Fat H-Tree: A cost-efficient tree-based on-chip network

Hiroki Matsutani, Michihiro Koibuchi, Yutaka Yamada, D. Frank Hsu, Hideharu Amano

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

The topological explorations of on-chip networks are important for efficiently using their enormous wire resources for low-latency and high-throughput communications using a modest silicon budget. In this paper, we propose a novel tree-based interconnection network called Fat H-Tree that meets these requirements. A Fat H-Tree provides a torus structure by combining two folded H-Tree networks and is an attractive alternative to tree-based networks such as the Fat Trees in a microarchitecture domain. We introduce its chip layout schemes based on a folding technique for 2D and 3D ICs. Three deadlock-free routing schemes are proposed for Fat H-Tree. We evaluate the performance of Fat H-Tree and other tree-based networks using real application traces. In addition, the network logic area, wire resource, and energy consumption of Fat H-Tree are compared with other topologies, based on a typical implementation of on-chip routers synthesized with a 90-nm standard cell library. The results show that 1) a Fat H-Tree outperforms a Fat Tree with two upward and four downward connections in terms of the throughput and average hop count, 2) a Fat H-Tree requires 19.8 percent-27.8 percent smaller network logic area than the Fat Tree, 3) a Fat H-Tree consumes slightly less energy than the Fat Tree does, and 4) a Fat H-Tree uses slightly more wire resources than the Fat Tree, but the current process technology can provide sufficient wire resources for implementing Fat-H-Tree-based on-chip networks.

Original languageEnglish
Pages (from-to)1126-1141
Number of pages16
JournalIEEE Transactions on Parallel and Distributed Systems
Volume20
Issue number8
DOIs
Publication statusPublished - 2009

Fingerprint

Oils and fats
Costs
Wire
Network-on-chip
Throughput
Routers
Energy utilization

Keywords

  • Interconnection networks
  • Network topology
  • On-chip networks
  • Routing algorithm
  • Tree

ASJC Scopus subject areas

  • Hardware and Architecture
  • Signal Processing
  • Computational Theory and Mathematics

Cite this

Fat H-Tree : A cost-efficient tree-based on-chip network. / Matsutani, Hiroki; Koibuchi, Michihiro; Yamada, Yutaka; Hsu, D. Frank; Amano, Hideharu.

In: IEEE Transactions on Parallel and Distributed Systems, Vol. 20, No. 8, 2009, p. 1126-1141.

Research output: Contribution to journalArticle

Matsutani, Hiroki ; Koibuchi, Michihiro ; Yamada, Yutaka ; Hsu, D. Frank ; Amano, Hideharu. / Fat H-Tree : A cost-efficient tree-based on-chip network. In: IEEE Transactions on Parallel and Distributed Systems. 2009 ; Vol. 20, No. 8. pp. 1126-1141.
@article{b6dba722adea48c5966631efa5c657cc,
title = "Fat H-Tree: A cost-efficient tree-based on-chip network",
abstract = "The topological explorations of on-chip networks are important for efficiently using their enormous wire resources for low-latency and high-throughput communications using a modest silicon budget. In this paper, we propose a novel tree-based interconnection network called Fat H-Tree that meets these requirements. A Fat H-Tree provides a torus structure by combining two folded H-Tree networks and is an attractive alternative to tree-based networks such as the Fat Trees in a microarchitecture domain. We introduce its chip layout schemes based on a folding technique for 2D and 3D ICs. Three deadlock-free routing schemes are proposed for Fat H-Tree. We evaluate the performance of Fat H-Tree and other tree-based networks using real application traces. In addition, the network logic area, wire resource, and energy consumption of Fat H-Tree are compared with other topologies, based on a typical implementation of on-chip routers synthesized with a 90-nm standard cell library. The results show that 1) a Fat H-Tree outperforms a Fat Tree with two upward and four downward connections in terms of the throughput and average hop count, 2) a Fat H-Tree requires 19.8 percent-27.8 percent smaller network logic area than the Fat Tree, 3) a Fat H-Tree consumes slightly less energy than the Fat Tree does, and 4) a Fat H-Tree uses slightly more wire resources than the Fat Tree, but the current process technology can provide sufficient wire resources for implementing Fat-H-Tree-based on-chip networks.",
keywords = "Interconnection networks, Network topology, On-chip networks, Routing algorithm, Tree",
author = "Hiroki Matsutani and Michihiro Koibuchi and Yutaka Yamada and Hsu, {D. Frank} and Hideharu Amano",
year = "2009",
doi = "10.1109/TPDS.2008.233",
language = "English",
volume = "20",
pages = "1126--1141",
journal = "IEEE Transactions on Parallel and Distributed Systems",
issn = "1045-9219",
publisher = "IEEE Computer Society",
number = "8",

}

TY - JOUR

T1 - Fat H-Tree

T2 - A cost-efficient tree-based on-chip network

AU - Matsutani, Hiroki

AU - Koibuchi, Michihiro

AU - Yamada, Yutaka

AU - Hsu, D. Frank

AU - Amano, Hideharu

PY - 2009

Y1 - 2009

N2 - The topological explorations of on-chip networks are important for efficiently using their enormous wire resources for low-latency and high-throughput communications using a modest silicon budget. In this paper, we propose a novel tree-based interconnection network called Fat H-Tree that meets these requirements. A Fat H-Tree provides a torus structure by combining two folded H-Tree networks and is an attractive alternative to tree-based networks such as the Fat Trees in a microarchitecture domain. We introduce its chip layout schemes based on a folding technique for 2D and 3D ICs. Three deadlock-free routing schemes are proposed for Fat H-Tree. We evaluate the performance of Fat H-Tree and other tree-based networks using real application traces. In addition, the network logic area, wire resource, and energy consumption of Fat H-Tree are compared with other topologies, based on a typical implementation of on-chip routers synthesized with a 90-nm standard cell library. The results show that 1) a Fat H-Tree outperforms a Fat Tree with two upward and four downward connections in terms of the throughput and average hop count, 2) a Fat H-Tree requires 19.8 percent-27.8 percent smaller network logic area than the Fat Tree, 3) a Fat H-Tree consumes slightly less energy than the Fat Tree does, and 4) a Fat H-Tree uses slightly more wire resources than the Fat Tree, but the current process technology can provide sufficient wire resources for implementing Fat-H-Tree-based on-chip networks.

AB - The topological explorations of on-chip networks are important for efficiently using their enormous wire resources for low-latency and high-throughput communications using a modest silicon budget. In this paper, we propose a novel tree-based interconnection network called Fat H-Tree that meets these requirements. A Fat H-Tree provides a torus structure by combining two folded H-Tree networks and is an attractive alternative to tree-based networks such as the Fat Trees in a microarchitecture domain. We introduce its chip layout schemes based on a folding technique for 2D and 3D ICs. Three deadlock-free routing schemes are proposed for Fat H-Tree. We evaluate the performance of Fat H-Tree and other tree-based networks using real application traces. In addition, the network logic area, wire resource, and energy consumption of Fat H-Tree are compared with other topologies, based on a typical implementation of on-chip routers synthesized with a 90-nm standard cell library. The results show that 1) a Fat H-Tree outperforms a Fat Tree with two upward and four downward connections in terms of the throughput and average hop count, 2) a Fat H-Tree requires 19.8 percent-27.8 percent smaller network logic area than the Fat Tree, 3) a Fat H-Tree consumes slightly less energy than the Fat Tree does, and 4) a Fat H-Tree uses slightly more wire resources than the Fat Tree, but the current process technology can provide sufficient wire resources for implementing Fat-H-Tree-based on-chip networks.

KW - Interconnection networks

KW - Network topology

KW - On-chip networks

KW - Routing algorithm

KW - Tree

UR - http://www.scopus.com/inward/record.url?scp=67650667517&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650667517&partnerID=8YFLogxK

U2 - 10.1109/TPDS.2008.233

DO - 10.1109/TPDS.2008.233

M3 - Article

AN - SCOPUS:67650667517

VL - 20

SP - 1126

EP - 1141

JO - IEEE Transactions on Parallel and Distributed Systems

JF - IEEE Transactions on Parallel and Distributed Systems

SN - 1045-9219

IS - 8

ER -