent round-robin dispatching (CRRD) scheme for the Clos-network switch. The CRRD scheme provides high switch throughput without expanding internal bandwidth. CRRD implementation is very simple because only simple round-robin arbiters are adopted. We show via simulation that CRRD achieves 100% throughput under uniform traffic. When the offered load reaches 1.0, the pointers of round-robin arbiters at the first- and second-stage modules are completely desynchronized and contention is avoided. Second, we introduce a concurrent master-slave round-robin dispatching (CMSD) scheme as an improved version of CRRD to make it more scalable. CMSD uses hierarchical round-robin arbitration. We show that CMSD preserves the advantages of CRRD, reduces the scheduling time by 30% or more when arbitration time is significant and has a dramatically reduced number of crosspoints of the interconnection wires between round-robin arbiters in the dispatching scheduler with a ratio of 1/√N, where N is the switch size. This makes CMSD easier to implement than CRRD when the switch size becomes large.

AB - A Clos-network switch architecture is attractive because of its scalability. Previously proposed implementable dispatching schemes from the first stage to the second stage, such as random dispatching (RD), are not able to achieve high throughput unless the internal bandwidth is expanded. This paper presents two round-robin-based dispatching schemes to overcome the throughput limitation of the RD scheme. First, we introduce a concurrent round-robin dispatching (CRRD) scheme for the Clos-network switch. The CRRD scheme provides high switch throughput without expanding internal bandwidth. CRRD implementation is very simple because only simple round-robin arbiters are adopted. We show via simulation that CRRD achieves 100% throughput under uniform traffic. When the offered load reaches 1.0, the pointers of round-robin arbiters at the first- and second-stage modules are completely desynchronized and contention is avoided. Second, we introduce a concurrent master-slave round-robin dispatching (CMSD) scheme as an improved version of CRRD to make it more scalable. CMSD uses hierarchical round-robin arbitration. We show that CMSD preserves the advantages of CRRD, reduces the scheduling time by 30% or more when arbitration time is significant and has a dramatically reduced number of crosspoints of the interconnection wires between round-robin arbiters in the dispatching scheduler with a ratio of 1/√N, where N is the switch size. This makes CMSD easier to implement than CRRD when the switch size becomes large.

KW - Arbitration

KW - Clos-network switch

KW - Dispatching

KW - Packet switch

KW - Throughput

UR - http://www.scopus.com/inward/record.url?scp=0036952165&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036952165&partnerID=8YFLogxK

U2 - 10.1109/TNET.2002.804823

DO - 10.1109/TNET.2002.804823

M3 - Article

VL - 10

SP - 830

EP - 844

JO - IEEE/ACM Transactions on Networking

JF - IEEE/ACM Transactions on Networking

SN - 1063-6692

IS - 6

ER -