Optimization and performance study of large-scale biological networks for reconfigurable computing

Bhuiyan, Mohammad A.; Nallamuthu, Ananth; Smith, Melinda; Pallipuram, Vivek K.

doi:10.1109/hprcta.2010.5670796

Cited by 11 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[13][14][15][16][17][18][19][20][21]33 This part includes digital implementation procedure of the Wilson neuron. [13][14][15][16][17][18][19][20][21]33 This part includes digital implementation procedure of the Wilson neuron.…”

Section: Design and Hardware Implementationmentioning

confidence: 99%

See 1 more Smart Citation

Digital implementation of biologically inspired Wilson model, population behavior, and learning

Karimi

Gholami

Farsa

2018

Circuit Theory & Apps

View full text Add to dashboard Cite

Spiking neurons, as a computational unit, are the main part in biological information processing systems. This paper presents a digital hardware implementation of a biological neuron on a field-programmable gate array due to its high accuracy and high speed, especially for large-scale simulations which is a key objective in the neuromorphic research field. Although this is a computationally expensive task, the use of more biological realistic system results in higher accuracy in mimicking biological behaviors of neural networks. Given that, the Wilson model is one of the most important biological neuron models that can be used in the architecture of spiking neural networks. To be closer to biological systems, a method is proposed to test the possibility of implementation of the Wilson neuron model on digital platforms. The results of the hardware implementation of the Wilson neuron and a spiking network on a field-programmable gate array, capable of character recognition with supervised learning algorithm, are presented in this paper; moreover, population behavior of this model is simulated. In large-scale implementation of 2000 Wilson neuron model, population capability, feasibility, and costs are investigated. This paper presents a method to the implementation of Wilson neurons on digital platforms, suggesting that the available system is an attainable platform for the implementation of large-scale biologically plausible neural networks on field-programmable gate array devices. Hardware synthesis, physical implementation on field-programmable gate array, and theoretical analysis confirm that the proposed model has hardware so that makes it an appropriate model for the large-scale digital implementation. KEYWORDS hardware implementation, learning, spiking neural network, Wilson Model

show abstract

Section: Design and Hardware Implementationmentioning

confidence: 99%

“…Field-programmable gate arrays can support an efficient programmable resource for hardware implementation of SNNs. [13][14][15][16][17][18][19][20][21]33 This part includes digital implementation procedure of the Wilson neuron. Analog implementation of neuro-inspired systems is a logical selection.…”

Section: Design and Hardware Implementationmentioning

confidence: 99%

Digital implementation of biologically inspired Wilson model, population behavior, and learning

Karimi

Gholami

Farsa

2018

Circuit Theory & Apps

View full text Add to dashboard Cite

show abstract

“…Such attempts are limited in scope and in-depth analysis of the requirements, relevant to the neuroscientific experiments, thus, fall short of painting the big picture. To the best of our knowledge, only Bhuiyan et al [22] have made an attempt for a more complete analysis of large-scale SNNs. The design was implemented on a SRC-7 H MAP platform, a software/hardware co-design HPC system that includes a Stratix II FPGA for acceleration.…”

Section: Related Workmentioning

confidence: 99%

Performance analysis of accelerated biophysically-meaningful neuron simulations

Smaragdos¹,

Chatzikostantis²,

Nomikou³

et al. 2016

2016 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)

View full text Add to dashboard Cite

In-vivo and in-vitro experiments are routinely used in neuroscience to unravel brain functionality. Although they are a powerful experimentation tool, they are also time-consuming and, often, restrictive. Computational neuroscience attempts to solve this by using biologically-plausible and biophysicallymeaningful neuron models, most prominent among which are the conductance-based models. Their computational complexity calls for accelerator-based computing to mount large-scale or realtime neuroscientific experiments. In this paper, we analyze and draw conclusions on the class of conductance models by using a representative modeling application of the inferior olive (InfOli), an important part of the olivocerebellar brain circuit. We conduct an extensive profiling session to identify the computational and data-transfer requirements of the application under various realistic use cases. The application is, then, ported onto two acceleration nodes, an Intel Xeon Phi and a Maxeler Vectis Data Flow Engine (DFE). We evaluate the performance scalability and resource requirements of the InfOli application on the two target platforms. The analysis of InfOli, which is a real-life neuroscientific application, can serve as a useful guide for porting a wide range of similar workloads on platforms like the Xeon Phi or the Maxeler DFEs. As accelerators are increasingly populating High-Performance Computing (HPC) infrastructure, the current paper provides useful insight on how to optimally use such nodes to run complex and relevant neuron modeling workloads.

show abstract

“…Traditional methods of computing, in which the common simulation tool-flows (such as MATLAB or specific neuromodeling tools like NEURON or Brian) are executed, are not up to the task of simulating neural networks of realistic sizes and high detail within a reasonable timeframe for brain research. High-Performance Computing (HPC) has been recently recognized as being able to provide a variety of solutions to cope with this limitation [2][3][4][5][6][7]. Unfortunately, the challenge of executing such simulation applications does not stop just at providing the necessary computational power.…”

Section: Introductionmentioning

confidence: 99%

“…The variety of options of viable SNN models used in studies is significant. Every type of model has scientific merit, depending on the subject under study, and models exhibit different characteristics when treated as computational workloads [6,8]. Modeling features like the inter-neuron connectivity density (the modeling of which also varies according to the biological system under study) can break the embarrassingly parallel (data-flow compatible) nature that most neuron models have, significantly changing the behavior of the application.…”

Section: Introductionmentioning

confidence: 99%

BrainFrame: a node-level heterogeneous accelerator platform for neuron simulations

et al. 2017

View full text Add to dashboard Cite

The BrainFrame framework is designed to transparently configure and select the appropriate back-end accelerator technology for use per simulation run. The PyNN integration provides a familiar bridge to the vast number of models already available. Additionally, it gives a clear roadmap for extending the platform support beyond the proof of concept, with improved usability and directly useful features to the computational-neuroscience community, paving the way for wider adoption.

show abstract

Optimization and performance study of large-scale biological networks for reconfigurable computing

Cited by 11 publications

References 20 publications

Digital implementation of biologically inspired Wilson model, population behavior, and learning

Digital implementation of biologically inspired Wilson model, population behavior, and learning

Performance analysis of accelerated biophysically-meaningful neuron simulations

BrainFrame: a node-level heterogeneous accelerator platform for neuron simulations

Contact Info

Product

Resources

About