Abstract
End-to-end network latency has become an important issue for parallel application on large-scale high performance computing (HPC) systems. It has been reported that randomly-connected inter-switch networks can lower the end-to-end network latency. This latency reduction is established in exchange for a large amount of routing information. That is, minimal routing on irregular networks is achieved by using routing tables for all destinations in the networks. In this work, a novel distributed routing method called LOREN (Layout-Oriented Routing with Entries for Neighbors) to achieve low-latency with a small routing table is proposed for irregular networks whose link length is limited. The routing tables contain both physically and topologically nearby neighbor nodes to ensure livelock-freedom and a small number of hops between nodes. Experimental results show that LOREN reduces the average latencies by 5.8% and improves the network throughput by up to 62% compared with a conventional compact routing method. Moreover, the number of required routing table entries is reduced by up to 91%, which improves scalability and flexibility for implementation.
| Original language | English |
|---|---|
| Pages (from-to) | 2796-2807 |
| Number of pages | 12 |
| Journal | IEICE Transactions on Information and Systems |
| Volume | E100D |
| Issue number | 12 |
| DOIs | |
| Publication status | Published - 2017 Dec 1 |
Fingerprint
Keywords
- High performance computing
- Interconnection networks
- Network topology
ASJC Scopus subject areas
- Software
- Hardware and Architecture
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering
- Artificial Intelligence
Cite this
A layout-oriented routing method for low-latency HPC networks. / Kawano, Ryuta; Nakahara, Hiroshi; Fujiwara, Ikki; Matsutani, Hiroki; Koibuchi, Michihiro; Amano, Hideharu.
In: IEICE Transactions on Information and Systems, Vol. E100D, No. 12, 01.12.2017, p. 2796-2807.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A layout-oriented routing method for low-latency HPC networks
AU - Kawano, Ryuta
AU - Nakahara, Hiroshi
AU - Fujiwara, Ikki
AU - Matsutani, Hiroki
AU - Koibuchi, Michihiro
AU - Amano, Hideharu
PY - 2017/12/1
Y1 - 2017/12/1
N2 - End-to-end network latency has become an important issue for parallel application on large-scale high performance computing (HPC) systems. It has been reported that randomly-connected inter-switch networks can lower the end-to-end network latency. This latency reduction is established in exchange for a large amount of routing information. That is, minimal routing on irregular networks is achieved by using routing tables for all destinations in the networks. In this work, a novel distributed routing method called LOREN (Layout-Oriented Routing with Entries for Neighbors) to achieve low-latency with a small routing table is proposed for irregular networks whose link length is limited. The routing tables contain both physically and topologically nearby neighbor nodes to ensure livelock-freedom and a small number of hops between nodes. Experimental results show that LOREN reduces the average latencies by 5.8% and improves the network throughput by up to 62% compared with a conventional compact routing method. Moreover, the number of required routing table entries is reduced by up to 91%, which improves scalability and flexibility for implementation.
AB - End-to-end network latency has become an important issue for parallel application on large-scale high performance computing (HPC) systems. It has been reported that randomly-connected inter-switch networks can lower the end-to-end network latency. This latency reduction is established in exchange for a large amount of routing information. That is, minimal routing on irregular networks is achieved by using routing tables for all destinations in the networks. In this work, a novel distributed routing method called LOREN (Layout-Oriented Routing with Entries for Neighbors) to achieve low-latency with a small routing table is proposed for irregular networks whose link length is limited. The routing tables contain both physically and topologically nearby neighbor nodes to ensure livelock-freedom and a small number of hops between nodes. Experimental results show that LOREN reduces the average latencies by 5.8% and improves the network throughput by up to 62% compared with a conventional compact routing method. Moreover, the number of required routing table entries is reduced by up to 91%, which improves scalability and flexibility for implementation.
KW - High performance computing
KW - Interconnection networks
KW - Network topology
UR - http://www.scopus.com/inward/record.url?scp=85038381248&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85038381248&partnerID=8YFLogxK
U2 - 10.1587/transinf.2017PAP0019
DO - 10.1587/transinf.2017PAP0019
M3 - Article
AN - SCOPUS:85038381248
VL - E100D
SP - 2796
EP - 2807
JO - IEICE Transactions on Information and Systems
JF - IEICE Transactions on Information and Systems
SN - 0916-8532
IS - 12
ER -