Litcius/Paper detail

DeepFire: Acceleration of Convolutional Spiking Neural Network on Modern Field Programmable Gate Arrays

Myat Thu Linn Aung, Chuping Qu, Liwei Yang, Tao Luo, Rick Siow Mong Goh, Weng‐Fai Wong

202118 citationsDOI

Abstract

Spiking neural networks (SNN) with their ‘integrate and fire’ (I&F) neurons replace the hardware-intensive multiply-accumulate (MAC) operations in convolutional neural networks (CNN) with accumulate operations — not only making it easy to implement on FPGAs but also opening up the opportunities for energy-efficient hardware acceleration. In this paper, we propose DeepFire — the high-performance RTL IP — for accelerating convolutional SNN inference. The IP exploits various resources available on modern FPGAs, and it outperforms existing SNN implementations by more than 10× in terms of both frame per second (FPS) and performance per watt (FPS/Watt). Our design achieves up to 40.1kFPS and 28.3kFPS on MNIST and CIFAR-10/SVHN datasets with 99.14% and 81.8%/93.1% accuracies respectively. IP was evaluated with 7-series and Ultrascale+ FPGAs from Xilinx achieving Fmax of 375MHz and 500MHz respectively.

Topics & Concepts

Field-programmable gate arrayComputer scienceMNIST databaseConvolutional neural networkSpiking neural networkHardware accelerationFrame (networking)AccelerationInferenceExploitComputer architectureComputer hardwareEmbedded systemParallel computingComputer engineeringArtificial neural networkArtificial intelligenceComputer networkPhysicsComputer securityClassical mechanicsAdvanced Memory and Neural ComputingFerroelectric and Negative Capacitance DevicesNeuroscience and Neural Engineering
DeepFire: Acceleration of Convolutional Spiking Neural Network on Modern Field Programmable Gate Arrays | Litcius