Hierarchical Address Event Routing for Reconfigurable Large-Scale Neuromorphic Systems
The DOI matches its Crossref record; 65 of the 68 references it cites were found in a registry or an index.
Abstract
We present a hierarchical address-event routing (HiAER) architecture for scalable communication of neural and synaptic spike events between neuromorphic processors, implemented with five Xilinx Spartan-6 field-programmable gate arrays and four custom analog neuromophic integrated circuits serving 262k neurons and 262M synapses. The architecture extends the single-bus address-event representation protocol to a hierarchy of multiple nested buses, routing events across increasing scales of spatial distance. The HiAER protocol provides individually programmable axonal delay in addition to strength for each synapse, lending itself toward biologically plausible neural network architectures, and scales across a range of hierarchies suitable for multichip and multiboard systems in reconfigurable large-scale neuromorphic systems. We show approximately linear scaling of net global synaptic event throughput with number of routing nodes in the network, at $3.6\times 10^{7}$ synaptic events per second per 16k-neuron node in the hierarchy.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Multiple layers of multicast address-event routing schemes (Network on Chip, FireFly, and Ethernet) 7,8 will allow spikes to travel ef fi ciently between cores, FPGAs, and servers.”
From HiAER-spike software-hardware reconfigurable platform for event-driven neuromorphic computing at scale (2026) · cites this paper as [7]
Citations
Cites
Measuring the thickness of the human cerebral cortex from magnetic resonance images
Fischl, B., & Dale, A. M. (2000) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.200033797 · Cited by 5,818 · cited 1×
“002 m3 volume and across 1 m2 cortical surface area, and at 20 W of metabolic power consumption [1], [2], [51]–[54].”
BackgroundA Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs
Karypis, G., & Kumar, V. (1998) · SIAM Journal on Scientific Computing · doi:10.1137/s1064827595287997 · Cited by 5,762 · cited 1×
“The general problem of efficient hierarchical graph partitioning is well studied, and solutions formulated in various application domains [59] may be ported to hierarchical synaptic partitioning, in tandem with compilation and analysis tools for efficient mapping of the hierarchical neural and synaptic structure onto…”
BackgroundA million spiking-neuron integrated circuit with a scalable communication network and interface
Merolla, P. A., Arthur, J. V., Alvarez-Icaza, R., Cassidy, A. S., Sawada, J., Akopyan, F., Jackson, B. L., Imam, N., Guo, C., Nakamura, Y., et al. (2014) · Science · doi:10.1126/science.1254642 · Cited by 4,147 · cited 2×
“IBM SyNAPSE TrueNorth [38] integrates a 2-”
MethodThe Synaptic Organization of the Brain
(2004) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780195159561.001.1 · Cited by 3,546
An Energy Budget for Signaling in the Grey Matter of the Brain
Attwell, D., & Laughlin, S. B. (2001) · Journal of Cerebral Blood Flow & Metabolism · doi:10.1097/00004647-200110000-00001 · Cited by 3,543
A Proof for the Queuing Formula: L = λ W
Little, J. D. C. (1961) · Operations Research · doi:10.1287/opre.9.3.383 · Cited by 2,777 · cited 3×
“Solid straight lines: theoretical model according to Little’s law Q = r d [47] for reference.”
BackgroundMethodInfluentialA 128$\times$128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision Sensor
Lichtsteiner, P., Posch, C., & Delbruck, T. (2008) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2007.914337 · Cited by 2,485
Churchland, P. S., & Sejnowski, T. J. (1992) · doi:10.7551/mitpress/2010.001.0001 · Cited by 1,757 · cited 5×
“traveling along axons carry neural information over long distances projecting to large numbers of other neurons distributed over varying spatial scales [1], [2].”
BackgroundInfluentialNeurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural Simulations
Benjamin, B. V., Gao, P., McQuinn, E., Choudhary, S., Chandrasekaran, A. R., Bussat, J.-M., Alvarez-Icaza, R., Arthur, J. V., Merolla, P. A., & Boahen, K. (2014) · Proceedings of the IEEE · doi:10.1109/jproc.2014.2313565 · Cited by 1,266 · cited 1×
“Grid-based [31], [34], [39], [40] and treebased [32], [33], [35]–[37], [41] extensions to AER have aimed at extending the bandwidth and spatial range of synaptic connectivity across multichip neural arrays in a scalable and efficient manner.”
BackgroundThe cost of cortical computation.
Lennie, P. (2003) · Current Biology · doi:10.1016/s0960-9822(03)00135-0 · Cited by 1,134 · cited 1×
“002 m3 volume and across 1 m2 cortical surface area, and at 20 W of metabolic power consumption [1], [2], [51]–[54].”
Background
Cited by
Items 101–117 of 117
An Asynchronous Soft Macro for Ultra-Low Power Communication in Neuromorphic Computing
Bertozzi, D., Bhardwaj, K., & Nowick, S. M. (2022) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas54282.2022.9869944 · Cited by 1
Neuromorphic Neural Interfaces
Broccard, F. D., Joshi, S., Wang, J., & Cauwenberghs, G. (2023) · Handbook of Neuroengineering · doi:10.1007/978-981-16-5540-1_41 · Cited by 1
Self-citationFrank, G., Hota, G., Wang, K., Deng, C., Arora, K., Vins, D., Uppal, A., Olajide, O., Yoshimoto, K., Wang, Q., et al. (2026) · npj Unconventional Computing · doi:10.1038/s44335-026-00062-8
“…in turn, contains multiple SNN cores that will run fully in parallel with dedicated interfaces to the on-module HBM. Multiple layers of multicast address-event routing schemes (Network on Chip, FireFly, and Ethernet) [7, 8] will allow spikes to travel efficiently between cores, FPGAs, and servers.”
Self-citationEnergy efficiency in adaptive neural circuits
Cauwenberghs, G. (2017) · Berkeley Symposium on Energy Efficient Electronic Systems & Steep Transistors Workshop (E3S) · doi:10.1109/e3s.2017.8246163
“Hierarchical address-event routing (HiAER) offers scalable long-range neural event communication tailored to locally dense and globally sparse synaptic connectivity [11, 12], while integrate-and-fire array transceiver (IFAT) CMOS neural arrays with up to 65k neurons integrated on a single chip [13, 14, 5] offer low-po…”
BackgroundMethodSelf-citationPark, J., Kim, Y. H., & Jung, S.-D. (2017) · IEEE Biomedical Circuits and Systems Conference (BioCAS) · doi:10.1109/biocas.2017.8325197
“A priority queue is designed to keep track the delay of incoming events [9].”
BackgroundSelf-citationAnalog circuits for mixed-signal neuromorphic computing architectures in 28 nm FD-SOI technologyPreprint
Qiao, N., & Indiveri, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.07874
Efficient On-chip Communication for Neuromorphic Systems
Kumar, S., Das, S., Jamadar, M. M., & Kaur, J. (2021) · IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) · doi:10.1109/swc50871.2021.00040
Neuromorphic Circuits and Systems: From Neuron Models to Integrate-and-Fire Arrays
Molin, J. L., & Etienne‐Cummings, R. (2023) · Handbook of Neuroengineering · doi:10.1007/978-981-16-5540-1_42 · Cited by 1
SONA: A Bio-Inspired, Self-Organizing Connective Fabric for Neuromorphic Circuits and FPGAs
Battel, D., & Parker, A. C. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191539
“In packet-based AER, connections are stored as a synaptic routing table, and can be added or removed by modifying this table [11], [12].”
BackgroundLarge-Scale Digital Neuromorphic Systems
Yang, S., & Chen, B. (2024) · Synthesis lectures on engineering, science, and technology · doi:10.1007/978-3-031-57873-1_5
Neuromorphic Electronics at BioCAS: A 20-year Legacy of Sparking Technology Revolutions
Akwaboah, A. D., & Etienne‐Cummings, R. (2024) · IEEE Biomedical Circuits and Systems Conference (BioCAS) · doi:10.1109/biocas61083.2024.10798206
Real-Time Large-Scale Neural Connectivity Inference on Spiking Neuromorphic System
Kim, D., Park, S., Jeong, Y., Kim, J., Lee, S., Kwak, J. Y., Jang, H. J., Kim, I., Kim, J., & Park, J. (2025) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2025.3583057
“Various neuro-morphic systems, which emulate biological neural structures and dynamics, have been developed [1], [2], [3], [4], [5] with efforts to apply them across various fields [6], [7], [8].”
Self-citationHardware architecture and routing-aware training for optimal memory usage: a case study
Weber, J., Ballet, T., & Payvand, M. (2024) · Neuro Inspired Computational Elements Workshop · doi:10.1109/nice65350.2025.11065267 · Cited by 3
“Different event-based NoC schemes have been developed to optimize various metrics such as latency of communication, flexibility of programming, and memory and power footprint [1], [4], [9], [10].”
An Ultra-Low-Power Synthesizable Asynchronous AER Encoder for Neuromorphic Edge Devices
Wang, Y., Peng, S.-Y., & Shah, S. (2026) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas67364.2026.11680645
“To address this, the Address-Event Representation (AER) protocol time-multiplexes spikes into digital addresses over shared buses [4]–[6].”
Thermodynamic constraints as organizing principles of neural efficiency and cognitive architecture
Torres–Martínez, S. (2026) · Biosystems · doi:10.1016/j.biosystems.2026.105921
Metadata
- Authors
- Park, J., Yu, T., Joshi, S., Maier, C., & Cauwenberghs, G.
- Affiliations
- Electronics and Telecommunications Research Institute (KR)
- Texas Instruments (United States) (US)
- University of California San Diego (US)
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2017-10
- Volume
- 28
- Issue
- 10
- Pages
- 2408-2422
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W2501518233
- Cited by
- 118
- References
- 68
- Citations by year
- 2026: 4 · 2025: 9 · 2024: 12 · 2023: 14 · 2022: 16 · 2021: 14 · 2020: 5 · 2019: 18 · 2018: 14 · 2017: 12
- FWCI
- 6.77
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Neural Networks and Learning Systems (publishedVersion)
- PubMed (publishedVersion)
- Funders
- NSF (EFRI-1137279, CCF-1317407)
- ONR (N00014-13-1-0205)
- DARPA (HR0011-10-C-0032 (NeoVision2))
- Evolved Machines
- Texas Instruments
- Qualcomm
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Physical Sciences › Computer Science › Computer Networks and Communications › Interconnection Networks and Systems
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Analog and Mixed-Signal Circuit Design
- Keywords
- neuromorphic systems, axonal delay
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.