Network traffic exploration on a many-core computing platform: SpiNNaker real-time traffic visualiser
Gengting Liu; Camilleri, P.; Furber, S.; Garside, J.
Abstract
The performance of modern supercomputers is ever-increasing. Different kinds of massively parallel programs are written to maximally utilise the computing power provided by these many-core computing machines. However, this performance shrinks when network congestion occurs. SpiNNaker is an energy-efficient and highly parallel computing platform, which has built-in diagnostic hardware and congestion-aware adaptive routing. This paper describes the diagnostic technology available in SpiNNaker machines and presents a new software tool called SpiNNaker real-time traffic visualiser which adopts visualisation technology to explore the network traffic in SpiNNaker machines. This visualiser can assist application developers in detecting network traffic congestion with the provision of real-time configuration and data-logging functions.