JJ-Soma: Toward a Spiking Neuromorphic Processor Architecture

Karamuftuoglu, Mustafa Altay; Bozbey, Ali; Razmkhah, Sasan

doi:10.1109/tasc.2023.3270766

Cited by 5 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our design, SFQ pulses from presynaptic connections are accumulated in both positive and negative branches, and then the two values are summed up. The value u is provided to the JJ-Soma [15], which acts as an activation function. The main component of such a comparator is a SQUID with an interrupted resistor.…”

Section: Model and Methodologymentioning

confidence: 99%

“…Superconductor electronics have long been regarded as a promising candidate for neural networks, with researchers exploring their potential for many years [12][13][14][15][16][17][18][19][20][21]. In [13], the authors introduce spiking neurons with standard superconductor components and a SQUID structure.…”

Section: Introductionmentioning

confidence: 99%

“…The proposed synapse design incorporates negative and positive weights. It is interfaced with a quantizer/buffer circuit to propagate the accumulated post-synaptic result into the JJ-Soma cell [15], which performs a somatic activation function and is compatible with the proposed structure. The whole integration, comprising JJ-Synapse, JJ-Soma, and a buffer, will mimic a neuron with an integrate-and-fire neuron model and with its synaptic connections.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hybrid synaptic structure for spiking neural network realization

Razmkhah,

Karamuftuoglu,

Bozbey

2024

Supercond. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Neural networks and neuromorphic computing represent fundamental paradigms as alternative approaches to Von-Neumann-based implementations, advancing in the applications of deep learning and machine vision. Nonetheless, conventional semiconductor circuits encounter challenges in achieving ultra-fast processing speed and low power consumption due to their dissipative properties. Conversely, single flux quantum (SFQ) circuits exhibit inherent spiking behavior, showcasing their characteristics as a promising candidate for spiking neural networks (SNNs). In this work, we present a compact hybrid synapse circuit to mimic the biological interconnect functionality, enabling the weighting operations for excitatory and inhibitory impulses. Additionally, the proposed structure facilitates input accumulation, which is performed before the activation function. In the experiments, our synaptic structure interfaces with a soma circuit fabricated using a commercial Nb process, underscoring its compatibility and supporting its potential for integration into efficient neural network architectures. The weight value on the synapse is configurable by utilizing cryo-CMOS circuits, providing adaptability to the inference networks. We’ve successfully designed, fabricated, and partially tested the JJ-Synapse within our cryocooler system, enabling high-speed inference implementation for SNNs.

show abstract

Section: Model and Methodologymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid synaptic structure for spiking neural network realization

Razmkhah,

Karamuftuoglu,

Bozbey

2024

Supercond. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…A non-spiking superconducting XOR neural network was experimentally demonstrated [31]. Several proposals demonstrate individual SFQ gates for neuronal [5][6][7]15], synaptic [7][8][9]32], or interconnect [10] functionality. Two-neuron oscillatory Hopfield networks [11,12] and single layer feed-forward spiking networks [13,[16][17][18] have been proposed, and a multi-layer feed-forward spiking network with heterogeneous CMOS-SFQ circuitry has been demonstrated in simulation [14].…”

Section: Single Flux Quanta Circuitrymentioning

confidence: 99%

“…Whereas modern large scale SNNs utilize inefficient packet-based routing networks [2][3][4], SFQ may be ideally suited for ultra-fast, ultra-low power SNN systems. The similarities between SFQ pulses and neuronal spiking have been explored in the literature [5][6][7][8][9][10][11][12][13][14][15][16][17], with synapses modifying the amplitude of spiking events.…”

Section: Introductionmentioning

confidence: 99%

Harnessing stochasticity for superconductive multi-layer spike-rate-coded neuromorphic networks

Edwards,

Krylov,

Friedman

et al. 2024

Neuromorph. Comput. Eng.

View full text Add to dashboard Cite

Conventional semiconductor-based integrated circuits are gradually approaching fundamental scaling limits. Many prospective solutions have recently emerged to supplement or replace both the technology on which basic devices are built and the architecture of data processing.Neuromorphic circuits are a promising approach to computing where techniques used by the brain to achieve high efficiency are exploited. Many existing neuromorphic circuits rely on unconventional and useful properties of novel technologies to better mimic the operation of the brain.One such technology is single flux quantum (SFQ) logic -- a cryogenic superconductive technology in which the data are represented by quanta of magnetic flux (fluxons) produced and processed by Josephson junctions embedded within inductive loops.The movement of a fluxon within a circuit produces a quantized voltage pulse (SFQ pulse), resembling a neuronal spiking event. These circuits routinely operate at clock frequencies of tens to hundreds of gigahertz, making SFQ a natural technology for processing high frequency pulse trains.This work harnesses thermal stochasticity in superconducting synapses to emulate stochasticity in biological synapses in which the synapse probabilistically propagates or blocks incoming spikes. The authors also present neuronal, fan-in, and fan-out circuitry inspired by the literature that seamlessly cascade with the synapses for deep neural network construction. Synapse weights and neuron biases are set with bias current, and the authors propose multiple mechanisms for training the network and storing weights. The network primitives are successfully demonstrated in simulation in the context of a rate-coded multi-layer XOR neural network which achieves a wide classification margin. The proposed methodology is based solely on existing SFQ technology and does not employ unconventional superconductive devices or semiconductor transistors, making this proposed system an effective approach for scalable cryogenic neuromorphic computing.

show abstract

SuperSIM: a comprehensive benchmarking framework for neural networks using superconductor Josephson devices

Zhu,

Kan,

Zhang

et al. 2024

Supercond. Sci. Technol.

View full text Add to dashboard Cite

This paper introduces SuperSIM, a benchmarking framework tailored for neural networks using superconducting Josephson devices, specifically focusing on Adiabatic Quantum Flux Parametron (AQFP) based Processing-in-Memory (PIM) architectures. Our framework offers in-depth architecture-level simulations and performance assessments to enhance AQFP PIM chip development. It supports single and multi-bit PIM designs, various AQFP memory cell types, and diverse clocking methods. Additionally, it integrates circuit-level models for precise energy, delay, and area measurements, ensuring accurate performance evaluation. The framework includes application, device, and architectural layers for versatile configurations and cycle-accurate energy, latency, and area simulations. Experiments validate our framework, with case studies on algorithm and architecture-level features, examining data precision, crossbar size, operating frequency and clocking scheme impacts on computational accuracy, energy use, overall latency and hardware cost.

show abstract

JJ-Soma: Toward a Spiking Neuromorphic Processor Architecture

Cited by 5 publications

References 44 publications

Hybrid synaptic structure for spiking neural network realization

Hybrid synaptic structure for spiking neural network realization

Harnessing stochasticity for superconductive multi-layer spike-rate-coded neuromorphic networks

SuperSIM: a comprehensive benchmarking framework for neural networks using superconductor Josephson devices

Contact Info

Product

Resources

About