Photonic in-memory co-processor for convolutional operations

US11556312B2 · kind B2 · utility

Assignees

• International Business Machines Corporation · US
• OXFORD UNIVERSITY INNOVATION LIMITED · GB
• UNIVERSITY OF EXETER · GB
• University of Muenster · DE

Inventors

• Abu Sebastian · Zürich, CH
• Manuel Le Gallo-Bourdeau · Zürich, CH
• Christopher Wright · Lympstone, GB
• Nathan Youngblood · North Hinksey, GB
• Harish Bhaskaran · North Hinksey, GB
• Xuan Li · Sunnyvale, US
• Wolfram Pernice · Münster, DE
• Johannes Feldmann · Münster, DE

Key dates

• Filing date: Jul 10, 2020
• Grant date: Jan 17, 2023
• Expiry date: Feb 4, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/0675
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A co-processor for performing a matrix multiplication of an input matrix with a data matrix in one step may be provided. The co-processor receives input signals for the input matrix as optical signals. A plurality of photonic memory elements is arranged at crossing points of an optical waveguide crossbar array. The plurality of memory elements is configured to store values of the data matrix. Input signals are connected to input lines of the optical waveguide crossbar array. Output lines of the optical waveguide crossbar array represent a dot-product between a respective column of the optical waveguide crossbar array and the received input signals, and values of elements of the input matrix to be multiplied with the data matrix correspond to light intensities received at input lines of the respective photonic memory elements. Additionally, different wavelengths are used for each column of the input matrix optical signals.