extended-abstract

Provable Neuromorphic Advantages for Computing Shortest Paths

Authors:

Yang Ho,

Yipu WangAuthors Info & Claims

SPAA '20: Proceedings of the 32nd ACM Symposium on Parallelism in Algorithms and Architectures

Pages 497 - 499

https://doi.org/10.1145/3350755.3400258

Published: 09 July 2020 Publication History

Get Access

Abstract

Neuromorphic computing offers the potential of an unprecedented level of parallelism at a local scale. Although in their infancy, current first-generation neuromorphic processing units (NPUs) deliver as many as 128K artificial neurons in a package smaller than current laptop CPUs and demanding significantly less energy. Neuromorphic systems consisting of such NPUs and offering a total of 100 million neurons are anticipated in 2020. NPUs were envisioned to accelerate machine learning, and designing neuromorphic algorithms to leverage the benefits of NPUs in other domains remains an open challenge. We design and analyze neuromorphic graph algorithms, focusing on shortest path problems. Our neuromorphic algorithms are packet-passing algorithms relying on data movement for computation, and we develop data-movement lower bounds for conventional algorithms. A fair and rigorous comparison with conventional algorithms and architectures is paramount, and we prove a polynomial-factor advantage even when we assume an NPU with a simple grid-like network of neurons. To the best of our knowledge, this is one of the first examples of a provable asymptotic computational advantage for neuromorphic computing.

References

[1]

Agarwal, S., Quach, T.-T., Parekh, O., Hsia, A. H., DeBenedictis, E. P., James, C. D., Marinella, M. J., and Aimone, J. B. Energy scaling advantages of resistive memory crossbar based computation and its application to sparse coding. Frontiers in neuroscience 9 (2015).

Google Scholar

[2]

Aimone, J. B. Neural algorithms and computing beyond moore's law. Communications of the ACM 62, 4 (2019), 110--110.

Digital Library

Google Scholar

[3]

Aimone, J. B., Parekh, O., Phillips, C. A., Pinar, A., Severa, W., and Xu, H. Dynamic programming with spiking neural computing. In Proceedings of the International Conference on Neuromorphic Systems (New York, NY, USA, 2019), ICONS '19, Association for Computing Machinery.

Digital Library

Google Scholar

[4]

Azevedo, F. A. C., Carvalho, L. R. B., Grinberg, L. T., Farfel, J. M., Ferretti, R. E. L., Leite, R. E. P., Jacob Filho, W., Lent, R., and Herculano-Houzel, S. Equal numbers of neuronal and nonneuronal cells make the human brain an isometrically scaled-up primate brain. The Journal of Comparative Neurology 513, 5 (Apr. 2009), 532--541.

Crossref

Google Scholar

[5]

Kwisthout, J., and Donselaar, N. On the computational power and complexity of Spiking Neural Networks. arXiv:2001.08439 [cs] (Jan. 2020). arXiv: 2001.08439.

Google Scholar

[6]

Moore, S. Intel's Neuromorphic System Hits 8 Million Neurons, 100 Million Coming by 2020 - IEEE Spectrum. https://spectrum.ieee.org/tech-talk/artificial-intelligence/embedded-ai/intels-neuromorphic-system-hits-8-million-neurons-100-million-coming-by-2020.

Google Scholar

[7]

Parekh, O., Phillips, C. A., James, C. D., and Aimone, J. B. Constant-depth and subcubic-size threshold circuits for matrix multiplication. In Proceedings of the 30th on Symposium on Parallelism in Algorithms and Architectures (2018), ACM, pp. 67--76.

Digital Library

Google Scholar

[8]

Schuman, C. D., Potok, T. E., Patton, R. M., Birdwell, J. D., Dean, M. E., Rose, G. S., and Plank, J. S. A survey of neuromorphic computing and neural networks in hardware. arXiv preprint arXiv:1705.06963 (2017).

Google Scholar

[9]

Thompson, C. D. Area-time complexity for VLSI. In Proceedings of the eleventh annual ACM symposium on Theory of computing (Atlanta, Georgia, USA, Apr. 1979), STOC '79, Association for Computing Machinery, pp. 81--88.

Digital Library

Google Scholar

Cited By

View all

Snyder SClerico VCong GKulkarni SSchuman CRisbud SParsa M(2024)Transductive Spiking Graph Neural Networks for LoihiProceedings of the Great Lakes Symposium on VLSI 202410.1145/3649476.3660366(608-613)Online publication date: 12-Jun-2024
https://dl.acm.org/doi/10.1145/3649476.3660366
Wang FSevera W(2024)Using STACS as a High-Performance Simulation Backend for Fugu2024 International Conference on Neuromorphic Systems (ICONS)10.1109/ICONS62911.2024.00030(156-160)Online publication date: 30-Jul-2024
https://doi.org/10.1109/ICONS62911.2024.00030
Zavyalov KBazenkov N(2024)Solving TSP Problem with Spiking Neural NetworkAdvances in Neural Computation, Machine Learning, and Cognitive Research VIII10.1007/978-3-031-73691-9_6(58-66)Online publication date: 20-Oct-2024
https://doi.org/10.1007/978-3-031-73691-9_6
Show More Cited By

Index Terms

Provable Neuromorphic Advantages for Computing Shortest Paths

Recommendations

Provable Advantages for Graph Algorithms in Spiking Neural Networks
SPAA '21: Proceedings of the 33rd ACM Symposium on Parallelism in Algorithms and Architectures

We present a theoretical framework for designing and assessing the performance of algorithms executing in networks consisting of spiking artificial neurons. Although spiking neural networks (SNNs) are capable of general-purpose computation, few ...
Mapping spiking neural networks onto a manycore neuromorphic architecture
PLDI '18

We present a compiler for Loihi, a novel manycore neuromorphic processor that features a programmable, on-chip learning engine for training and executing spiking neural networks (SNNs). An SNN is distinguished from other neural networks in that (1) its ...
Mapping spiking neural networks onto a manycore neuromorphic architecture
PLDI 2018: Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and Implementation

We present a compiler for Loihi, a novel manycore neuromorphic processor that features a programmable, on-chip learning engine for training and executing spiking neural networks (SNNs). An SNN is distinguished from other neural networks in that (1) its ...

Comments

Information & Contributors

Information

Published In

SPAA '20: Proceedings of the 32nd ACM Symposium on Parallelism in Algorithms and Architectures

July 2020

601 pages

ISBN:9781450369350

DOI:10.1145/3350755

General Chair:
Christian Scheideler
Institut fuer Informatik Universitaet Paderborn Fuerstenallee 11
,
Program Chair:
Michael Spear

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 09 July 2020

Check for updates

Author Tags

Qualifiers

Extended-abstract

Conference

SPAA '20

Sponsor:

SPAA '20: 32nd ACM Symposium on Parallelism in Algorithms and Architectures

July 15 - 17, 2020

Virtual Event, USA

Acceptance Rates

Overall Acceptance Rate 447 of 1,461 submissions, 31%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

10
Total Citations
View Citations
284
Total Downloads

Downloads (Last 12 months)44
Downloads (Last 6 weeks)5

Reflects downloads up to 25 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Snyder SClerico VCong GKulkarni SSchuman CRisbud SParsa M(2024)Transductive Spiking Graph Neural Networks for LoihiProceedings of the Great Lakes Symposium on VLSI 202410.1145/3649476.3660366(608-613)Online publication date: 12-Jun-2024
https://dl.acm.org/doi/10.1145/3649476.3660366
Wang FSevera W(2024)Using STACS as a High-Performance Simulation Backend for Fugu2024 International Conference on Neuromorphic Systems (ICONS)10.1109/ICONS62911.2024.00030(156-160)Online publication date: 30-Jul-2024
https://doi.org/10.1109/ICONS62911.2024.00030
Zavyalov KBazenkov N(2024)Solving TSP Problem with Spiking Neural NetworkAdvances in Neural Computation, Machine Learning, and Cognitive Research VIII10.1007/978-3-031-73691-9_6(58-66)Online publication date: 20-Oct-2024
https://doi.org/10.1007/978-3-031-73691-9_6
Vetter JDate PFahim FKulkarni SMaksymovych PTalin ATallada MVanna-iampikul PYoung ABrooks DCao YGu-Yeon WLim SLiu FMarinella MSumpter BMiniskar N(2023)Abisko: Deep codesign of an architecture for spiking neural networks using novel neuromorphic materialsThe International Journal of High Performance Computing Applications10.1177/1094342023117853737:3-4(351-379)Online publication date: 22-Jun-2023
https://doi.org/10.1177/10943420231178537
Cong GLim SKulkarni SDate PPotok TSnyder SParsa MSchuman C(2022)Semi-Supervised Graph Structure Learning on Neuromorphic ComputersProceedings of the International Conference on Neuromorphic Systems 202210.1145/3546790.3546821(1-4)Online publication date: 27-Jul-2022
https://dl.acm.org/doi/10.1145/3546790.3546821
Date PPotok TSchuman CKay B(2022)Neuromorphic Computing is Turing-CompleteProceedings of the International Conference on Neuromorphic Systems 202210.1145/3546790.3546806(1-10)Online publication date: 27-Jul-2022
https://dl.acm.org/doi/10.1145/3546790.3546806
Schuman CKulkarni SParsa MMitchell JDate PKay B(2022)Opportunities for neuromorphic computing algorithms and applicationsNature Computational Science10.1038/s43588-021-00184-y2:1(10-19)Online publication date: 31-Jan-2022
https://doi.org/10.1038/s43588-021-00184-y
Kay BSchuman CO'Connor JDate PPotok T(2021)Neuromorphic Graph Algorithms: Cycle Detection, Odd Cycle Detection, and Max FlowInternational Conference on Neuromorphic Systems 202110.1145/3477145.3477172(1-7)Online publication date: 27-Jul-2021
https://dl.acm.org/doi/10.1145/3477145.3477172
Date PKay BSchuman CPatton RPotok T(2021)Computational Complexity of Neuromorphic AlgorithmsInternational Conference on Neuromorphic Systems 202110.1145/3477145.3477154(1-7)Online publication date: 27-Jul-2021
https://dl.acm.org/doi/10.1145/3477145.3477154
Schuman CKay BDate PKannan RSao PPotok T(2021)Sparse Binary Matrix-Vector Multiplication on Neuromorphic Computers2021 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)10.1109/IPDPSW52791.2021.00054(308-311)Online publication date: Jun-2021
https://doi.org/10.1109/IPDPSW52791.2021.00054

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Provable Advantages for Graph Algorithms in Spiking Neural Networks

Mapping spiking neural networks onto a manycore neuromorphic architecture

Mapping spiking neural networks onto a manycore neuromorphic architecture

Comments

Published In

Sponsors

Publisher

Publication History

Check for updates

Author Tags

Qualifiers

Conference

Acceptance Rates

Other Metrics

Article Metrics

Other Metrics

Cited By

Login options

Full Access

PDF

eReader

Abstract

References

Cited By

Index Terms

Recommendations

Provable Advantages for Graph Algorithms in Spiking Neural Networks

Mapping spiking neural networks onto a manycore neuromorphic architecture

Mapping spiking neural networks onto a manycore neuromorphic architecture

Comments

Information

Published In

Sponsors

Publisher

Publication History

Check for updates

Author Tags

Qualifiers

Conference

Acceptance Rates

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

Login options

Full Access

View options

PDF

eReader

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations