TeMPO: Efficient Time-Multiplexed Dynamic Photonic Tensor Core for Edge AI with Compact Slow-Light Electro-Optic Modulator
Electronic-photonic computing systems offer immense potential in energy-efficient artificial intelligence (AI) acceleration tasks due to the superior computing speed and efficiency of optics, especially for real-time, low-energy deep neural network (DNN) inference tasks on resource-restricted edge platforms. However, current optical neural accelerators based on foundry-available devices and conventional system architecture still encounter a performance gap compared to highly customized electronic counterparts. To bridge the performance gap due to lack of domain specialization, we present a time-multiplexed dynamic photonic tensor accelerator, dubbed TeMPO, with cross-layer device/circuit/architecture customization. At the device level, we present foundry-compatible, customized photonic devices, including a slow-light electro-optic modulator with experimental demonstration, optical splitters, and phase shifters that significantly reduce the footprint and power in input encoding and dot-product calculation. At the circuit level, partial products are hierarchically accumulated via parallel photocurrent aggregation, lightweight capacitive temporal integration, and sequential digital summation, considerably relieving the analog-to-digital conversion bottleneck. We also employ a multi-tile, multi-core architecture to maximize hardware sharing for higher efficiency. Across diverse edge AI workloads, TeMPO delivers digital-comparable task accuracy with superior quantization/noise tolerance. We achieve a 368.6 TOPS peak performance, 22.3 TOPS/W energy efficiency, and 1.2 TOPS/mm$^2$ compute density, pushing the Pareto frontier in edge AI hardware. This work signifies the power of cross-layer co-design and domain-specific customization, paving the way for future electronic-photonic accelerators with even greater performance and efficiency.
Code (0)
등록된 구현이 없습니다.
Tasks
QuantizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Deep Binarized Photonic Reservoir Computing for Ultrafast Multimedia Signal Processing
We present a deep photonic neural network architecture based on ultrafast binary optical modulation from a digital micro-mirror device (DMD), optical scattering in random medium, high-speed photodetection with a CMOS sen…
Speech RecognitionCharacterization of the frequency response of channel-interleaved photonic ADCs based on the optical time-division demultiplexer
We characterize the frequency response of channel-interleaved photonic analog-to-digital converters (CI-PADCs) theoretically and experimentally. The CI-PADC is composed of a photonic frontend for photonic sampling and an…
QuantizationDOCTOR: Dynamic On-Chip Temporal Variation Remediation Toward Self-Corrected Photonic Tensor Accelerators
Photonic computing has emerged as a promising solution for accelerating computation-intensive artificial intelligence (AI) workloads, offering unparalleled speed and energy efficiency, especially in resource-limited, lat…
Edge-computingUnsupervised Image Classification Through Time-Multiplexed Photonic Multi-Layer Spiking Convolutional Neural Network
We present results of a deep photonic spiking convolutional neural network, based on two-section VCSELs, targeting image classification. Training is based on unsupervised spike-timing dependent plasticity, whereas neuron…
image-classificationImage ClassificationUnsupervised Image ClassificationWhat Is Next for LLMs? Next-Generation AI Computing Hardware Using Photonic Chips
Large language models (LLMs) are rapidly pushing the limits of contemporary computing hardware. For example, training GPT-3 has been estimated to consume around 1300 MWh of electricity, and projections suggest future mod…