A Compact 14 GS/s 8-Bit Switched-Capacitor DAC in 16 nm FinFET CMOS

Caragiulo, P.; Mattia, Oscar E.; Arbabian, Amin; Murmann, Boris

doi:10.1109/vlsicircuits18222.2020.9162776

Cited by 7 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We further evaluate the power consumption for static inference tasks, where the weights can be considered constant. We assumed the power required for sending and receiving an optical signal of 13.3 pJ/clock, which includes the power of an ADC, 55 a digital-to-analog converter (DAC), 56 and other components of optical interconnection such as lasers, transimpedance amplifiers, and PDs (see the Supporting Information, Section VII). In addition, the power of phase shifters should be taken into account.…”

Section: ■ Resultsmentioning

confidence: 99%

Si Microring Resonator Crossbar Array for On-Chip Inference and Training of the Optical Neural Network

Ohno¹,

Toprasertpong²,

Takagi³

et al. 2022

ACS Photonics

View full text Add to dashboard Cite

Deep learning has been a powerful tool in various fields. Faced with the limits of the current electronics platform, optical neural networks (ONNs) based on Si programmable photonic integrated circuits (PICs) have attracted considerable attention as a novel deep-learning scheme with optical-domain matrix-vector multiplication (MVM). However, most of the proposed Si programmable PICs for ONNs have several drawbacks, such as low scalability, high power consumption, and lack of frameworks for training. To address these issues, we have proposed a microring resonator (MRR) crossbar array as a Si programmable PIC for an ONN. In this Article, we present a prototype of a fully integrated 4 × 4 MRR crossbar array for MVM and demonstrate a simple image classification task using this chip. Moreover, we propose on-chip backpropagation using the transpose matrix operation of the MRR crossbar array, enabling the on-chip training of the ONN. The proposed ONN scheme can establish a scalable, power-efficient deep-learning accelerator for both inference and training tasks.

show abstract

Section: ■ Resultsmentioning

confidence: 99%