Stanley S. Cheung

The perspective of all-silicon photonics and systems

Yuan Yuan, Yiwei Peng, Stanley S. Cheung, Xian Xiao et autres

Silicon photonics has emerged as a transformative solution to address the energy and bandwidth challenges of modern computing and communication systems. While integrating diverse materials with silicon has enhanced the functionality of photonic integrated circuits, these hybrid approaches often face challenges related …

us (code pays fourni par la source)

Heterogeneous III-V/Si micro-ring laser array with multi-state non-volatile memory for ternary content-addressable memories

Stanley S. Cheung, Yanir London, Yuan Yuan, Bassem M. Tossoun et autres

In this work, we introduce programmable memory elements embedded within III-V/Si light sources which facilitate non-volatile wavelength tuning. These non-volatile III-V/Si micro-ring lasers (MRLs) exhibit non-volatile wavelength shifts of ~80 pm with ~40 dB signal extinction ratio while consuming 0 electrical static …

us (code pays fourni par la source)

All-silicon non-volatile optical memory based on photon avalanche-induced trapping

Yuan Yuan, Yiwei Peng, Stanley S. Cheung, Wayne V. Sorin et autres

Abstract Implementing on-chip non-volatile optical memories has long been an actively pursued goal, promising significant enhancements in the capability and energy efficiency of photonic integrated circuits. Here, we demonstrate an non-volatile optical memory exclusively using the most common semiconductor material, silicon. By …

us (code pays fourni par la source)

Optical content-addressable memories for tree-based machine learning

Yanir London, Luca Buonanno, Lei Ping Zhao, Giacomo Pedretti et autres

In this work, we describe the hardware implementation of a decision tree (DT) model using our microring-based timedivision multiplexing (TDM) optical content-addressable memory (O-CAM) architecture, which uses a customized encoding scheme that allows ternary search. Mainstream machine learning models, such as neural …

Roadmap on Neuromorphic Photonics

Daniel Brunner, Bhavin J. Shastri, Mohammed Qadasi, Hitesh Ballani et autres

This roadmap consolidates recent advances while exploring emerging applications, reflecting the remarkable diversity of hardware platforms, neuromorphic concepts, and implementation philosophies reported in the field. It emphasizes the critical role of cross-disciplinary collaboration in this rapidly evolving field.

fr, be, de, us, ca (code pays fourni par la source)

Large-Scale Integrated Photonic Device Platform for Energy-Efficient AI/ML Accelerators

Bassem M. Tossoun, Xian Xiao, Stanley S. Cheung, Yuan Yuan et autres

The convergence of deep learning and big data has spurred significant interest in developing novel hardware that can run large artificial intelligence (AI) workloads more efficiently. Over the last several years, silicon photonics has emerged as a disruptive technology for next-generation accelerators …

us, in, gb (code pays fourni par la source)

Photonic KAN: a Kolmogorov-Arnold Network Inspired Efficient Neuromorphic Accelerator

Yiwei Peng, Sean Hooten, Xinling Yu, Thomas Van Vaerenbergh et autres

We propose Photonic Kolmogorov-Arnold Networks, leveraging optical non-linear transfer functions along edges. It achieves 2300×reduction in footprint-energy efficiency, alongside a 7× reduction in latency compared to previous photonic accelerators.

us (code pays fourni par la source)

In-Memory Optical Computing with Non-Volatile Silicon Photonic Memory

Bassem M. Tossoun, Di Liang, Stanley S. Cheung, Yuan Yuan et autres

Research in non-volatile memory on silicon photonic integrated circuits is advancing rapidly. We explore recent progress in this emerging area and discuss their applications within programmable PICs for machine learning, artificial intelligence, and quantum computing.

us, ie (code pays fourni par la source)

Silicon Photonics Platform and Optical Memory

Yuan Yuan, Stanley S. Cheung, Yiwei Peng, Di Liang et autres

We introduce a silicon photonics platform that maximally harnesses the potential of both the heterogeneous III-V material system and silicon, supporting a diverse range of high-performance optoelectronic devices, including lasers, optical amplifiers, modulators, photodetectors, and emerging non-volatile optical memories. This platform delivers …

us (code pays fourni par la source)

Arrays of Non-Volatile III-V/Si Micro-Ring Lasers for Memory Search Applications

Stanley S. Cheung, Yanir London, Yuan Yuan, Bassem M. Tossoun et autres

We explore the use of non-volatile III-V/Si ring lasers as storage elements in wavelength-division multiplexed (WDM) optical ternary content-addressable memory (O-TCAM) search. This provides new opportunity for photonic memory applications in non-volatile photonic systems.

us (code pays fourni par la source)

Heterogeneous III-V/Si Micro-Ring Laser Array with Multi-State Non-Volatile Memory for Ternary Content-Addressable Memories

Stanley S. Cheung, Yanir London, Yuan Yuan, Bassem M. Tossoun et autres

us (code pays fourni par la source)

Hybrid III-V/Si Micro-Ring Laser with Non-Volatile Charge Trap Memory

Stanley S. Cheung, Dong Liang, Yuan Yuan, Bassem M. Tossoun et autres

We demonstrate hybrid III-V/Si microring lasers with optical non-volatility via co-integrated charge trap memory. Multi-state (4 states) optical memory is achieved with non-volatile duration up to 24 hours and most likely beyond.

us (code pays fourni par la source)