Understanding the interconnection network of SpiNNaker

@inproceedings{Navaridas2009UnderstandingTI,
  title={Understanding the interconnection network of SpiNNaker},
  author={Javier Navaridas and Mikel Luj{\'a}n and Jos{\'e} Miguel-Alonso and Luis A. Plana and Stephen B. Furber},
  booktitle={ICS '09},
  year={2009}
}
SpiNNaker is a massively parallel architecture designed to model large-scale spiking neural networks in (biological) real-time. Its design is based around ad-hoc multi-core System-on-Chips which are interconnected using a two-dimensional toroidal triangular mesh. Neurons are modeled in software and their spikes generate packets that propagate through the on- and inter-chip communication fabric relying on custom-made on-chip multicast routers. This paper models and evaluates large-scale… 

Figures and Tables from this paper

Population-based routing in the SpiNNaker neuromorphic architecture

TLDR
A novel approach to the projection routing problem is described that shows advantages in both the size of the routing tables generated and the computational complexity for the generation of routing tables.

SpiNNaker: impact of traffic locality, causality and burstiness on the performance of the interconnection network

TLDR
The results show that the interconnection network of SpiNNaker can operate without dropping packets with traffic loads that exceed more than 3.5 times those required to simulate 109 spiking neurons, despite using non-local traffic.

SpiNNaker: Enhanced multicast routing

Analytical Assessment of the Suitability of Multicast Communications for the SpiNNaker Neuromimetic System

TLDR
Analytical proof is shown that the novel multicast router in SpiNNaker is a better solution for simulating neural nets than more powerful point-to-point routers such as those found on datacentres or high performance computing systems, even when it has significantly lower requirements in terms of complexity, area and power.

Interconnection system for the spiNNaker biologically inspired multi-computer

TLDR
This study describes the practical techniques and details employed in two components of the SpiNNaker system, including the proposed board-to-board interconnection system and the proposed peripheral I/O subsystem developed as a layer on top ofSpiNNlink.

On generating multicast routes for SpiNNaker

TLDR
Results show that the communication infrastructure of SpiNNaker will be able to support the high communication pressure exerted by simulating in real-time biologically plausible spiking neural applications.

Development of a Dynamically Extendable SpiNNaker Chip Computing Module

TLDR
A Dynamically Extendable SpiNNaker Chip Computing Module is presented that allows a Spinnaker machine to be deployed on small mobile robots and to demonstrate the general purpose capabilities of this new platform.

Distributed configuration of massively-parallel simulation on SpiNNaker neuromorphic hardware

TLDR
This work proposes distributed software mechanisms to address the problems of machine configuration, program loading and simulation monitoring given a lack of globally-shared memory resources, intrinsic addressing mode or sideband configuration channel, and presents experiments which demonstrate the necessity of this approach in contrast to centralised mechanisms.

Managing Burstiness and Scalability in Event-Driven Models on the SpiNNaker Neuromimetic System

TLDR
Simulation results indicate the viability of SpiNNaker for large-scale neural modelling, while emphasizing the need for effective burst management and network mapping.

SpiNNaker: Fault tolerance in a power- and area- constrained large-scale neuromimetic architecture

...

References

SHOWING 1-10 OF 24 REFERENCES

SpiNNaker: Mapping neural networks onto a massively-parallel chip multiprocessor

TLDR
The methods by which neural networks are mapped onto the system, and how features designed into the chip are to be exploited in practice are described to ensure that, when the chip is delivered, it will work as anticipated.

Efficient modelling of spiking neural networks on a scalable chip multiprocessor

  • Xin JinS. FurberJ. V. Woods
  • Computer Science
    2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)
  • 2008
TLDR
A system based on the Izhikevich model running on a scalable chip multiprocessor - SpiNNaker - for large-scale spiking neural network simulation and an approach based on using two scaling factors is developed, making the precision comparable to the original.

An On-Chip and Inter-Chip Communications Network for the SpiNNaker Massively-Parallel Neural Net Simulator

TLDR
This paper presents the on-chip and inter-chip communications network for SpiNNaker, a scalable, multichip system designed for the purpose of real-time modelling of spiking neurons with an efficient multicast communications infrastructure inspired by neurobiology.

On-chip and inter-chip networks for modeling large-scale neural systems

TLDR
The design emphasizes modeling flexibility, power-efficiency, and fault-tolerance, and is intended to yield a general-purpose platform for the real-time simulation of large-scale spiking neural systems.

Emulation engine for spiking neurons and adaptive synaptic weights

TLDR
A field-programmable gate array (FPGA) based emulation engine, called spiking neural network emulation engine (SEE), for spiking neurons and adaptive synaptic weights is presented, that tackles this bottle-neck problem by providing a distributed memory architecture and a high bandwidth to the weight memory.

Reducing complexity in tree-like computer interconnection networks

The Adaptive Bubble Router

TLDR
This proposal is the adaptive router with the shortest clock cycle and node delay when compared with other state-of-the-art alternatives, which translates into the lowest latency and highest throughput under standard synthetic loads.

IBM Research Report Design and Analysis of the BlueGene/L Torus Interconnection Network

TLDR
A parallel performance simulator that was used extensively to help architect and design the torus network is described and sample simulator performance studies that contributed to design decisions are presented.

INSEE: An Interconnection Network Simulation and Evaluation Environment

In this paper we introduce INSEE, an environment to help in the design of interconnection networks for parallel computing systems. It contains two main modules: a system to generate traffic (TrGen)