LiteCON: An All-Photonic Neuromorphic Accelerator for Energy-efficient Deep Learning (Preprint)

TL;DR

LiteCON is an innovative all-photonic neuromorphic accelerator that significantly enhances energy efficiency and throughput for deep learning, capable of both training and inference, using novel silicon microdisk and memristor technologies.

Contribution

The paper introduces LiteCON, the first all-photonic CNN accelerator that supports both training and inference with high energy efficiency and speed, leveraging silicon microdisk and memristor technologies.

Findings

Up to 32x increase in CNN throughput

Up to 37x improvement in energy efficiency

Up to 5x better computational efficiency

Abstract

Deep learning is highly pervasive in today's data-intensive era. In particular, convolutional neural networks (CNNs) are being widely adopted in a variety of fields for superior accuracy. However, computing deep CNNs on traditional CPUs and GPUs brings several performance and energy pitfalls. Several novel approaches based on ASIC, FPGA, and resistive-memory devices have been recently demonstrated with promising results. Most of them target only the inference (testing) phase of deep learning. There have been very limited attempts to design a full-fledged deep learning accelerator capable of both training and inference. It is due to the highly compute and memory-intensive nature of the training phase. In this paper, we propose LiteCON, a novel analog photonics CNN accelerator. LiteCON uses silicon microdisk-based convolution, memristor-based memory, and dense-wavelength-division-multiplexing for energy-efficient and ultrafast deep learning. We evaluate LiteCON using a commercial CAD framework (IPKISS) on deep learning benchmark models including LeNet and VGG-Net. Compared to the state-of-the-art, LiteCON improves the CNN throughput, energy efficiency, and computational efficiency by up to 32x, 37x, and 5x respectively with trivial accuracy degradation.