US-20260127425-A1 - SEMICONDUCTOR DEVICES OF OPTICAL NEURAL NETWORK AND METHODS OF FORMING THE SAME

US20260127425A1US 20260127425 A1US20260127425 A1US 20260127425A1US-20260127425-A1

Abstract

A semiconductor device includes an oxide layer having a first side and a second side opposite to each other. The semiconductor device includes a plurality of first waveguides that are disposed across a plurality of first insulator layers, respectively, on the first side of the oxide layer. The semiconductor device includes a plurality of second waveguides that are disposed across a plurality of second insulator layers, respectively, on the second side of the oxide layer. The plurality of first waveguides and the plurality of second waveguides collectively form a plurality of photonic neural network layers of an artificial neural network.

Inventors

Weiwei SONG
Stefan Rusu

Assignees

TAIWAN SEMICONDUCTOR MANUFACTURING COMPANY, LTD.

Dates

Publication Date: 20260507
Application Date: 20251229

Claims (20)

1 . A semiconductor device, comprising: an oxide layer having a first side and a second side opposite to each other; a plurality of first waveguides that are disposed across a plurality of first insulator layers, respectively, on the first side of the oxide layer; and a plurality of second waveguides that are disposed across a plurality of second insulator layers, respectively, on the second side of the oxide layer; wherein the plurality of first waveguides and the plurality of second waveguides collectively form a plurality of photonic neural network layers of an artificial neural network; and wherein adjacent ones of the plurality of first waveguides have their respective tapered ends vertically overlapped with each other, and adjacent ones of the plurality of second waveguides have their respective tapered ends vertically overlapped with each other.
2 . The semiconductor device of claim 1 , wherein the plurality of first waveguides and the plurality of second waveguides are each formed of silicon nitride.
3 . The semiconductor device of claim 1 , wherein the plurality of first waveguides and the plurality of second waveguides are each formed of silicon.
4 . The semiconductor device of claim 1 , further comprising: an input optical device formed on the first side of the oxide layer; and an output optical device also formed on the first side of the oxide layer.
5 . The semiconductor device of claim 4 , further comprising: a first interconnect structure extending through the plurality of first insulator layers and electrically coupled to the input optical device.
6 . The semiconductor device of claim 4 , wherein the input optical device is configured to receive a first array of optical signals, at least some of the plurality of first waveguides and the plurality of second waveguides are configured to perform a linear transformation and then a nonlinear transformation on the first array of optical signals into a second array of optical signals, and the output optical device is configured to convert the second array of optical signals into a plurality of electrical signals.
7 . The semiconductor device of claim 4 , wherein the input optical device and the output optical device are both formed below a bottommost one of the plurality of first insulator layers.
8 . The semiconductor device of claim 1 , wherein the plurality of first waveguides and the plurality of second waveguides each have a tapered end, when viewed from the top.
9 . The semiconductor device of claim 4 , further comprising: a second interconnect structure extending through the plurality of first insulator layers and electrically coupled to the output optical device.
10 . The semiconductor device of claim 1 , wherein a respective subset of the plurality of first waveguides disposed in each of the plurality of first insulator layers collectively function as a first one of the plurality of photonic neural network layers, and a respective subset of the plurality of second waveguides disposed in each of the plurality of second insulator layers collectively function as a second one of the plurality of photonic neural network layers.
11 . An apparatus for implementing an artificial neural network, comprising: an input region configured to receive a first optical signal; a neural network region optically coupled to the input region and configured to transform the first optical signal to a second optical signal; and an output region optically coupled to the neural network region and configured to convert the second optical signal into a first electrical signal; wherein the neural network region comprises a plurality of waveguides that have their respective tapered ends vertically overlapped with each other.
12 . The apparatus of claim 11 , wherein the input region includes at least one modulator configured to modulate the first optical signal based on a second electrical signal received through a first via structure.
13 . The apparatus of claim 11 , wherein the input region includes at least one photodetector configured to output the first electrical signal through a second via structure.
14 . The apparatus of claim 11 , wherein the plurality of waveguides are each formed of silicon nitride.
15 . The apparatus of claim 11 , wherein the plurality of waveguides are each formed of silicon.
16 . The apparatus of claim 11 , wherein the neural network region comprises the plurality of waveguides that are disposed across a plurality of vertically stacked insulator layers, respectively.
17 . The apparatus of claim 11 , wherein the plurality of waveguides collectively form at least one of a sequence of layers of an artificial neural network.
18 . A method for making semiconductor devices, comprising: forming a plurality of optical devices in an overlaying silicon layer disposed on a first side of a silicon-on-insulator (SOI) substrate; forming, over the plurality of optical devices, a plurality of first waveguides disposed across a plurality of first insulator layers, respectively; and forming, over a second side of the SOI substrate opposite to the first side, a plurality of second waveguides disposed across a plurality of second insulator layers, respectively; wherein the plurality of first waveguides and the plurality of second waveguides collectively form a plurality of photonic neural network layers of an artificial neural network; and wherein adjacent ones of the plurality of first waveguides have their respective tapered ends vertically overlapped with each other, and adjacent ones of the plurality of second waveguides have their respective tapered ends vertically overlapped with each other.
19 . The method of claim 18 , wherein the plurality of first waveguides and the plurality of second waveguides are each formed of silicon nitride, silicon, or combinations thereof.
20 . The method of claim 18 , further comprising: attaching a carrier substrate to the SOI substrate with the plurality of first waveguides interposed therebetween; flipping the SOI substrate; removing an underlying silicon layer disposed on the second side of the SOI substrate to form the plurality of second waveguides; and forming a plurality of interconnect structures electrically coupled to the plurality of optical devices, respectively.

Description

CROSS-REFERENCE TO RELATED APPLICATION This application is a continuation of U.S. Utility application Ser. No. 17/844,192, filed Jun. 20, 2022, the entire disclosure of which is incorporated herein by reference for all purposes. BACKGROUND The semiconductor industry has experienced rapid growth due to continuous improvements in the integration density of a variety of electronic components. Electrical signaling and processing are one technique for signal transmission and processing. Optical signaling and processing have been used in increasingly more applications in recent years, due to the use of optical fiber-related applications for signal transmission. BRIEF DESCRIPTION OF THE DRAWINGS Aspects of the present disclosure are best understood from the following detailed description when read with the accompanying figures. It is noted that, in accordance with the standard practice in the industry, various features are not drawn to scale. In fact, the dimensions of the various features may be arbitrarily increased or reduced for clarity of discussion. FIG. 1 illustrates an example arrangement of components of a photonic neural network system, in accordance with some embodiments. FIG. 2 illustrates a top view of the photonic neural network system of FIG. 1, in accordance with some embodiments. FIG. 3 illustrates a first example cross-sectional view of a portion of the photonic neural network system of FIG. 1, in accordance with some embodiments. FIG. 4 illustrates a second example cross-sectional view of a portion of the photonic neural network system of FIG. 1, in accordance with some embodiments. FIG. 5A illustrates a cross-sectional view of two waveguides, in accordance with some embodiments. FIG. 5B illustrates a corresponding top view of the two waveguides in FIG. 5A, in accordance with some embodiments. FIGS. 6A-6H illustrate cross-sectional views of an example photonic neural network system during various fabrication stages, in accordance with some embodiments. FIG. 7 is an example flow chart of a method for fabricating a photonic neural network system, in accordance with some embodiments. DETAILED DESCRIPTION The following disclosure provides many different embodiments, or examples, for implementing different features of the provided subject matter. Specific examples of components and arrangements are described below to simplify the present disclosure. These are, of course, merely examples and are not intended to be limiting. For example, the formation of a first feature over, or on a second feature in the description that follows may include embodiments in which the first and second features are formed in direct contact, and may also include embodiments in which additional features may be formed between the first and second features, such that the first and second features may not be in direct contact. In addition, the present disclosure may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. Further, spatially relative terms, such as “beneath,” “below,” “lower,” “above,” “upper” “top,” “bottom” and the like, may be used herein for ease of description to describe one element or feature's relationship to another element(s) or feature(s) as illustrated in the figures. The spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. The apparatus may be otherwise oriented (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein may likewise be interpreted accordingly. Optical signaling and processing are typically combined with electrical signaling and processing to provide full-fledged applications. For example, optical fibers may be used for long-range signal transmission, and electrical signals may be used for short-range signal transmission as well as processing and controlling. Accordingly, devices integrating optical components and electrical components are formed for the conversion between optical signals and electrical signals, as well as the processing of optical signals and electrical signals. Packages thus may include a number of optical (or photonic) dies each having various optical devices, and a number of electronic dies each having various electronic devices. The present disclosure provides multi-layers of SiN to perform photonic neural network operation. In some embodiments, the high speed conversion between optical signals and electrical signals can be realized on a silicon-on-insulator (SOI) layer. Electronic neural network has been intensively investigated for artificial intelligence, big data, and machine learning applications. However, speed of the electronic neural network may be bottlenecked by data exchanging speed among computing blocks, communications with