A Large-Scale Spiking Neural Network Accelerator for FPGA Systems

Cheung, Kit; Schultz, Simon R.; Luk, Wayne

doi:10.1007/978-3-642-33269-2_15

Cited by 47 publications

(34 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This optimization is based on the fact that new neuron states do not need to be calculated at every single time step but only in the instances that a new input arrives at the neuron, as otherwise the neuron state would not change. To improve on their initial memory-bandwidth requirements [4], Cheung et al replaced the FPGA board with a Maxeler Dataflow Machine [5]. This FPGA-based device features state-of-the-art memory systems that increase the bandwidth capabilities greatly compared to simple FPGA boards.…”

Section: Related Workmentioning

confidence: 98%

“…Two of the most notable implementations using Izhikevich neurons are the designs proposed by Cheung et al [5,4] and by Moore et al (Bluehive [15]). Each approach proposed an FPGA architecture for very large-scale SNNs which is event-driven for optimizing the network traffic and the assorted memory-bandwidth needs.…”

Section: Related Workmentioning

confidence: 98%

“…Izhikevich models are useful for researching the dynamics of large neural networks. Their simplicity also allows for the implementation of very large network sizes in FPGA devices, as described in [5] and [15], achieving sizes already significant to actual brain subsystems (tens of thousands of neurons). A little more costly than the IaF, each Izhikevich neuron model requires 13 operations per 1ms.…”

Section: Comparison To Related Workmentioning

confidence: 99%

See 2 more Smart Citations

FPGA-based biophysically-meaningful modeling of olivocerebellar neurons

Smaragdos

Isaza

Eijk

et al. 2014

Proceedings of the 2014 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays

View full text Add to dashboard Cite

The Inferior-Olivary nucleus (ION) is a well-charted region of the brain, heavily associated with sensorimotor control of the body. It comprises ION cells with unique properties which facilitate sensory processing and motor-learning skills. Various simulation models of ION-cell networks have been written in an attempt to unravel their mysteries. However, simulations become rapidly intractable when biophysically plausible models and meaningful network sizes (≥100 cells) are modeled. To overcome this problem, in this work we port a highly detailed ION cell network model, originally coded in Matlab, onto an FPGA chip. It was first converted to ANSI C code and extensively profiled. It was, then, translated to HLS C code for the Xilinx Vivado toolflow and various algorithmic and arithmetic optimizations were applied. The design was implemented in a Virtex 7 (XC7VX485T) device and can simulate a 96-cell network at real-time speed, yielding a speedup of ×700 compared to the original Matlab code and ×12.5 compared to the reference C implementation running on a Intel Xeon 2.66GHz machine with 20GB RAM. For a 1,056-cell network (non-real-time), an FPGA speedup of ×45 against the C code can be achieved, demonstrating the design's usefulness in accelerating neuroscience research. Limited by the available on-chip memory, the FPGA can maximally support a 14,400-cell network (non-real-time) with online parameter configurability for cell state and network size. The maximum throughput of the FPGA IONnetwork accelerator can reach 2.13 GFLOPS.

show abstract

Section: Related Workmentioning

confidence: 98%

Section: Related Workmentioning

confidence: 98%

Section: Comparison To Related Workmentioning

confidence: 99%

See 1 more Smart Citation

FPGA-based biophysically-meaningful modeling of olivocerebellar neurons

Smaragdos

Isaza

Eijk

et al. 2014

Proceedings of the 2014 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays

View full text Add to dashboard Cite

show abstract

“…Qualitative and quantitative comparison of the FPGA with alternatives (for example, XC5VLX330T compared with Core2/3GHz and GT200/1.2GHz) were given in [1][2][3][4]. In the case of solving complex problems we have a clear superiority of the approach in time and productivity.…”

Section: Introductionmentioning

confidence: 99%

FPGA implementations of scale-invariant models of neural networks

Zhanabaev¹,

Kozhagulov²,

Zhexebay³

2016

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Integrated circuit implementations of new models of neural networks with scale-invariant properties are presented. The specifics of such models are necessary in analysis of discrete mappings containing fractional power. We suggest an algorithm for increasing the power of a physical value by using a field-programmable gate array (FPGA).Comparisons between FPGA implementations and numerical results are demonstrated.

show abstract

“…Another design based in the Izhikevich neurons is presented in [21]. The authors propose a Izhikevich neuron [10] simulator capable of simulating 64000 cells.…”

Section: -1 Related Workmentioning

confidence: 99%

Multi-chip dataflow architecture for massive scale biophysically accurate neuron simulation

Hofmann

Zjajo

Galuzzi

et al. 2016

2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

The ability to simulate brain neurons in real-time using biophysically-meaningful models is a critical pre-requisite grasping human brain behavior. By simulating neurons' behavior, it is possible, for example, to reduce the need for in-vivo experimentation, to improve artificial intelligence and to replace damaged brain parts in patients. A biophysically accurate but complex neuron model, which can be used for such applications, is the Hodgkin-Huxley (HH) model. State of the art simulators are capable of simulating, in real-time, tens of neurons, at most. The currently most advanced simulator is able to simulate 96 HH neurons in real-time. This simulator is limited by its exponential growth in communication costs. To overcome this problem, in this thesis, we propose a new system architecture, which massively increases the amount of neurons which is possible to simulate. By localizing communications, the communication cost is reduced from an exponential to a linear growth with the number of simulated neurons As a result, the proposed system allows the simulation of over 3000 to 19200 cells (depending on the connectivity scheme). To further increase the number of simulated neurons, the proposed system is designed in such a way that it is possible to implement it over multiple chips. Experimental results have shown that it is possible to use up to 8 chips and still keeping the communication costs linear with the number of simulated neurons. The systems is very flexible and allows to tune, during run-time, various parameters, including the presence of connections between neurons, eliminating (or reducing) resynthesis costs, which turn into much faster experimentation cycles. All parts of the system are generated automatically, based on the neuron connectivity scheme. A powerful simulator that incorporates latencies for on and off chip communication, as well as calculation latencies, can be used to find the right configuration for a particular task. As a result, the resulting highly adaptive and configurable system allows for biophysicallyaccurate simulation of massive amounts of cells. The undersigned hereby certify that they have read and recommend to the Faculty of Electrical Engineering, Mathematics and Computer Science for acceptance a thesis entitled "Multi-chip dataflow architecture for massive scale biophysically accurate neuron simulation" by Jaco A. Hofmann in partial fulfillment of the requirements for the degree of Master of Science. AbstractThe ability to simulate brain neurons in real-time using biophysically-meaningful models is a critical pre-requisite grasping human brain behavior. By simulating neurons' behavior, it is possible, for example, to reduce the need for in-vivo experimentation, to improve artificial intelligence and to replace damaged brain parts in patients. A biophysically accurate but complex neuron model, which can be used for such applications, is the Hodgkin-Huxley (HH) model. State of the art simulators are capable of simulating, in real-time, tens of neurons, at most. The...

show abstract

A Large-Scale Spiking Neural Network Accelerator for FPGA Systems

Cited by 47 publications

References 10 publications

FPGA-based biophysically-meaningful modeling of olivocerebellar neurons

FPGA-based biophysically-meaningful modeling of olivocerebellar neurons

FPGA implementations of scale-invariant models of neural networks

Multi-chip dataflow architecture for massive scale biophysically accurate neuron simulation

Contact Info

Product

Resources

About