An efficient strategy for reducing head-of-line blocking in fat-trees

Authors:
Jesus Escudero-Sahuquillo;Pedro Javier Garcia;Francisco J. Quiles;Jose Duato
Affiliations:
Dept. of Computing Systems, University of Castilla-La Mancha, Spain;Dept. of Computing Systems, University of Castilla-La Mancha, Spain;Dept. of Computing Systems, University of Castilla-La Mancha, Spain;Dept. of Computer Engineering, Technical University of Valencia, Spain
Venue:
Euro-Par'10 Proceedings of the 16th international Euro-Par conference on Parallel processing: Part II
Year:
2010

Citing 10
Cited 3

Fat-trees: universal networks for hardware-efficient supercomputing

IEEE Transactions on Computers
Dynamically-Allocated Multi-Queue Buffers for VLSI Communication Switches

IEEE Transactions on Computers
High-speed switch scheduling for local-area networks

ACM Transactions on Computer Systems (TOCS)
Interconnection Networks: An Engineering Approach

Interconnection Networks: An Engineering Approach
k -ary n -trees: High Performance Networks for Massively Parallel Architectures

IPPS '97 Proceedings of the 11th International Symposium on Parallel Processing
A Memory-Effective Routing Strategy for Regular Interconnection Networks

IPDPS '05 Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Papers - Volume 01
Destination-Based HoL Blocking Elimination

ICPADS '06 Proceedings of the 12th International Conference on Parallel and Distributed Systems - Volume 1
Efficient, Scalable Congestion Management for Interconnection Networks

IEEE Micro
RECN-IQ: A Cost-Effective Input-Queued Switch Architecture with Congestion Management

ICPP '07 Proceedings of the 2007 International Conference on Parallel Processing
FBICM: efficient congestion management for high-performance networks using distributed deterministic routing

HiPC'08 Proceedings of the 15th international conference on High performance computing

dFtree: a fat-tree routing algorithm using dynamic allocation of virtual lanes to alleviate congestion in infiniband networks

Proceedings of the first international workshop on Network-aware data management
A new proposal to deal with congestion in InfiniBand-based fat-trees

Journal of Parallel and Distributed Computing
An integrated solution for QoS provision and congestion management in high-performance interconnection networks using deterministic source-based routing

The Journal of Supercomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The fat-tree is one of the most common topologies for the interconnection networks of PC Clusters which are currently used for high-performance parallel computing. Among other advantages, fat-trees allow the use of simple but very efficient routing schemes. One of them is a deterministic routing algorithm that has been recently proposed, offering similar (or better) performance than Adaptive Routing while reducing complexity and guaranteeing in-order packet delivery. However, as other deterministic routing proposals, this deterministic routing algorithm cannot react when high traffic loads or hot-spot traffic scenarios produce severe contention for the use of network resources, leading to the appearance of Head-Of-Line (HOL) blocking, which spoils network performance. In that sense, we present in this paper a simple, efficient strategy for dealing with the HOL blocking that may appear in fat-trees with the aforementioned deterministic routing algorithm. From the results presented in the paper, we can conclude that, in the mentioned environment, our proposal considerably reduces HOL blocking without significantly increasing switch complexity and required silicon area.