Fault-Tolerant Spiking Neural Network Mapping Algorithm and Architecture to 3D-NoC-Based Neuromorphic Systems
Neuromorphic computing uses spiking neuron network models to solve machine learning problems in a more energy-efficient way when compared to conventional artificial neural networks. However, mapping the various network components to the neuromorphic hardware is not trivial to realize the desired mod...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10130549/ |
| _version_ | 1797810674286460928 |
|---|---|
| author | Williams Yohanna Yerima Ogbodo Mark Ikechukwu Khanh N. Dang Abderazek Ben Abdallah |
| author_facet | Williams Yohanna Yerima Ogbodo Mark Ikechukwu Khanh N. Dang Abderazek Ben Abdallah |
| author_sort | Williams Yohanna Yerima |
| collection | DOAJ |
| description | Neuromorphic computing uses spiking neuron network models to solve machine learning problems in a more energy-efficient way when compared to conventional artificial neural networks. However, mapping the various network components to the neuromorphic hardware is not trivial to realize the desired model for an actual simulation. Moreover, neurons and synapses could be affected by noise due to external interference or random actions of other components (i.e., neurons), which eventually lead to unreliable results. This work proposes a fault-tolerant spiking neural network mapping algorithm and architecture to a 3D network-on-chip (NoC)-based neuromorphic system (R-NASH-II) based on a rank and selection mapping mechanism (RSM). The RSM allows the ranking and rapid selection of neurons for fault-tolerant mapping. Evaluation results show that with our proposed mechanism, we could maintain a mapping efficiency of 100% with 20% spare rate and a fault rate (40%) more than in the previous mapping framework. The Monte Carlo simulation evaluation of reliability shows that the RSM mechanism has increased the mean time to failure (MTTF) of the previous mapping technique by 43% on average. Furthermore, the operational availability of the RSM for mapping to a <inline-formula> <tex-math notation="LaTeX">$4\times 4\times 4$ </tex-math></inline-formula> (smallest) and <inline-formula> <tex-math notation="LaTeX">$6\times 6\times 6$ </tex-math></inline-formula> (largest) NoC is 88% and 67% respectively. |
| first_indexed | 2024-03-13T07:12:24Z |
| format | Article |
| id | doaj.art-eecbeccc7514482b93223891dad78df0 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T07:12:24Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-eecbeccc7514482b93223891dad78df02023-06-05T23:00:44ZengIEEEIEEE Access2169-35362023-01-0111524295244310.1109/ACCESS.2023.327880210130549Fault-Tolerant Spiking Neural Network Mapping Algorithm and Architecture to 3D-NoC-Based Neuromorphic SystemsWilliams Yohanna Yerima0https://orcid.org/0009-0001-5044-6233Ogbodo Mark Ikechukwu1https://orcid.org/0000-0003-0041-9111Khanh N. Dang2https://orcid.org/0000-0001-6702-3870Abderazek Ben Abdallah3https://orcid.org/0000-0003-3432-0718Graduate School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, Fukushima, JapanGraduate School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, Fukushima, JapanGraduate School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, Fukushima, JapanGraduate School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, Fukushima, JapanNeuromorphic computing uses spiking neuron network models to solve machine learning problems in a more energy-efficient way when compared to conventional artificial neural networks. However, mapping the various network components to the neuromorphic hardware is not trivial to realize the desired model for an actual simulation. Moreover, neurons and synapses could be affected by noise due to external interference or random actions of other components (i.e., neurons), which eventually lead to unreliable results. This work proposes a fault-tolerant spiking neural network mapping algorithm and architecture to a 3D network-on-chip (NoC)-based neuromorphic system (R-NASH-II) based on a rank and selection mapping mechanism (RSM). The RSM allows the ranking and rapid selection of neurons for fault-tolerant mapping. Evaluation results show that with our proposed mechanism, we could maintain a mapping efficiency of 100% with 20% spare rate and a fault rate (40%) more than in the previous mapping framework. The Monte Carlo simulation evaluation of reliability shows that the RSM mechanism has increased the mean time to failure (MTTF) of the previous mapping technique by 43% on average. Furthermore, the operational availability of the RSM for mapping to a <inline-formula> <tex-math notation="LaTeX">$4\times 4\times 4$ </tex-math></inline-formula> (smallest) and <inline-formula> <tex-math notation="LaTeX">$6\times 6\times 6$ </tex-math></inline-formula> (largest) NoC is 88% and 67% respectively.https://ieeexplore.ieee.org/document/10130549/Neuromorphicfault-tolerantneuron mappingselection and ranking3D-NoC |
| spellingShingle | Williams Yohanna Yerima Ogbodo Mark Ikechukwu Khanh N. Dang Abderazek Ben Abdallah Fault-Tolerant Spiking Neural Network Mapping Algorithm and Architecture to 3D-NoC-Based Neuromorphic Systems IEEE Access Neuromorphic fault-tolerant neuron mapping selection and ranking 3D-NoC |
| title | Fault-Tolerant Spiking Neural Network Mapping Algorithm and Architecture to 3D-NoC-Based Neuromorphic Systems |
| title_full | Fault-Tolerant Spiking Neural Network Mapping Algorithm and Architecture to 3D-NoC-Based Neuromorphic Systems |
| title_fullStr | Fault-Tolerant Spiking Neural Network Mapping Algorithm and Architecture to 3D-NoC-Based Neuromorphic Systems |
| title_full_unstemmed | Fault-Tolerant Spiking Neural Network Mapping Algorithm and Architecture to 3D-NoC-Based Neuromorphic Systems |
| title_short | Fault-Tolerant Spiking Neural Network Mapping Algorithm and Architecture to 3D-NoC-Based Neuromorphic Systems |
| title_sort | fault tolerant spiking neural network mapping algorithm and architecture to 3d noc based neuromorphic systems |
| topic | Neuromorphic fault-tolerant neuron mapping selection and ranking 3D-NoC |
| url | https://ieeexplore.ieee.org/document/10130549/ |
| work_keys_str_mv | AT williamsyohannayerima faulttolerantspikingneuralnetworkmappingalgorithmandarchitectureto3dnocbasedneuromorphicsystems AT ogbodomarkikechukwu faulttolerantspikingneuralnetworkmappingalgorithmandarchitectureto3dnocbasedneuromorphicsystems AT khanhndang faulttolerantspikingneuralnetworkmappingalgorithmandarchitectureto3dnocbasedneuromorphicsystems AT abderazekbenabdallah faulttolerantspikingneuralnetworkmappingalgorithmandarchitectureto3dnocbasedneuromorphicsystems |