CN108604940B

CN108604940B - Optoelectronic switch

Info

Publication number: CN108604940B
Application number: CN201680077887.1A
Authority: CN
Inventors: A.里克曼; N.法林顿; A.S.纳格拉
Original assignee: Rockley Photonics Ltd
Current assignee: Rockley Photonics Ltd
Priority date: 2015-11-05
Filing date: 2016-11-04
Publication date: 2020-06-19
Anticipated expiration: 2036-11-04
Also published as: CN108604940A; CN108476080B; CN108476080A; WO2017077094A1; WO2017077093A2; WO2017077093A3

Abstract

The present invention provides a switch module for use in an optoelectronic switch, the switch module having: a client portion for connecting to an input device or an output device; a first component (fabric) and a second component each for processing signals and communicating with other switch modules, the first component having a transmit side and a receive side, the transmit side having: a transmit side input for receiving a first electronic signal carrying information, the information comprising information about a destination switch module of the first electronic signal, the first electronic signal being received from an output or input device of the second component part via the client part; a transmission-side conversion means for converting the first electronic signal into a first plurality of optical signals containing the same information; a transmit side multiplexer for converting the first plurality of optical signals into a multiplexed fabric output signal for transmission to an active switch, and the receive side having: a receive-side demultiplexer to receive a multiplexed fabric input signal from an active switch and to separate the multiplexed fabric input signal into a second plurality of optical signals; a receiving-side converting means for converting the second plurality of optical signals into second electrical signals; and a receive side output for sending the second electronic signal via the client portion to a transmit side input or output of the second component portion.

Description

Optoelectronic switch

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority and benefit from U.S. provisional application No. 62/251,572 entitled "Optical Switch architecture" filed on 5.11.2015, which is incorporated herein by reference in its entirety.

Technical Field

One or more aspects in accordance with embodiments of the present invention relate to switch modules that can be used in optoelectronic switches, and also to optoelectronic switches that incorporate the switch modules.

Background

The current and continuing increase in data traffic and the data center requirements for switching speed and reduced energy consumption have led to a number of recent innovations. In particular, it has been recognized that optical switching (optical switching) provides many desirable properties, but that optical devices need to be controlled by and used with electronic devices, including traditional electronic data servers.

The optical device itself does not necessarily reduce the size or complexity of the switch. In order to improve flexibility in assembling and applying the optical switch unit, it is desirable to improve scalability (scalability) of the optical switch. An improved approach involves the topology of components within a switch network. It is desirable to produce highly scalable optical switching units. Thus, there remains a need for a packet switch that optimally benefits from the speed of optics and the flexibility of CMOS electronics assembled in an architecture suitable for large scalability.

To describe most clearly a network topology, such as a computer network or an optical switching network, as in embodiments of the present invention, the following terms and notations may be used:

graph G is a set of vertices V and a set of edges E, the edges connecting pairs of vertices. The graph may be represented as G ═ V, E. Thus, the network may be modeled as a graph, where nodes (i.e., individual switching elements) are represented by vertices and the links between pairs of nodes are graph edges.

The physical topology of the network is the location in real 3D space of nodes and links. The logical topology of the network is mathematically represented as graph G ═ of (V, E) of the network.

The base number R of a single switching element is the number of ports on the switching element. A switch port may be a client port (connected to an external client such as a host or server) or a fabric port (connected to other switching elements), or unconnected. The number of client ports per switching unit is C and the number of fabric interfaces per switching element is F.

A path is a sequence of links connecting a source node to a destination node, and the length of the path is the number of links in the sequence. The smallest path between two nodes is the path with the shortest length, and the diameter of the network is the longest smallest path between any two nodes. The switching elements in a switch may be arranged in N dimensions (also referred to herein as layers (tier)).

The known named network topology is the folded claus network. This is a common topology currently used in data center networks and multi-chip switches. The topology is also referred to as a k-ary n-tree. The network can be described with only R and N:

C_{general assembly}Total number of client ports, i.e.

Diameter, D ═ 2(N-1)

Table 1 below shows the value of N, the number of client ports for various different values of the parameter, which, as mentioned above, indicates the number of external clients connectable using such a network with the given parameter.

Table 1: the value of N for a folded claus network with varying values of R and N.

Fig. 15A to C show examples of folded claus network arrangements with different values of N and R, and C thereof_{General assembly}P and D. Clearly, when used in an actual switching network, the number of switching elements used is much larger than that shown in these figures. In these examples, the client ports are in each case represented by unconnected links on the bottom row of switching elements. Herein, the term "leaf" may be used for switching elements connected to both clients and other switching elements, and "backbone" may be used for those switches connected to only other leaves. In this application, the terms "backbone" and "active switch" may also be used interchangeably.

Summary of The Invention

Most generally, embodiments of the present invention provide an optoelectronic switch having a plurality of switching elements organized using an improved (physical) network topology that yields great scalability improvements. In order to realize an optoelectronic switch using an improved physical topology, the switching elements that make up the optoelectronic switch must have specific characteristics, and specific connection capabilities. In particular, the switching elements acting as leaves, referred to herein as "switch modules," may require certain internal components for optimal performance. Accordingly, a first aspect of an embodiment of the present invention provides a switch module for use in an optoelectronic switch, the switch module having:

a client portion for connecting to an input device or an output device;

a first component part and a second component part each for processing signals and communicating with other switch modules, the first component part having a transmission side and a reception side,

the transmission side has:

a transmit side input to receive a first electronic signal carrying information, the information comprising information about a destination switch module of the first electronic signal, the first electronic signal received via the client portion from:

an output of said second component, or

An input device;

a transmission-side conversion means for converting the first electronic signal into a first plurality of optical signals containing the same information;

a transmit-side multiplexer for converting the first plurality of optical signals into a multiplexed fabric output signal for transmission to an active switch, and

the receiving side has:

a receive-side demultiplexer to receive a multiplexed fabric input signal from an active switch and to separate the multiplexed fabric input signal into a second plurality of optical signals;

a receiving side converting means for converting the second plurality of optical signals into a second electrical signal, an

A receive-side output to send, via the client portion, the second electronic signal to:

the transmission-side input of said second component, or

And an output device.

To avoid confusion, it should be noted that in the following the term "fabric portion" is used to describe the fabric port itself, i.e. the interface between the switch module and the network fabric (the link between the switch modules), and all associated components within the switch module. Similarly, the "client portion" is used to describe the client port itself, i.e., the interface to external clients, and all associated components within the switch module. An input device and/or an output device may refer to an external client, such as a server or a host.

Preferably, the second component part is configured to perform the same optical and electronic processing as the first component part, such that the same processing may take place on the electronic signal, for example when the second electronic signal is sent from the output of the first component part to the input of the second component part, so that the electronic signal is transmitted elsewhere. In this way, the switch module may act as an intermediate switch module (or backbone), wherein received data is not forwarded directly to an output device, but is forwarded to another switch module for subsequent further transmission to another switch module, or to an output device. Thus, the second component part may comprise:

a transmit side input to receive a second electronic signal carrying information, the information comprising information about a destination switch module of the electronic signal, the second electronic signal received via the client portion from:

an output of said first component part, or

An input device;

a transmission-side conversion means for converting the second electronic signal into a third plurality of optical signals containing the same information;

a transmit-side multiplexer to convert the third plurality of optical signals into a multiplexed fabric output signal for transmission to an active switch;

a receive-side demultiplexer to receive a multiplexed fabric input signal from an active switch and to separate the multiplexed fabric input signal into a fourth plurality of optical signals;

a receiving side converting means for converting the fourth plurality of optical signals into a third electronic signal, an

A receive-side output to send, via the client portion, the third electronic signal to:

the transmission-side input of said first component part, or

And an output device.

The switch module may also comprise more than one client part, and preferably two client parts. Having an increased number of client portions on each switch module increases the number of external devices that can be connected to each switch module when the switch module is used in an optoelectronic switch.

The switch module may comprise more than the first and second component parts depending on the dimension (dimension) of the optoelectronic switch in which the switch module is to be used. Thus, the output of the second component part may alternatively be configured to send a signal to a third component part instead of the first component part.

The switch module according to the first aspect of the present invention provides the functionality required to build a scalable multi-dimensional (i.e. N >1, using the terminology introduced in the background section of the present application) optoelectronic switch capable of transmitting optical signals received at the client portion of one switch module to the client portion of another switch module. The conversion associated with the transmit side/receive side conversion means allows most of the data transfer to take place in the optical domain rather than the electronic domain. Thus, it is possible to transmit data at high data rates over long distances with lower power, and the power loss may be lower than in the electronic domain. In addition, the use of the optical domain enables the use of wavelength division multiplexing. An additional important advantage of using the optical domain during active switching is bit rate independence, where switch plane data operates at packet rate rather than bit rate.

As mentioned at the outset of this section, the optoelectronic switch (of the second aspect) of the present invention uses a new topology that provides several improved aspects over the aforementioned folded claus technology and other topologies known for use in optical switching networks. In general, a second aspect of the invention provides an optoelectronic switch comprising an array of switch modules and active switches arranged in an improved physical topology. The switch modules are those according to the first aspect of the invention that include both a client port ("client portion") and a fabric port ("fabric portion") and are thus both connected to the optical fabric and any external clients.

Accordingly, a switch module according to the first aspect of the invention may be interconnected to an optoelectronic switch according to the second aspect of the invention, wherein the N-dimensional optoelectronic switch for transmitting optical signals from an input device to an output device comprises a plurality of interconnected switch modules according to the first aspect of the invention, wherein:

the switch modules are arranged in an N-dimensional array, the ith dimension having a size R_i(

i

1,2.. N), each switch module having an associated set of coordinates giving its position relative to each of the N dimensions;

each switch module is N sub-arrays S_iMember of (2), each subarray S_iIncluding R that differs only in terms of coordinates of position in the i-th dimension_iA plurality of switch modules, and each of the N sub-arrays is associated with a different dimension;

each of the switch modules is configured to generate a multiplexed fabric output signal,

each subarray S_iAlso includes having R_iAn input terminal and R_iAn active switch at one of the output terminals,

each input of each active switch is configured to receive the R from the sub-array_iThe multiplexed fabric output signals of each of the individual switch modules,

the active switch is configured to multiplex a fabric output signal from its R based on the destination information contained in the first electronic signal received at the transmit-side input of the switch module_iAny one of the input terminals leading to its R_iAny one of a plurality of outputs, the active switch receiving the multiplexed fabric output signal from the switch module.

From said R_iThe signal transmitted by each of the individual outputs may form the R's that may be transmitted by the sub-arrays_iThe multiplexed fabric input signal received by another one of the switch modules.

Here, the "size" R of the ith dimension is most easily understood by considering, for example, 120 switch modules organized into a 4x 5x 6 array_i. Thus, R₁＝4、R₂＝5、R ₃6. In other words, the size of the ith dimension may also be considered as the length of the array in the direction associated with the dimension. It has to be emphasized that this does not mean that the modules are physically arranged, for example in a 3D array, which only represents the connections between the switch modules, as will be described in more detail below. This will be apparent from the 5D array that the switch modules can, for example, be arranged to be clearly impractical in real space. In the arrangement described above, it will be appreciated that the size R of the ith dimension_iAnd is associated with sub-array S_iThe same number of inputs/outputs of the active switch, wherein the coordinates in the dimension change. In this way, it can be guaranteed that the active switch is connected to all switch modules in the sub-array.

The total interconnection grid formed between fabric portions of all switch modules and including the active switches mayReferred to as an "optical fabric" or "switch fabric" and includes optical links connecting various components. Preferably, the optical link is an optical fiber. Also, the optical links are preferably bidirectional, which may be achieved by bundling two or more optical links within a single cable. Alternatively, the optical link may be in the form of an optical polymer waveguide embedded in, for example, a PCB or a silicon waveguide formed on or in a substrate. Similarly, an "active switch" refers to a type of switch that is capable of actively controlling the path through which signals travel. Thus, the active switch is able to provide full mesh connections without having to provide a full mesh, or similar fabric, of interconnecting fibers. In addition, if the active switch receives its R at the same time_iR of the inputs each having a different intended destination_iA different multiplex signal, the active switch is then able to send all signals simultaneously. The active switch preferably operates in a non-blocking manner, and more preferably in a strictly non-blocking manner rather than a re-arrangeable non-blocking manner. The active switch described herein performs the functions of the "backbone" described above, as the active switch is only connected to the switch module, not to external client devices.

In the illustrative example, where each active switch in the entire array has the same cardinality R (i.e., each active switch in the entire array has R inputs/outputs, regardless of the dimension/sub-array associated with the active switch). These are the cardinality R and the number of dimensions N of each switch module. Thus, using notation as used in the background section of the invention, the following relationship applies:

total number of leaves, i.e. switch modules, P₁＝R^N

The backbone, i.e., the total number of active switches,

D＝2N

table 2 below shows C for exemplary values of R and N_{General assembly}And shows that the number of clients an optoelectronic switch according to the present invention can support is greatly improved over folded claus networks. It should be noted that this improvement is still evident in cases where the cardinality of the switches in different arrays is not exactly the same. However, for manufacturing reasons, it is preferred that all active switches used in the optoelectronic switch of the present invention are identical or substantially identical.

Table 2: c for optoelectronic switches of the invention for varying values of R and N_{General assembly}Value of (A)

In a 2D embodiment of the invention, the optoelectronic switch comprises an array of interconnected switch modules according to the first aspect of the invention arranged in an X Y array, the array having X columns of Y switch modules, and Y rows of X switch modules. Thus, each of the Y rows has an associated active switch (with X inputs/outputs) and each of the X columns has an associated active switch (with Y inputs/outputs). Each active switch provides a connection between all active switches in its associated row or column. In this case, it can be seen that each switch module is connected to two different active switches, namely an active switch associated with its column and an active switch associated with its row.

Thus, the switch modules used in such optoelectronic switches each require two fabric parts.

Similarly, in a 3D embodiment of the invention, an optoelectronic switch comprises an array of interconnected switch modules according to the first aspect of the invention arranged in an X Y X Z array, the array having:

x columns (each consisting of a Y X Z array),

y rows (each row consisting of an X X Z array) and

z layers (each layer consisting of an X Y array).

Thus, each sub-array of switch modules has an associated active switch, each of the switch modules being located, for example, in the same column/row, but at different layers. Thus, there are X Y active switches associated with a sub-array containing Z switch modules that differ only by layer, each active switch having Z inputs/outputs. Also, there are X Z active switches associated with a subarray that contains Y switch modules that differ only in row, each active switch having Y inputs/outputs. Also, there are Y X Z active switches associated with a subarray that contains X switch modules that are not identical in only columns, each active switch having X inputs/outputs. Similar to the 2D case above, each switch module is connected to three different active switches, i.e. the active switches associated with each of the sub-arrays described earlier in the paragraph. Thus, in a 3D implementation of an optoelectronic switch according to the present invention, three fabric parts are required for each switch module.

As can be seen from the above, it is preferred that each switch module has at least N group members, each of the N group members being associated with a different sub-array of which the switch module is a member. Thus, via the proprietary fabric portion for the sub-array, the switch module can transmit data to any other switch module in the sub-array via the active switch associated with the sub-array. After the optical hop has occurred, the signal reaches a different switch module that is a member of a different set of sub-arrays than the first sub-array, and can then perform the same processing to send the data to another switch module having a common sub-array. In this way all data transfer from one switch module to another can take place in a series of optical and electronic hops.

In this arrangement, it is possible to send data from any switch module in the array to any other switch module in the array by a maximum of N optical hops (where optical hops are hops involving signals passing through the optical fabric via the active switch). This is possible because individual switch modules can act as intermediate switch modules, i.e. because the output of a first fabric portion can send an electronic signal (e.g. a data packet) to the input of another fabric portion on the same switch module, and correspondingly, the input of the first fabric portion on a switch module can receive data from the output of a second switch module. Electronic signals may be communicated between two fabric portions using an integrated switch, such as an electronic crossbar switch, or an electronic shared memory switch that provides a connection between two fabric portions, two client portions, or a connection between one fabric portion and one client portion. Thus, during data transfer operations, data is able to perform optical hops to another fabric portion located in the same sub-array, via the active switch associated with that sub-array. The data is then able to perform an electronic hop through the switch module itself to the fabric portion associated with the different sub-arrays, then a second optical hop may occur-the process is repeated at most N times until the data packet reaches its final destination, i.e. the switch module with the client portion via which the data (e.g. in packet form) is transmitted to the output device.

With more than N organization sections on each switch, flexibility is provided for expanding the optoelectronic switch into higher dimensions. For example, consider M with an array organized as a square²Case of 2D optoelectronic switch of individual modules. This situation can be extended to have an organization into cubic arrays (i.e., N layers, N) by connecting, via a new proactive switch, the unused fabric portions on switch modules in each (newly defined) layer having the same rows and columns to define new sub-arrays and associated proactive switches²A switch) M³A 3D optoelectronic switch of each switch module. Redundant fabric ports may also be formed by providing more than one fabric portion to connect one switch module to another switch module within the same sub-arrayAnd (4) utilizing.

The transmit side switching means of each switch module preferably further comprises a transmit side packet processor configured to receive the first electronic signal in the form of a packet, preferably an original packet, having a packet header containing the destination information. Except for the data itself. The information included in the packet may include information relating to the destination of the packet, e.g., the client portion to which the packet should be last sent. The packet header may also include various pieces of information including source and destination addresses, packet length, protocol version, sequence number, payload type, hop count, quality of service indicator, and other information.

The transmission-side packet processor may be configured to perform packet fragmentation, wherein data packets having the same destination switch module are arranged into frames having a predetermined size, and wherein the data packets may be fragmented into a plurality of packet fragments arranged in a corresponding plurality of frames, and wherein optionally one frame may contain data from one or more data packets. Each packet fragment preferably has its own packet fragment header that includes information that identifies at least the packet to which the packet fragment originally belongs so that the packet can be reconstructed after subsequent processing and transmission. For example, consider the case where the packet processor is configured such that the frame payload size is 1000B, and three packets of 400B, 800B, and 800B are input into the switch module. If each of these packets is to be sent on a packet-by-packet basis in a separate frame, this may represent an efficiency of (400+800+800)/3000 ═ 67%. However, by using packet fragmentation, the first frame may include 400B packets, and 600B of the first 800B packet, and then the second frame may include the remaining 200B of the second 800B packet and the first 800B packet. This results in 100% efficiency. The frames constructed by this process represent the data packets by their own power and, therefore, when a packet undergoes more than one optical hop in order to reach the destination switch module, further fragmentation can take place at the intermediate switch module.

In order to maximize efficiency, subsequent processing of a frame (e.g., forwarding the frame for conversion into the first plurality of optical signals) may not be performed until the fill fraction of the frame reaches a predetermined threshold, preferably greater than 80%, more preferably greater than 90%, and most preferably 100%. After a predetermined amount of time has elapsed, packets may be alternately sent for subsequent processing. In this way, if a packet of data for a given switch module stops arriving at the packet processor, frames still below the threshold fill fraction may still be sent for subsequent processing, rather than stalling the packet processor. The predetermined amount of time may be between 50ns and 1000ns, but is preferably between 50ns and 200 ns. Most preferably, the time interval is approximately 100 ns. Thus, the transmit side packet processor may include or be associated with a transmit side memory for temporarily storing incomplete frames during frame construction. The elapsed time may vary depending on the communication needs; in general, the higher the rate of communication traffic, the shorter the time that will elapse, and the lower rate of communication traffic may result in increased time intervals.

When the packet processor is configured to perform packet fragmentation, the receive-side conversion means preferably further comprises a receive-side packet processor configured to reconstruct the original packets from the packet fragments when the original packets are dispersed in more than one frame. This operation may be performed with reference to the packet fragment header described above. When a packet undergoes several separate fragmentation by successive intermediate switch modules on its journey from source to destination, the final reassembly of the packet by the receive-side packet processor may be delayed until all the constituent parts of the original packet have reached the destination switch module. Thus, the receive-side packet processor may include or be associated with a receive-side memory to temporarily store the constituent parts.

The transmission side conversion means may comprise a modulator configured to receive light from the light source, and more preferably comprises a plurality of modulators, preferably light modulators. The optical modulator may be a phase or intensity modulator such as an electro-absorption modulator (EAM), a Franz-Keldysh (Franz-Keldysh) modulator, a modulator based on the quantum confined stark effect, a Mach-Zehnder (Mach-Zehnder) modulator, and the plurality of modulators preferably includes 8 modulators. Each modulator may be associated with only a single light source or may be illuminated by fewer light sources, with the light sources shared between the modulators. Each modulator may be configured to receive an electronic signal from the input or the transmit side packet processor, and unmodulated light from a light source. By combining the electronic signal and the unmodulated light, the modulator generates a modulated light signal that has the same wavelength as the unmodulated light from the light source and that carries the information carried by the original electronic signal. This modulated optical signal may then be transmitted to the transmit side multiplexer. The light source is preferably in the form of a laser to generate a substantially monochromatic beam of light limited to a narrow wavelength band. To minimize losses, the modulator is preferably configured to receive light having a wavelength in the C-band or L-band of the electromagnetic spectrum, i.e., 1530nm to 1625 nm. More preferably, the light has a wavelength within the C-band or "erbium window", having a wavelength of 1530 to 1565 nm.

The laser may be a fixed wavelength laser or a tunable laser. In an array of modulators, the light sources associated with each modulator should have different wavelengths and not overlap in bandwidth in order to minimize crosstalk in the multiplexer. When the light source is a laser, the modulator may be in the form of an electro-absorption modulator (EAM) that uses a varying voltage to modulate the intensity of the laser, thereby carrying the information contained in the electronic signal. Using EAM means only changing the intensity, not the frequency, of the laser light and thus preventing any change in the wavelength of the modulated optical signal.

When multiple modulators are present, the transmit-side packet processor may also be configured to perform packet slicing, in which frames (as constructed by the packet slicing process described above) or data packets are sliced into a first plurality of electrical signals. Each of the first plurality of electrical signals is then sent to a different one of the plurality of modulators, whereby the electrical signals are converted into a first plurality of optical signals. The receiving-side converting means may comprise a photo detector, for example a photo diode, for converting the second plurality of optical signals into the second plurality of electrical signals. More preferably, the receiving-side converting member may include a plurality of photodetectors. The receive-side packet processor may be configured to reassemble the second plurality of electronic signals representing packet slices into the second electronic signal. By dividing a packet or frame into multiple slices before sending to another switch module, data can be sent using many different wavelengths multiplexed into a single optical link by a multiplexer. In this way, several pieces of information can be sent in parallel and result in increased bandwidth and more efficient data transfer.

In the case where the transmit side packet processor is configured to perform both packet slicing and packet slicing, the packet slicing step (i.e., forming frames of data) is performed first, followed by slicing the frames. Accordingly, at the destination (or intermediate) switch module that receives the signal, the packet processor reassembles the second plurality of electronic signals (i.e., packet slices) into a single second electronic signal before reconstructing the original packet from the frame.

After fragmentation, frames are constructed that each contain data prepared for only a single destination switch module. Thereafter, data is converted into the first plurality of optical signals of different wavelengths, and the transmission-side multiplexer wavelength-multiplexes the data to form the multiplexed constituent output signal. Preferably, the switch module is configured to operate in a burst mode, wherein the switch module is configured to transmit the multiplexed fabric output signal in a series of consecutive bursts, each burst comprising packets and/or packet fragments from a single data frame, such that each burst comprises only packets and/or packet fragments having the same destination module. Each successive burst may include data frames having different destination switch modules. The paired sequential bursts may be separated by a predetermined time interval, which may be between 50ns and 1000ns, but is preferably between 50ns and 200 ns. Most preferably, the time interval is approximately 100 ns. Preferably, all fabric portions of the active switches connected to a single sub-array are configured to operate synchronously, i.e., each fabric portion simultaneously transmits bursts to the input of the active switch. In this way, the active switch is able to route each signal to the next switch module in one switching action.

The transmit side packet processor may also be configured to error correct incoming data packets. This operation may be performed by methods such as error correction and retransmission or Forward Error Correction (FEC). Additionally, the switch module may further include a management portion configured to perform fabric management procedures including initialization, program routing/forwarding tables, failure reporting, diagnostics, statistics reporting, and metering.

To control the exchange of data by the active switches, each sub-array of the switch module may include an arbiter configured to control operation of the active switches included in the sub-array based on destination information stored in the data packets to be exchanged. This allows providing a route that ensures that all data reaches its destination in a non-blocking manner and minimizes the occurrence of bottlenecks. The arbiter may be connected to a switch driver that controls operation of the switch. The arbiter may be connected to the transmit side packet processors in each switch module of the sub-array that includes it. Alternatively, each fabric portion of each switch module may further include a controller via which the arbiter may be connected to the transmit side packet processor. When a data packet is received at the transmit side packet processor, the transmit side packet processor is configured to send a request to the arbiter, the request preferably identifying a destination switch module for the data packet. The transmit side packet processor may look up in a look-up table or otherwise which output of the active switch to which the transmit side packet processor is connected corresponds to the destination switch module that is the subject of the request. More specifically, the output of the intermediate switch module that is connected to the destination switch module or where the next optical hop should occur then requests the arbiter for the output itself.

Thus, one or both of the transmit side packet processor and the arbiter can include a lookup table containing R for switch modules in a sub-array with an active switch_iInformation associated with each output. When a request is made, the arbiter then establishes a scheme that ensures, to the greatest extent possible, that each packet is able to perform its next optical hop. More particularly, toThe arbiter may be configured to perform R to compute an active switch_iAn input terminal and R_iA bipartite graph matching algorithm of pairings between outputs, such that each input is paired with at most one output, and vice versa. Naturally, in some cases, such as in the case where several fabric parts send large amounts of data all prepared for the same output of the proactive switch, the request cannot be fulfilled. Thus, the arbiter may be configured to store information about requests that cannot be satisfied in a request queue. The associated data is then buffered on the switch module, e.g. in the transmit side packet processor or in a separate transmit side memory, until these requests are fulfilled. Thus, requests that cannot be fulfilled are delayed, rather than being dropped, for example, when a local bottleneck occurs at the active switch. In other words, the arbiter maintains the state of a buffer memory or Virtual Output Queue (VOQ) on the switch module, which may be in the form of a counter (counting the number of packets or bytes per VOQ, for example) or a first-in-first-out (FIFO) storing packet descriptors. However, the actual packets themselves remain stored on the switch module, not at the arbiter.

When it is necessary for a packet to perform more than one hop in order to reach its destination switch module, the route can be inferred entirely from the comparison between the coordinates of the source and destination switch modules. For example, in a process known as dimension-ordered routing, a first hop may match first coordinates of the source and destination switch modules, a second hop may match second coordinates of the source and destination switch modules, and so on until all coordinates match, i.e., until the packet has been transferred to the destination switch module. For example, in a four-dimensional network, if the source switch module would have coordinates (a, b, c, d) and the destination switch module would have coordinates (w, x, y, z), then the dimension ordered route may be: (a, b, c, d) → (w, b, c, d) → (w, x, c, d) → (w, x, y, d) → (w, x, y, z). At any point along the route, the packet processor may compare the coordinates of the source switch module and the coordinates of the destination switch module and determine which coordinates do not yet match. The packet processor will then decide to route along the non-matching direction, e.g. with the lowest index or the highest index.

The active switch of the present invention may be in the form of an optical active switch. Such optical active switches may be based on an arrangement of mach-zehnder interferometers (MZIs), and more particularly, may be in the form of MZI cascaded switches. The MZI cascaded switch comprises a plurality of MZIs each having: two arms split at the input coupler and feeding the split paths into the output coupler for recombining the paths; and two output sections. The plurality of MZIs are preferably arranged to provide a path from each input to each output of the MZI cascaded switch. To the greatest extent possible, the arms have the same length. Alternatively, the arms may be unbalanced, preferably with a default output. Each MZI may comprise an electro-optic region at one or both arms, with the refractive index being dependent on a voltage applied to the region via one or more electrodes. The phase difference of light travelling through the electro-optic region can therefore be controlled by applying a bias voltage via the electrodes. By adjusting the phase difference and thus the resulting interference at the output coupling, light can be switched from one output to the other of the MZI. Preferably, the MZI cascaded switch has R_iAn input terminal and R_iA plurality of outputs, and these may be made up of, for example, a plurality of 1x2 and 2x 1 MZIs arranged to provide a path from each input to each output. When R is_iAt 5 or greater, an MZI cascaded switch, or any other active switch such as this, is being used to connect R_iA full mesh of interconnected switch modules is beneficial because the full mesh requires 1/2R_i(R_i-1) fibers to connect all fabric parts, while the active switch only needs 2R_iAn optical fiber. It is possible to construct R_iA 1x R_iDeplexing Tree "and R_iA 1 is_ix1 multiplexing trees "to form a tree with R_i＝2ⁿMZI cascaded switches with inputs and outputs, wherein each tree comprises n switches with 1x2 (de-multiplexing) or 2x 1 (multiplexing)Stage at kth stage with 2^kA switch. By building up R on each side_i+1 trees and ignoring internal connections, additional ports may be supported on each cascaded switch so that the inputs are not connected to outputs connected to the switch itself. Such MZI cascaded switches are for the most part wavelength agnostic and are therefore able to switch the entire multiplexed fabric output signal from input to output without requiring any demultiplexing/multiplexing at the input and output.

Alternatively, the active switch may be in the form of an electronic active switch, such as an electronic crossbar switch. More preferably, the electronic active switch may be an electronic shared memory switch. An electronic shared memory switch is an electronic crossbar switch that also includes memory. The presence of memory within the switch is advantageous because it means that the switch is able to perform not only switching but also buffering, i.e. storing queues of packets when bottlenecks occur at the electronic shared memory switch, as described above. This means that the electronics on the packet processor can be simplified.

In order to use an electronic, rather than an optical, active switch in the architecture of the present invention, the multiplexed fabric output signal must be converted to a signal that can be switched electrically. Thus, the electronic active switch may comprise an opto-electrical converter at each input for converting the multiplexed fabric output signal from an optical signal to an electronic active switch signal; and an electro-optical converter at each output for converting the electronic active switching signal to an optical signal in the form of a multiplexed fabric input signal, wherein the electronic active switch is configured to convert the electronic active switching signal from its R_iTo which any one of the inputs is switched_iAny one of the outputs. Furthermore, in order to handle the multiplexing nature of the signals, the optical-to-electrical converter may comprise a demultiplexer for demultiplexing the multiplexed fabric output signal into a first plurality of intermediate optical signals, each of which is preferably converted by a corresponding plurality of photodetectors into a signal for switching into a desired outputAn intermediate electronic active switching signal, and the electrical-to-optical converter may be configured to convert the plurality of switched intermediate electronic active switching signals into a second plurality of intermediate optical signals, and further comprising a multiplexer for multiplexing the second plurality of intermediate optical signals to form a multiplexed fabric input signal. In a preferred embodiment, the electronic active switch may be configured to temporarily store a queue of packets or frames of data when a request associated with the packet or frame cannot be satisfied.

Any or all of the multiplexer, the transmission side multiplexer, the demultiplexer, and the reception side demultiplexer are preferably in the form of an Arrayed Waveguide Grating (AWG), the AWG being a passive device. AWGs allow a single fiber along a river to carry multiple optical signals of different wavelengths. Because the wavelengths of the multiple modulated optical signals produced by the modulators are all different, the multiplexed fabric output signal produced by the AWG suffers from little to no crosstalk because the different wavelengths of light only interfere linearly. Alternatively, instead of an AWG, the multiplexed signal may be broadcast to a number of wavelength selective filters, each tuned to receive one of the desired split signals of a wavelength.

An important consideration in switching systems, such as the switch of the present invention, is its bandwidth. In the following discussion, "bandwidth" is used to refer to the maximum rate at which a particular portion of data transfer can be achieved, and is typically measured in billions of bits per second (abbreviated herein as "Gbps"). In particular, it is important to ensure that bandwidth is preserved on both a local and global scale. To ensure that more data is unlikely to enter the switch module at a given time (i.e., create a bottleneck that is localized to the switch module) than can be transmitted away from a given switch module at the same time, the total bandwidth of the client portion on a switch module preferably does not exceed the total bandwidth of the fabric portion on the same switch module. More preferably, the total bandwidth of fabric portions on a switch module exceeds the total bandwidth of client portions on the same switch module, and most preferably, the bandwidth of each fabric portion on a switch module exceeds or equals the total bandwidth of all client portions on the switch module. In this way, local bottlenecks caused by an unexpectedly large amount of incoming data from multiple client devices all being directed to the same fabric portion on the same switch module can be avoided. In particular, this allows all signals to be multiplexed together for subsequent transmission in a non-blocking manner.

In a preferred embodiment, the active switch is located on or in the optical backplane, and is preferably connected to the optical backplane. Preferably, the backplane contains optical links for connecting the switch modules to the active switches, thus providing a connection between each switch module and each active switch, each of the switch modules sharing a sub-array with an active switch. More specifically, each of the optical links may provide a connection for carrying multiplexed fabric output signals between a transmit-side multiplexer on a switch module and an input of an active switch. When the backplane is used in conjunction with an optical active switch or the like as described above, an Active Optical Backplane Module (AOBM) may be used. The switch module may be detachable or detachable from the backplane so that it can be rearranged as required externally. Thus, the switch module may also comprise a connection member for connecting to an optical backplane. The connecting member may comprise an array of single mode optical fibres which are joined using an MPO connector or similar device.

According to a third aspect of the present invention there is provided an optical backplane for use in an N-dimensional optoelectronic switch, the optical backplane being arranged to provide connections between switch modules arranged in an N-dimensional array of the N-dimensional array, the ith dimension having a radix R_i(i-1, 2.. N), wherein each switch module has an associated set of coordinates giving its position relative to each of the N dimensions, and each switch module is N sub-arrays S_iMember of (2), each subarray S_iIncluding R that differs only in terms of coordinates of position in the i-th dimension_iA plurality of switch modules, and each of the N sub-arrays is associated with a different dimension, the optical backplane comprising:

an array of active switches each having R_iAn input terminal and I_iAn output terminal, activeSub-array S of switchboard and switchboard module_iIn association, the array of switches is configured such that when the array of switch modules is connected to an optical backplane:

each input of each active switch is connected to the associated sub-array S via an optical link_iThe R in (1)_iEach of the plurality of switch modules is configured to,

the active switch is configured to R the signal received from the optical link from it_iAny one of the input terminals leading to its R_iAny one of the outputs.

According to a fourth aspect of the present invention there is provided a method for switching data packets from a first switch module to a second switch module using an N-dimensional optoelectronic switch according to the second aspect of the present invention. It should be noted that any of the above optical features may be combined with the method of the fourth aspect of the invention and the hardware applications of the first, second and third aspects. The method comprises the following steps:

(a) receiving, at an input of a fabric portion of a first switch module, a data packet carrying information identifying an intended destination switch module;

(b) converting the packets into a first plurality of optical signals containing the same information;

(c) multiplexing the first plurality of optical signals into a multiplexed fabric output signal;

(d) transmitting the multiplexed fabric output signal to an input of an active switch, the active switch and the first and second switch modules both being located in the same sub-array S_iPerforming the following steps;

(e) switching the multiplexed fabric output signal to an output of the active switch corresponding to the second switch module to generate a multiplexed fabric input signal;

(f) demultiplexing the multiplexed fabric input signal into a second plurality of optical signals at a first fabric port of the second switch module;

(g) converting the second plurality of optical signals back into the original datagram; and

(h) forwarding the data packet to a client portion of the second switch module or an input of a second component portion of the second switch module.

Such an approach is suitable, for example, for switching signals from a source switch module to a destination switch module when the source and destination switch modules are located in the same sub-array. Alternatively, the method may be adapted to switch from a source switch module to an intermediate switch module. The method may be adapted to transmit a signal to a third switch module, e.g. a destination switch module, by adding the following steps:

(i) receiving, at the input of the second fabric port of the second switch module, a data packet carrying information identifying the destination switch module;

(j) converting the packets into a third plurality of optical signals containing the same information;

(k) multiplexing the third plurality of optical signals into a multiplexed fabric output signal;

(l) Transmitting the multiplexed fabric output signal to the same sub-array S as the second and third switches_iAn input of the active switch;

(m) switching the multiplexed fabric output signal to an output of the active switch corresponding to the third switch module to generate a multiplexed fabric input signal;

(n) demultiplexing the multiplexed fabric input signal into a second plurality of optical signals at a first fabric port of the third switch module;

(o) converting the second plurality of optical signals back into the original data packets.

Since the optoelectronic switch is adapted to transmit an optical signal from the input device to the output device, the optical signal may be received from the input device before step (a) and the data packet may be forwarded to the output device after step (h) or step (o) depending on whether intermediate optical hopping is required.

In some embodiments, rather than each sub-array comprising a single active switch, the sub-array may comprise a plurality or group of active switches, and thus, another aspect of the present invention may provide an N-dimensional optoelectronic switch for transmitting optical signals from an input device to an output device, the optoelectronic switch comprising a plurality of switch modules according to claim 1, the switch modules being interconnected, wherein:

i

each of the switch modules is configured to generate a multiplexed fabric output signal;

each subarray S_iFurther comprising one or more active switches arranged to provide connections between all switch modules in the sub-array;

each active switch has an input configured to receive the R from the sub-array_iA multiplexed fabric output signal of one or more of the plurality of switch modules; and is

Each of the one or more active switches is configured to direct a multiplexed fabric output signal from any of the switch modules to any other of the sub-arrays based on the destination information contained in the first electronic signal received at the transmit-side input of the switch module from which the active switch receives the multiplexed fabric output signal.

In particular, in some embodiments of the above aspects of the invention, R_iOne sub-array of a switch module only comprises a sub-array with R_iAn input terminal and R_iA single active switch of the output terminal, andand:

each input of the active switch is configured to receive the R from the sub-array_iThe multiplexed fabric output signals of each of the individual switch modules,

each of the switch modules is configured to receive the R from the active switch_iA multiplexed configuration of one of the outputs constituting an output signal, an

In other embodiments, subarray S_iMay include P_subAn active switch preferably arranged to form a network connecting each open module in the sub-array with each other switch module in the sub-array. P_subMay be the same for all sub-arrays and may be equal to the number of switch modules in a given sub-array, or alternatively, P_subMay be greater or less than the number of switch modules in a given sub-array. In some embodiments, P_subMay be the same for all sub-arrays associated with a given dimension, but P_subThe dimensions may differ from dimension to dimension. In some embodiments, for sub-arrays associated with some dimensions, it is possible that only a single active switch interconnects the switch modules within those sub-arrays, and multiple or a group of P' s_subThe active switches exist in sub-arrays associated with other dimensions. This enables the optoelectronic switch to be tailored to the needs of the customer. Using multiple active switches within a sub-array eliminates the need for a large radix active switch, replacing it with several active switches with small radix. In a preferred embodiment, P_subCan be etcThe number of client ports on each switch module.

In some embodiments of the invention, there may be additional "layers" of switches between the switch module and one or more active switches in a given sub-array. The additional layer of switches is referred to herein as an "intermediate switch". In other words: each switch module in a given sub-array is connected to an active switch in that sub-array via an intermediate switch. The intermediate switch may be an optical active switch, or an electronic active switch, such as an electronic packet switch. The nature of the switching elements (i.e., switch modules, intermediate switches, and active switches) will be discussed in more detail in this application. For clarity, in the following paragraphs, the terms "leaf and stem" are used, whereby the following terms are employed: the switch modules are referred to as "leaf switches" and the active switches are referred to as "backbone switches".

In one or more preferred embodiments, the intermediate switch is bidirectional, i.e., the intermediate switch carries signals in both directions. An example of a bidirectional switch is an electronic packet switch, which will be described in detail later. In embodiments that include bidirectional intermediate switches, signals may be sent from the source leaf switch to the backbone switch through the same "layer" intermediate switch at the time of the signal hop, and from the backbone switch to the destination leaf switch in the signal trip. In such embodiments, the structure of the sub-arrays may be represented by a folded claus network that allows for optoelectronic switches to be scaled, thereby eliminating the need to use bulky and potentially costly large radix active switches (i.e., large radix backbone switches), i.e., allowing for a substantial increase in the number of external clients that may be connected to each other.

In embodiments using unidirectional intermediate switches, it may be desirable in such cases to include a first layer of intermediate switches for hops from the source leaf switch to the backbone switches, and a second layer of intermediate switches for hops from the backbone switches to the destination leaf switches. Such interconnections are best represented using an expanded claus network (or a "partially collapsed" claus network), but are not within the scope of the claimed invention.

The use of a folded/unfolded/partially folded claus network or any claus-like network ensures advantageous non-blocking operation of the optoelectronic switch. In fact, leaf switches, intermediate switches, and backbone switches in a given sub-array may be interconnected with any other network configuration having suitable path redundancy to ensure or improve the scope of non-blocking operation.

Using the terms leaf and backbone described above, an embodiment may be defined as an N-dimensional optoelectronic switch for transmitting an optical signal from an input device to an output device, the optoelectronic switch comprising:

a plurality of leaf switches each having a radix R and arranged in an N-dimensional array, wherein each dimension i has a respective size R_i(

i

1,2.. times.n), each leaf switch having an associated coordinate N-tuple (x) giving its position relative to each of the N dimensions₁,...,x_N)；

Wherein each leaf switch is a member of N sub-arrays, each of the N sub-arrays being associated with a different one of the N dimensions and comprising:

plural R_iLeaf switches whose coordinates differ only with respect to the ith dimension, each leaf switch having C client portions for connection to an input device or an output device, and F fabric portions for connection to backbone switches;

a plurality of S_iBackbone switches each having R fabric portions for connecting to the fabric portions of the leaf switches, and

wherein in a given sub-array, each leaf switch in the sub-array is connected to each backbone switch via an intermediate switch.

To relieve the beneficial effects of embodiments that include intermediate switches connected between leaf switches and backbone switches, consider sub-arrays in which backbone switches are connected only via a single backbone switch or a set of parallel backbone switches ("parallel" meaning that backbone switches are each connected only to leaf switches and not to other backbone switches). Each of these backbone switches has a comparative connection to each leaf switch in the sub-array under consideration and each leaf switch must be connected to each backbone switch or it may not be possible to provide a connection between each leaf switch and all other leaf switches in the sub-array.

Thus, as described above, for large sub-arrays, a large number of large radix backbone switches are required. Each leaf switch still needs to have a connection to each backbone switch, but in the embodiments discussed herein, the leaf switches are connected to the backbone switches via intermediate switches. Each intermediate switch may have a number of inputs and a number of outputs, the number of inputs being the same as the number of outputs. The "radix" of the intermediate switch refers to the number of inputs or outputs, not to the total number of inputs and outputs. Thus, the output of a given intermediate switch may be connected to multiple or a group of backbone switches in a sub-array. A given leaf switch may be connected to a cluster of intermediate switches, each intermediate switch connected to a set of backbone switches. More specifically, each of the intermediate switches of the cluster to which a given leaf switch is connected may be connected to a different disjoint set of backbone switches ("disjoint" meaning that no two intermediate switches in a given cluster are connected to the same backbone switch, i.e., there is no overlap of sets of backbone switches).

In this way, the leaf switch under consideration may be connected to all of the backbone switches in the sub-array, but via the smaller radix intermediate switches. Because the intermediate switch also has multiple inputs, these inputs can be shared among multiple leaf switches. In other words, for a given cluster of intermediate switches (the outputs of the intermediate switches providing connections to all of the backbone switches in the sub-array), each input of each intermediate switch in the cluster may be connected to a corresponding (i.e., different) leaf switch. Thus, a leaf switch may be divided into multiple clusters, and specifically: in a given sub-array, the leaf switches may be divided into a plurality of clusters, each containing a plurality of leaf switches. Each cluster may have its own associated cluster of intermediate switches that provide connections between each leaf switch cluster in the array and each backbone switch via a cluster of intermediate switches, in other words each leaf switch cluster may be associated with a cluster of one or more intermediate switches to form a line card assembly, each leaf switch in the cluster may be connected to each intermediate switch in the line card assembly, and the intermediate switches may be arranged such that signals pass through the intermediate switches during transmission from the leaf switches to the backbone switches.

Optionally, in a given sub-array, each backbone switch may be connected to an intermediate switch among the line card components located in the sub-array, and no more than one fabric entry intermediate switch among the line card components is connected to the given backbone switch. Within a line card assembly, there may be M distinct sets of intermediate switches, each set configured to transmit signals within a respective sub-array containing the line card assembly, each of those sub-arrays being associated with a respective one of the M dimensions.

To maximize topological regularity, it is preferred that all or substantially all of the intermediate switches used in embodiments of the present invention have the same cardinality, or more specifically, the same number of inputs and outputs. In particular, when all intermediate switches in a given sub-array have a given cardinality, by which the number of leaf switches increases, it is possible to support the same number of backbone switches without compromising split bandwidth. For example, if a radix-3 intermediate switch is used, the size of the sub-array may be tripled. In other words, the opportunity to scale up the array is greatly increased without increasing the size of the backbone switches used.

The connections are associated with transmitting signals from the output of the leaf switch to the input of the backbone switch. To complete the transmission of a signal from one leaf switch in a sub-array to another leaf switch in the sub-array, the signal must be transmitted from the output of the backbone switch to the fabric portion on the destination (or intermediate) leaf switch. This transmission is also done via an intermediate switch, which is preferably different from the intermediate switch used by the signal ingress backbone switch, but it is possible that the intermediate switch is a member of the same cluster.

When the leaf switches, intermediate switches, and backbone switches are as described above, within a given sub-array, the leaf switches are effectively connected via a five-level claus network, i.e., leaf switch → intermediate switch → backbone switch → intermediate switch → leaf switch. As discussed, the use of such a Claus network (or partially folded Claus network) means that it is possible to accommodate R in a sub-array in a non-blocking manner_iAny combination of one-to-one pairings between leaf switches.

The arrangement described in the previous paragraph need not be used for swapping in all N dimensions. In some embodiments of the invention, each leaf switch in a given sub-array may be connected to each backbone switch via an intermediate switch with respect only to the sub-arrays associated with the M dimensions, where M < N. The other optional features set forth above may apply to any or all dimensions in which switching between leaf switches is via intermediate switches.

Any or all of the leaf switches, backbone switches, and intermediate switches may be disposed on the optical backplane. Thus, leaf switches, intermediate switches, and backbone switches may be located on the cards. The card may be a printed circuit board on which, for example, electronic components, optical components, and control components (i.e., arbiters) are formed. The card may also accommodate optical and electronic components therebetween. In particular, embodiments of the present invention may include two types of cards: line cards and fabric cards. More specifically, the components may be located on a line card or fabric card. The line cards are "client-oriented" cards, and the fabric cards are "fabric-oriented" cards.

Leaf switches and intermediate switches, i.e., line card assemblies as described above, may be located on respective line cards. More specifically, a single line card includes at least one leaf switch and at least one intermediate switch. In some embodiments, a single line card may include multiple leaf switches and/or multiple intermediate switches. In embodiments where there are a cluster of leaf switches and associated cluster of intermediate switches, the cluster of leaf switches and its associated cluster of intermediate switches are preferably installed on the same line card. In the N-dimensional embodiment of the invention, each leaf switch is a member of N sub-arrays, as previously discussed in this application.

In embodiments where there are a cluster of leaf switches and a cluster of intermediate switches, each leaf switch cluster and its associated cluster of intermediate switches may be located on its own line card. The backbone switches may be located on a fabric card in a given sub-array. The fabric card may also include an arbiter for controlling the path of signals through the backbone switches located on the fabric card. The fabric card may also include a plurality of arbiters each configured to control the path of signals through a respective backbone switch on the fabric card. It is not necessary that all of the backbone switches be on the same fabric card, but more than one backbone switch may be located on a given fabric card. In the current embodiment of the invention there are two control elements: route/load balancing, and arbitration.

The packet processor may make routing decisions based on the destination address and current location of the packet. On the path from the leaf to the backbone, the routing decision selects the backbone to route to (typically attempting to balance the load on the available backbones), which in turn determines the specific output ports on both the local leaf switches and the intermediate switches. The output identifier of the intermediate switch is passed to the arbiter so that the arbiter can determine which input of the intermediate switch needs to be connected to which output thereof. On the path from the backbone to the leaf, the routing decision selects the appropriate leaf based on the destination of the packet, which in turn determines the local output port on the backbone and the appropriate intermediate switch located between the backbone and the destination leaf switch.

Arbitration is performed by an arbiter and is the process by which the arbiter determines the path that a signal should take through an intermediate switch (i.e. from which input to which output) in order to ensure that all signals incident on the intermediate switch are directed towards the correct next switching element (which may be a backbone switch or a leaf switch depending on which "stage" the signal is at). Thus, in some embodiments, there may be an arbiter associated with each intermediate switch in a given sub-array, in other words, a line card may include an arbiter for controlling the path of signals through the intermediate switches included in the line card assembly located on the line card, or there may be multiple arbiters each configured to control the path of signals through a respective intermediate switch. Alternatively, since the intermediate switches may have a small radix (e.g., 2, 3, 4, 5, 6, 7, or 8), the arbitration process is relatively simple (e.g., compared to a radix 24 switching element), and thus multiple arbiters may be combined into a single arbitration component, which may be an ASIC. In some embodiments, there may be a single arbiter, or a single arbitration component as described above, on each line card. In the embodiments described in this paragraph, the control performed by the arbiter is constrained within the boundaries of the line card under consideration. This minimizes latency and synchronization problems associated with the control plane: the distance/time of flight on the card can be controlled to a tighter tolerance within the physical dimensions of a single card that span cards that can be positioned a substantial distance from each other. Furthermore, by having several arbiters, each associated with a small number (e.g., one) of intermediate switches, a large number of small problems can be solved quickly and in parallel, as compared to more complex problems that must be aggregated relatively slowly.

Generally, the intermediate switches are controlled by an arbiter configured to control the actions of at least one of the intermediate switches and the backbone switches within a given sub-array based on destination information stored in the data packets to be exchanged. This thus allows providing routes that ensure that all data reaches the appropriate leaf switch in a non-blocking manner and that the occurrence of bottlenecks is minimized. The packet processors in the leaf switches may each be connected to an arbiter. When a data packet is received at the transmit-side packet processor, the packet processor may send a request to an arbiter to which the packet processor is connected, the request preferably identifying a destination leaf switch, or alternatively identifying a next leaf switch (which may be a destination leaf switch) to which the data packet should be sent. The arbiter can then generate a scheme that ensures that to the maximum extent possible, each packet can perform its next hop. The structure of the leaf switches will be described in more detail below.

The arbiter may be connected to other components, such as the packet processor and intermediate switches, using dedicated control channels. The arbiter may also be connected to a driver chip configured to control the actions of the intermediate switch.

In order to facilitate manufacturing of the optoelectronic switches according to embodiments of the present invention, it is preferable that each of the leaf switches contain the same components as each of the backbone switches. Further, in other embodiments, each of the intermediate switches may contain the same components as each of the leaf switches and/or the backbone switches. Effectively, all switching elements (i.e., switch modules, active switches, leaf switches, intermediate switches, and backbone switches, depending on the terminology used) may be the same or substantially the same. As such, optoelectronic switches can be constructed by assembling these elements, and then the different functionalities of the switching elements (e.g., the different functions of the leaf switches, intermediate switches, and backbone switches as described above) can be controlled using, for example, software. The intermediate switches and backbone switches may differ from the leaf switches in that the intermediate switches and backbone switches do not have a client portion because the intermediate switches and backbone switches are only connected to other switching elements within the optoelectronic switch and are not connected to client (i.e., external) devices. Furthermore, it must be emphasized that although the switching elements may have identical components, or may be structurally identical or substantially identical, the functionality of the different types of switching elements may vary. It should be noted that the reason for adopting the term leaf/backbone/middle is to say that the three types of switching elements can be identical/substantially identical, instead of using the terms "switch module" and "active switch" as may appear to be different components.

To use the term "leaf and backbone" as used earlier in the description, three different types of switches can be defined as follows:

■ A leaf switch is a switching element having:

a client portion for connecting to an input device or an output device;

a first component part and a second component part each for processing signals and communicating with other switching elements, the first component part having a transmission side and a reception side,

the transmission side has:

an output of said second component, or

An input device;

a transmit-side multiplexer for converting the first plurality of optical signals into a multiplexed fabric output signal for transmission to an intermediate or backbone switch, and

the receiving side has:

a receive-side multiplexer to receive a multiplexed fabric input signal from a mid switch or a backbone switch and to separate the multiplexed fabric input signal into a second plurality of optical signals;

the transmission-side input of said second component, or

And an output device.

■ the backbone switch is a switching element with:

the transmission side has:

a transmit side input for receiving a first electronic signal carrying information, the information comprising information about a destination switch module of the first electronic signal, the first electronic signal being received from an output of the second component part;

a transmit-side multiplexer for converting the first plurality of optical signals into a multiplexed fabric output signal for transmission to an intermediate switch or a leaf switch, and

the receiving side has:

a receive-side multiplexer to receive a multiplexed fabric input signal from an intermediate switch or a leaf switch and to separate the multiplexed fabric input signal into a second plurality of optical signals;

A receive side output for sending the second electronic signal to a transmit side input of the second component part.

■ the intermediate switch is a switching element having:

the transmission side has:

a transmit-side multiplexer for converting the first plurality of optical signals into a multiplexed fabric output signal for transmission to a backbone switch or a leaf switch, and

the receiving side has:

a receive-side multiplexer to receive a multiplexed fabric input signal from a backbone switch or a leaf switch and to separate the multiplexed fabric input signal into a second plurality of optical signals;

From this section, it can be seen that the order of switching elements encountered by a signal on its journey from a source to a destination leaf switch may be:

■ in embodiments that include intermediate switches, the source leaf switch → intermediate switch → backbone switch → intermediate switch → destination leaf switch.

■ in embodiments that do not include intermediate switches, i.e., where there is a single backbone switch, or a single set of parallel backbone switches, the source leaf switch → backbone switch → destination leaf switch.

As is apparent from the above, only the leaf switches comprise the client portion, since such leaf switches are the only "client-oriented" switching elements. The intermediate switches and backbone switches are defined as an interconnect fabric connecting all the leaf switches together and therefore comprise only a fabric portion. It will be noted in the foregoing that all of the switching elements in an optoelectronic switch may be the same or substantially the same. This is possible even though the backbone switches and intermediate switches do not have client portions, since the term "client portion" is a functional term used to describe the fact that external devices can be connected to these portions. Each of the switching elements may have the same physical structure, but various uses may differ. Similarly, when the switch element acts as a leaf/backbone/intermediate switch depending on the particular implementation of the invention, a different number of client/fabric portions may be used. It is also worth noting that the optical features set out above with reference to the switch module of the first aspect of the invention are equally applicable to leaf switches, backbone switches and intermediate switches as defined herein.

It is envisaged that similar advantages may be achieved by providing an optoelectronic switch for transmitting an optical signal from an input device to an output device, the optoelectronic switch comprising a plurality of interconnected switch modules according to the first aspect of the invention, wherein:

the switch modules are arranged in an N-dimensional array with the ith dimension having a radix R_i(

i

1,2.. N) and each switch module has an associated set of coordinates giving its position relative to each of the N dimensions;

each switch module is a member of at most N sub-arrays associated with a set of coordinates of the associated switch module;

the switch modules are connected by an array of active switches each having an input and an output, wherein each active switch is associated with a given sub-array or sub-arrays of the switch module array,

and, in use:

each input of each active switch is configured to receive a multiplexed fabric output signal from the switch module to which it is connected,

each active switch is configured to direct a signal from any of its inputs to any of its outputs based on the destination information contained in the first electronic signal received at the transmit-side input of the switch module from which it receives a multiplexed fabric output signal, and

the signals sent from the outputs of the active switches form a multiplexed fabric input signal that can be received by another switch module to which the active switch is connected.

Description of the drawings

These and other features and advantages of the present invention will be understood and appreciated with reference to the specification, claims, and appended drawings, wherein:

fig. 1 is a schematic diagram illustrating the manner in which two switch modules may be connected in one embodiment of the invention.

Fig. 2 is a schematic diagram of a switch module, identifying the different functional parts.

Figure 3 is a schematic diagram illustrating components of a fabric portion within a switch module according to an embodiment of a first aspect of the present invention.

Fig. 4 is a schematic diagram showing components of two different fabric portions of a switch module according to an alternative configuration.

Fig. 5 is a schematic diagram of a one-dimensional switch that may be implemented using a switch module according to an embodiment of the invention.

Fig. 6 is a schematic diagram of a two-dimensional switch according to an implementation of a second aspect of the present invention, and the two-dimensional switch may be constructed using a switch module according to an implementation of the first aspect of the present invention.

Fig. 7 is a schematic diagram of an alternative layout of a two-dimensional switch according to another implementation of the second aspect of the present invention, and which may be constructed using switch modules according to an implementation of the first aspect of the present invention.

Fig. 8 is a schematic diagram of a three-dimensional switch according to another implementation of the second aspect of the present invention, and which may be constructed using switch modules according to an implementation of the first aspect of the present invention.

Fig. 9A, B and C are schematic diagrams illustrating further examples of switch fabrics according to the second aspect of the invention, where all active switches have the same number of inputs/outputs.

Figure 10 is a schematic diagram illustrating the manner in which an arbiter can be connected to a switch module arranged in accordance with the second aspect of the invention.

Fig. 11 is a schematic diagram illustrating a connection between an arbiter and a space optical switch according to an embodiment of the present invention.

FIG. 12 shows an exemplary arrangement of Mach-Zehnder switches that may be used as spatial optical switches as part of an array of switches in accordance with an embodiment of the second aspect of the present invention;

figures 13A, B and C each show an example of an embodiment of the present invention in which an electronic active switch or switches are used instead of an optical active switch.

Fig. 14A, B and C show representations of a 2D optoelectronic switch. FIGS. 14A and B are foldable; only 14C is unfolded.

Fig. 15A, B and C show schematic diagrams of known folded claus networks.

Detailed Description

The detailed description set forth below in connection with the appended drawings is intended as a description of exemplary embodiments of switch modules and optoelectronic switches provided in accordance with the present invention and is not intended to represent the only forms in which the present invention may be constructed or utilized. The description sets forth the features of the invention in connection with the illustrated embodiments. It is to be understood, however, that the same or equivalent functions and structures may be accomplished by different embodiments that are also intended to be encompassed within the spirit and scope of the invention. Like element designations are intended to refer to like elements or features, as indicated elsewhere herein.

Fig. 1 is a schematic illustration depicting a typical connection between two switch modules of a switch fabric according to an embodiment of the invention. In this figure only two photo detectors P and two modulators M are shown on each switch module to illustrate the connections between the switch modules.

Switch module 1 has a fabric side F1 for connecting with other switch modules present in the optoelectronic switch (in this schematic diagram, only switch module 2), and a client side C1 for connecting to external devices. On the fabric side F1 of the switch module 1, there are two electro-absorption modulators M1, M2, the outputs of which are incident on a multiplexer MUX1, in this case multiplexer MUX1 being an AWG. MUX1 combines the signals exiting M1 and M2 and transmits the signals (dashed arrows) to R_ix R_iOptical active switch (herein, "optical active switch," unless the context clearly indicates otherwise) 4, having R_iAn input terminal and R_iAnd an output terminal. The characteristics of this switch will be described in more detail below.

The optical active switch 4 passes signals from the input where the multiplexed signal arrives from the MUX1 to the output, depending on the desired destination switch module for the signal, in this case switch module 2. The control scheme used to determine the destination switch module will be described in more detail later. The signal is transmitted from the output of the optical active switch 4 to the destination switch module 2 (dashed arrow). The signal is incident on the demultiplexer DEMUX2 of the switch module 2. Here, the multiplexed signals are demultiplexed into their constituent individual signals, each of which is incident on a single photodetector P3, P4. The signals may be transmitted from the photodetectors P3, P4 further to the client portion on the client side C2 of the switch module 2, or (in the case of optoelectronic switch multi-dimensions) the signals may be transmitted back to the fabric side F2 for further transmission. The solid arrows in fig. 1 show an alternative transmission of signals from the switch module 2 to the switch module 1. The arrows in the figure (both solid and dashed arrows) represent WDM optical connections.

Figure 2 shows a schematic diagram of a typical switch module used in an embodiment of the invention. Each switch module includes an integrated switch segment having a client side and a fabric side, as shown in the previous figures. The number of client ports and fabric ports depends on the requirements of the product, and bandwidth constraints. In the switch module shown in fig. 2, there is also a management part configured to perform fabric management procedures such as initialization, program routing/forwarding tables, failure reporting, diagnostics, statistics reporting, metering, and the like.

Figure 3 shows a more detailed view of fabric side F1 of a typical switch module 1 used in the architecture of an embodiment of the present invention. First, the structure of the switch module 1 will be described, followed by a description of the path of the signal in the switch module 1. The fabric side F1 is divided into two parts, a transmit side Tx and a receive side Rx. The transmit side Tx includes an array of packet processors PP-Tx, EAM MOD1, MOD2, … …, MODQ, each of the EAMs receiving input from one of an array of light sources LS1, LS2, … …, LSQ. Each of the EAMs of the array is connected to a signal multiplexer WDM-MUX which then outputs its WDM signal to an optical active switch which may be considered to be a "fabric" of interconnections between switch modules 1 of an optoelectronic switch implementing embodiments of the present invention. The reception side Rx has a similar structure. More specifically, the receive side Rx comprises a packet processor PP-Rx receiving inputs from an array of photo-detectors PD1, PD2, … …, PDQs, each receiving inputs from a single demultiplexer WDM-DEMUX. The demultiplexer receives an input from an optical active switch (not shown in figure 3). The controller CTRL is also included in the switch module 1 and is not tied to either the transmission side Tx or the reception side Rx. The controller CTRL is bidirectionally connected to the two packet processors PP-Tx, PP-Rx and to the arbiter illustrated by the arrow marked AR.

At a higher level, it should be noted that all data transfers taking place on the left side of the drawing take place in the electrical domain and all data transfers taking place on the right side of the drawing take place in the optical domain, i.e. all data transfers take place between the multiplexer WDM-MUX and the demultiplexer WDM-DEMUX.

The history of packets passing through the various components of the switch module 1 will now be described. Containing information to be transmitted from the source switch module to the destination switch module. In particular, the inclusion of information relating to the intended destination switch module. In the following description of the history experienced by the packet, it is assumed that all data associated with that packet has the same intended destination switch module.

The following process is performed in the electrical domain. The packets may for example be incident on the transmission side Tx of the switch module 1 from a client part, which is connected to the client side of the switch module 1. Alternatively, packets may be received from the receive side Rx of the switch module 1 (i.e. the same switch module) via an integrated switch such as shown in fig. 2, so that the packets can be forwarded to another switch module (not shown) for delivery to a different dimension. This packet transfer between dimensions will be explained more deeply later. Packets incident on the transmit side Tx enter the packet processor PP-Tx where they are sliced into a first plurality of Q electrical signals in packet slices, each having the same destination switch module. Each of the electrical signals is then transmitted to one of Q EAM MOD1, MOD2, … …, MODQ. At this time, each of the electrical signals contains information corresponding to data in the packet slice and information about a destination switch module of the packet.

Consider now the package slices incident on MOD 1. MOD1 has two inputs: (a) electrical package slice, and (b) from a light source LS1 with a given wavelength λ₁Of (2) is detected. The optical channels are chosen to minimize crosstalk and it is relatively easy to fabricate the waveguides with good yield. An optical channel spacing between 0.4nm and 2nm is preferred. The laser may have a line width as narrow as is specific to the application and is preferably no less than 1 KHz. In other configurations, the frequency resolution and spacing will depend on the finesse of the device and thus on the passive components. If there are, for example, 8 wavelengths, the device can be quite "crude", but if more wavelengths are to be used, then higher specifications will be required.

MOD1 then modulates the light from light source LS1 to carry the information contained in the package slices, producing a slice having a given wavelength λ₁The optical signal of (1). From this point on, the data is transferred in the optical domain. Each modulator operates similarly to produce a first plurality of Q optical signals. From EAM MOD1,The Q optical package slices for each of MOD2, … …, MODQ are incident on a multiplexer MUX where wavelength division multiplexing occurs to combine the Q optical signals (from each EAM) into a single output fiber. Each of the Q optical signals has a different wavelength, so cross-talk between the signals is minimized. The multiplexed signal forming the multiplexed fabric output signal is then transmitted to an optical active switch (described in more detail later). The optical signal generated in the switch module 1 is then transmitted by the optical active switch to its destination switch module or to an intermediate switch module routed to the destination switch module. The control flow and associated hardware architecture to ensure that the signals ultimately arrive at the correct destination will be described in more detail later.

For the purposes of this description, we will continue to refer to fig. 3, but in general use, the source and destination switch modules will not be the same switch module. However, the source and destination modules may be one and the same module, e.g. for testing purposes. However, the source and destination switch modules should be substantially identical to each other so that the description based on fig. 3 still applies equally. The optical multiplex fabric input signal from the optical active switch is incident on a demultiplexer DEMUX located on the receive side Rx of the switch module 1. The multiplexed fabric input signal is demultiplexed by the demultiplexer DEMUX into a second plurality of Q optical signals equivalent to those combined at the multiplexer MUX on the source switch module 1. The Q demultiplexed signals are then incident on each of the arrays of photodetectors PD1, PD2, … …, PDQ. In the photodetector, the demultiplexed signal is converted back into a second plurality of Q electrical signals, again containing the information contained in the original packet slice. The electrical signals are then transmitted to the packet processor PP-Rx where they are recombined into the original packets incident on the packet processor PP-Tx of the source switch module 1, using the information contained in the header of the packet slice.

In some embodiments, each fabric section on a given switch module 1 has its own associated multiplexer and demultiplexer.

However, in an alternative configuration, as shown in fig. 4, it can be seen that this is not the case. In this case, EAM MOD1, MOD2, … …, MODQ (and its associated light sources), photodetector PD1, PD2, … …, PDQ, multiplexer WDM-MUX, and demultiplexer WDM-DEMUX are shared among the N constituent ports. The diagram is divided into two sections to show which flows occur in the optical domain and which in the electrical domain. In this embodiment, there is an additional array of multiplexers and demultiplexers, shown to the left of the dashed line. In contrast to the multiplexer MUX at the output of EAM MOD1, MOD2, … …, MODQ for wavelength division multiplexing, the multiplexer to the left of the dashed line is configured to multiplex the signals together in the electrical domain rather than the optical domain. The same applies to the demultiplexer DEMUX. In another implementation, the multiplexer and demultiplexer may be in the form of CMOS combinational logic circuits integrated into the switch module. The history of packets from the source switch module to the destination switch module will now be described with reference to figure 4. In the case where the flow or the components are the same as those in fig. 3, the description will not be repeated here. The packets entering the first component part pass through the packet processor PP-Tx as before, wherein in this case the packets are divided into three packet fragments, each in the form of an electrical signal. Similarly, at the same time, the packet arriving at the fabric part F2 enters the packet processor PP-Tx on the second fabric part and is also split into three packet fragments, again all in the form of electrical signals. The three optical packet fragments generated by the packet processors PP-Tx of each of the first and second constituent parts are then issued to three different multiplexers MUX. In other words, each of the multiplexers MUX receives two electrical signals, each corresponding to a packet fragment from a different packet, one electrical signal incident on the PP-Tx on the first component part and one electrical signal incident on the PP-Tx on the second component part. These two signals are then multiplexed into a single multiplexed electronic signal, which is then transmitted to one of EAM MOD1, MOD2, … …, MODQ. As in fig. 3, the EAM modulates the signals from the light sources LS1, LS2, … …, LSQ so as to produce an optical signal carrying the information previously carried by the electrical signal, each EAM MOD1, MOD2, … …, MODQ producing a signal having a different wavelength. Thus, as in FIG. 3, the optical signals output from EAM MOD1, MOD2, … …, MODQ are wavelength division multiplexed into a single optical fiber by a multiplexer WDM-MUX. For each time slot used to transmit a signal, an arbitration step is necessary in order to determine which fabric portion is eligible to use the optical transmission path. Only one input to each multiplexer MUX can be reached at any given time to avoid data loss. Equivalently, on the reverse path, the demultiplexer DEMUX must be similarly controlled to send incoming packets to the correct receive fabric portion, etc.

In addition to NxN optical active switches, 1xK additional optical multiplexers/demultiplexers are required, since in this configuration each switch module has only one optical transmitter and receiver, which must be optically coupled to K different optical fibers (in both directions) for different dimensions, and therefore, these multiplexers also need to be properly controlled to properly direct the signals. For the demultiplexer DEMUX this means that the dimension along which the transmission is to be carried is selected. For a multiplexer WDM-MUX this implies that all switch modules connected to this module need to be coordinated in such a way that only one of the incoming fibers carries a valid signal in any given time slot. To achieve this, the configuration shown in FIG. 4 requires that the arbiters be connected along all dimensions.

Also, as described above, the signal is received by a switch module different from the switch module transmitting the signal, but for convenience and brevity, the reception-side Rx process will be described herein with reference to the same drawing. The demultiplexer WDM-DEMUX demultiplexes the optical signal received from the 1xK demultiplexer into the same Q signals that enter the multiplexer WDM-MUX. One of the demultiplexed optical signals is then incident on each of the photodetectors PD1, PD2, … …, PDQ, which convert the optical signal back into a corresponding electrical signal. Each of the photodetectors PD1, PD2, … …, PDQ outputs said electrical signal to one of the three electrical domain demultiplexers DEMUX, so as to be demultiplexed into its two constituent electrical signals, i.e. one electrical signal originally coming from the first constituent part (in fig. 4) and one electrical signal originally coming from the second constituent part. Each of the three electrical domain demultiplexers DEMUX outputs two signals, packet fragments from the packet processors PP-Tx on each of the fabric sections. The three received packet fragments for each fabric portion are then combined at the packet processor PP-Rx on each fabric portion to reproduce the original packet originally incident on the source switch module. Thereafter, the packet may be transmitted to another fabric portion for transmission into another dimension, or to a client portion for transmission to an external device connected to the optoelectronic switch.

The configuration shown in fig. 4 requires time division multiplexing as well as wavelength division multiplexing in order to grant access to the fabric portions for each dimension. This can be done using strict time-division multiplexing rules, i.e. sequentially through successive texture parts. Alternatively, time division multiplexing may be performed in a more flexible manner-as long as only a single fabric portion is eligible to transmit signals in a given time slot. In an alternative and more advanced configuration, it is possible to split the available wavelengths, then have multiple fabric portions transmitting simultaneously, but at different wavelengths. Then, by using cyclic AWGs for the multiplexer WDM-MUX and demultiplexer WDM-DEMUX, more than one fabric portion can be transmitted along different dimensions simultaneously by using disjoint subsets of the available wavelengths.

Figure 5 shows an example of a 1D optoelectronic switch. This example demonstrates the basic connectivity of the optoelectronic switch fabric of an embodiment of the present invention, as well as notations that can be used to conveniently describe more complex multi-dimensional optoelectronic switches.

Each of the small squares in the middle row of the figure represents a single switch module as shown, for example, in fig. 3 and 4. The ellipses below these squares represent client ports that can be connected to external devices. As for the description of the connectivity of the switch modules, the fabric part and the client part are largely independent of each other, and therefore will not be discussed in the following description. The switch module represents the smallest building block of the optoelectronic switch of some embodiments, and is referred to herein as a layer 0 switch. In the following description, a layer i switch, where i >0, is an active switch that provides connections between switch modules (i.e., layer 0 switches) along the ith dimension, i.e., between switch modules having the same coordinates (except for the coordinates in the ith direction). Each of the layer 0 switches (labeled S1) is connected to an optical active switch (labeled S2) represented by a long rectangle. This switch is referred to as a layer 1 switch in this figure and has 8 bidirectional inputs/outputs.

The following notation will be used to describe an array of layer 0 switches in various configurations/architectures of embodiments of the present invention. The switch fabric as a whole may be described using the notation (N, R), where N is the number of layers of optical switches in the switch fabric, which is equal to the number of dimensions, and R is the form { R }₁,R₂...R_NThe vector of (i) gives the cardinality of each layer, which is the same as the "size" of the dimension as defined in the "summary of the invention" section, where cardinality gives each active in layer i (i.e. layer i, where i is>0) The number of layer 0 switches to which the switch is connected. More specifically, a layer is an array of active switches or switch modules. In the following description, a layer 0 switch represents a switch module (e.g., as shown in fig. 3), and a layer i switch (where i is>0) Representing an active switch. The layers include all of the switches associated with switching optical signals within a given dimension, and thus there are N layers in an N-dimensional switch. In this notation, the optoelectronic switch shown in fig. 5 can be described as an (N-1, R-8) switch because the highest level switch is a layer 1 switch and the highest level switch is connected to all eight layer 0 switches. Number of switches t in ith layer_iEqual to the product of the cardinality of the dimensions up to the ith dimension, i.e.

In other words, t_iEqual to the product of terms in the vector R that do not refer to the ith dimension.

Each individual optical switch may be labeled as follows: s (i; C), where i denotes the layer in which the switch is located, e.g. layer 0, layer 1, etc., and C is a vector with (N-1) elements, corresponding to the position of the switch at layer i within its layer, the cardinality at the layerExcept for the layer corresponding to the switch. For example, in a layer 3 network, a switch in layer 2 has C ═ (C)₁,c₃) Wherein c is₁And c₃Indicating a label for the switch with respect to the layer.

Fig. 6 shows a schematic example of a 2D optoelectronic switch classified according to the above notation as (N-2, R-8, 4). In this particular embodiment, there are 32 (i.e., 8x4) layer 0 switches connected together. Each of the 32 layer 0 switches has two fabric ports, one for connecting to switches in layer 1 and one for connecting to switches in layer 2. Because 32 layer 0 switches are organized into 4 groups of 8 switches, there are 4 layer 1 switches and 8 layer 2 switches. This figure clearly shows an important property of an optoelectronic switch according to an embodiment of the present invention, namely that the maximum number of optical hops required from one layer 0 switch to any other layer 0 switch is the number of layers in the switch fabric (i.e., N). For example, consider the transfer of data from a switch labeled S1 to a switch labeled S2, where the hops are shown with thicker lines. First, data is transferred from switch S1 to switch S3 via switch S4. Next, in the second hop, the data is transferred from switch S3 to S2 via switch S5. Thus, it can be seen that in a switch according to an embodiment of the present invention, data may be transmitted in a series of optical hops, each via a layer i switch in a different layer.

More specifically, at each stage, packets are transferred from one layer 0 switch to another layer 0 switch, as described above with reference to fig. 3, and then the packets may be required to be transmitted via electronic hops within the layer 0 switches themselves before the next optical hop can occur; however, electronic hopping does not significantly slow down operation because electronic data transfer has lower latency, integrated switches have a lower associated cardinality, and flight time does not need to be considered. Furthermore, since the transfer is simply from one fabric portion to another within the same layer 0 switch, no external arbitration or control is required either.

FIG. 7 shows thisAn alternative schematic of a 2D optoelectronic switch having (N-2, R-8, 8). This switch has the same properties as the switch shown in fig. 6. This switch also more clearly shows the interrelationship between the layer i switch and the layer 0 switch. In particular, it can be seen that the layer 0 switches are arranged in an 8x 8 array, with layer 1 switches associated with each row and layer 2 switches associated with each column. More specifically, since each tier 0 switch has a fabric portion associated with each of the tiers, it can be seen that the tier i (i ≠ 0) switch provides a route between a given tier 0 switch and each other tier 0 switch (which has the same coordinates in all tiers except tier i). (wherein the coordinates within layer i are in the range 0 to t_iA value of-1, t_iIs the number of active switches in layer i). This can also be seen in fig. 8, which fig. 8 shows a 3D optoelectronic switch with (N-3, R-8, 4, 2). Here, it is possible to reach from any layer 0 switch to any other layer 0 switch with up to 3 optical hops, each via a different layer i (i ≠ 0) switch. It can be seen that the 3D optoelectronic switch of figure 8 is formed by placing two of the 2D switches shown in figure 6 side by side and introducing an array of 32 layers 3 to provide the required interconnected rows. 32 layer 3 switches are required because layer 3 switches are required for each set of layer 0 switches with the same coordinates in layer 1 and layer 2. Since there are effectively 2 groups each of 8x4 layer 0 switches, it can be seen that 32 layer 3 switches are necessary, each switch being connected to one layer 0 switch in the first set and one layer 0 switch in the second set. Thus, the layer 3 switches shown in fig. 8 each have two connections. More simply, the number of switches in each layer i (i ≠ 0) is equal to the product of the cardinalities of each of the other layers i (i ≠ 0).

Figures 9A to C show further arrangements of optoelectronic switches according to embodiments of the present invention. In these examples, all active switches have the same cardinality, referred to herein as R. In the above notation, this is denoted as R ═ { R, R } ═ {4,4,4 }.

In order for a layer i (i ≠ 0) switch to operate correctly and to send the optical signal to the correct destination layer 0 switch, the switch must be controlled by an arbiter. Fig. 11 shows a schematic diagram of how the arbiter is connected to the layer i (i ≠ 0) optical active switch. For example, the input to the arbiter is connected to the controller CTRL as shown in fig. 3 and 4. These controllers CTRL receive inputs from packet processors, such as PP-Tx and PP-Rx, associated with the intended destination into which the packets are to be injected. This information is then forwarded to the arbiter, which calculates the optimal operating scheme for the layer i (i ≠ 0) optical active switch to reach the correct destination layer 0 switch for all signals, i.e., to provide a data transfer route to pair each transmit side of the fabric portion with the correct receive side of the fabric portion, thereby providing non-blocking operation. This calculated operating scheme is then transmitted to a switch driver which drives and controls the operation of the optical active switch by layer i (i ≠ 0) in order to achieve an efficient switching of the optical signals received at its input.

Fig. 10 illustrates the connections between a layer 0 switch and an arbiter in an exemplary 3x 3 optoelectronic switch. Much like a layer i (i ≠ 0) optical active switch, there is an arbiter associated with each subarray of a layer 0 switch having the same coordinates in all but one layer. In the 2D case, i.e. with only two layers, this means that each row is associated with a row arbiter RA and each column is associated with a column arbiter CA. Thus, data transfer between layer 0 switches in the same row can be controlled by the associated row arbiter RA, followed by subsequent optical jumps between rows (via layer i (i ≠ 0) optical active switches) can be controlled by the associated column arbiter CA. As explained elsewhere in this application, the switches may be connected using optical or electronic switches. In the case of an electronic switch using, for example, shared memory, a separate arbiter as shown in fig. 10 may not be required.

Fig. 12 shows an example of an arrangement of MZIs inside an optical MZI cascaded switch that can be used as an optical active switch in embodiments of the present invention. Solid rectangles indicate individual MZIs. Using the notation of the "summary of the invention" system, it can be seen thatIn this particular configuration, the MZI cascaded switch has R_i＝4＝2²(i.e., n-2) inputs and outputs. The input side may consist of four 1x 4 "trees" (one tree highlighted with a dashed square), each tree comprising two levels of 1x2 MZIs. The output side has a mirror image arrangement. The inner two layers of 1x2 MZIs are connected so that routes from all inputs to all outputs can be provided simultaneously in a non-blocking manner. In other words, 4!of possible input-output terminals between the four input terminals and the output terminal! Each of the 24 combinations will be accommodated by this MZI cascaded switch. A switch driver such as that shown in fig. 11 is configured to control which of the 24 combinations should be selected by controlling the voltage applied to each 1x2MZI electro-optic zone.

Figure 13A shows an arrangement of components to be used when using an electronic active switch instead of an optical active switch as shown in figure 12. For simplicity, only one switch module is shown. The bidirectional link shown carries the multiplex fabric output signal towards the (electronic) shared memory switch SMS. At the SMS, the signal is incident on a demultiplexer DEMUX configured to split the multiplexed signal into a plurality of optical signals. The DEMUX has substantially the same structure as the MUX (shown in an enlarged view) but the opposite is true. The equivalent of the module labeled "Rx" or "Tx" on the DEMUX acts as an optical-to-electronic (O/E) converter for converting an optical signal into a plurality of electronic signals, which are then switched by the SMS to the correct output. The module "Rx" or "Tx" then acts as an electronic-to-optical (E/O) converter to convert the switch electronic signals into optical signals, which are then multiplexed to form a multiplexed fabric input signal. This signal is then carried by an optical (WDM) fibre to the correct switch module.

Figure 13C shows an arrangement similar to that in figures 13A and 13B in which, instead of using a single electronic active switch to connect the switch modules located in each sub-array of switch modules, a plurality or group of electronic active switches are used. It should be noted that it is also possible to use a set of optics, for example of the type described in the preceding paragraphAn active switch. Topologically, these two approaches are the same, and for the sake of brevity only the embodiment using an electronic active switch is described in detail. Using multiple switches to interconnect the switch modules in each sub-array results in a large split bandwidth. This situation will be best understood from a comparison between fig. 13B and 13C, which are drawn using similar layouts. In these examples, there are R sets of R switch modules, which can be viewed, for example, as a square array with R columns and R rows, (the switch modules being labeled 1 through R²). In this particular case, the subarray is:

dimension 1: each of the R sets having R switch modules, an

Dimension 2: a set of switch modules having the same location within each of the R sets.

In the arrangement shown in fig. 13B, a single electronic active switch is used to connect all switch modules in a given sub-array, as also shown, for example, in fig. 9B. However, in an alternative embodiment, rather than using a single electronic active switch to interconnect the sub-arrays, an array of S electronic active switches is used instead, as shown in figure 13C. In the illustrated embodiment, the connections between switch modules in a given sub-array via electronic active switches are in the form of a claus network and more particularly a folded claus network, since the links are bi-directional. However, other network topologies may be used to interconnect the sub-arrays. In this embodiment, there are S electronic active switches within each group. Preferably, S is chosen to be equal to the number of client ports on each of the switch modules.

Figure 14A shows a two-dimensional example of a connection in an optoelectronic switch according to an embodiment of the present invention as described in more detail above, with the backbone of the second (blue) dimension not shown. In fig. 14A, the leaf switches are depicted only once in the collapsed configuration. Similarly, FIG. 14B shows a folded representation of a two-dimensional optoelectronic switch according to the present invention. Fig. 14C shows an alternative expanded representation of a 2-dimensional optoelectronic switch that includes an array of sixty-four leaf switches at the edges of the figure, and two sets of sixteen backbone switches in the center (each associated with switching of each of the dimensions). The red lines represent connections in one dimension, while the blue lines represent connections in the other dimension.

Although exemplary embodiments of the switch module and optoelectronic switch have been specifically described and illustrated herein, many modifications and variations will be apparent to those skilled in the art. It should be understood, therefore, that a switch module or optoelectronic switch constructed in accordance with the principles of the present invention may be implemented other than as specifically described herein. The invention is also defined in the claims and equivalents thereof.

Claims

1. A switch module for use in an optoelectronic switch, the switch module having:

a client portion for connecting to an input device or an output device;

the transmission side has:

a transmit side input for receiving a first electronic signal carrying information, the information comprising information about a destination switch module of the first electronic signal, the first electronic signal being received from an output of the second component part or from an input device via the client part;

the receiving side has:

A receive side output for sending the second electronic signal to a transmit side input of the second component part or to an output device via the client part.

2. The switch module of claim 1, wherein the transmit side conversion means comprises a transmit side packet processor configured to receive the first electronic signal in the form of an original packet having a packet header containing destination information.

3. The switch module of claim 2, wherein the transmit side packet processor is configured to perform packet fragmentation, wherein:

data packets having the same destination module are arranged into frames having a predetermined size; and is

The data packet is segmented into a plurality of packet fragments arranged in a corresponding plurality of frames;

wherein the receive-side conversion means comprises a receive-side packet processor configured to reconstruct the packets from the packet fragments when the original packets are dispersed in more than one frame.

4. The switch module of claim 3, wherein the switch module is configured to send the multiplexed fabric output signal in a series of consecutive bursts, each burst comprising packets and/or packet fragments from a single frame, such that each burst comprises only packets and/or packet fragments having the same destination module, and pairs of sequential bursts are separated by time intervals.

5. The switch module of claim 2, wherein:

the transmission side converting means comprises a plurality of modulators;

the transmit side packet processor is configured to perform packet slicing in which frames or packets are sliced into a first plurality of electronic signals; and is

The transmit-side packet processor is configured to send each of the first plurality of electronic signals to a different one of the plurality of modulators, whereby the first plurality of electronic signals is converted into the first plurality of optical signals.

6. The switch module of claim 5, wherein the receive-side conversion means comprises a plurality of photo-detectors configured to convert the second plurality of optical signals into a second plurality of electronic signals, and further comprising a receive-side packet processor configured to reassemble the second plurality of electronic signals into the second electronic signal.

7. The switch module of claim 6, wherein the transmit side packet processor and/or the receive side packet processor are connected to a controller for connection to an arbiter.

8. The switch module of claim 7, wherein the transmit side packet processor is configured to send a request to the arbiter, the request identifying a destination switch module for a packet.

9. The switch module of claim 8, wherein the transmit side packet processor is configured to use a lookup table or otherwise to find which output of an active switch to which the transmit side packet processor is connected corresponds to the destination switch module that is the subject of the request.

10. The switch module of claim 1, wherein either or both of the transmit side multiplexer and the receive side demultiplexer are Arrayed Waveguide Gratings (AWGs).

11. The switch module of claim 1, wherein the switch comprises means for connecting to an optical backplane.

12. An N-dimensional optoelectronic switch for transmitting optical signals from an input device to an output device, the optoelectronic switch comprising a plurality of switch modules according to claim 1, the switch modules being interconnected, wherein:

the switch modules are arranged in an N-dimensional array, the ith dimension having a size R_iN, each switch module having an associated set of coordinates giving its position relative to each of the N dimensions;

each switch module is N sub-arrays S_iMember of (2), each subarray S_iComprising R_iA switch module, said R_iThe coordinates of the switch modules differ only with respect to their position in the ith dimension, and each of the N sub-arrays is associated with a different dimension;

each subarray S_iAlso includes having R_iAn input terminal and R_iAn active switch at each output;

each input of each active switch is configured to receive the R from the sub-array_iA multiplexed fabric output signal for each of the individual switch modules; and is

The active switch is configured to multiplex a fabric output signal from its R based on destination information contained in the first electronic signal received at the transmit-side input of the switch module_iAny one of the input ends is led to the R_iAny one of the outputs from which the active switch receives the multiplexed fabric outputA signal.

13. The optoelectronic switch of claim 12, wherein each switch module has at least N group members, each of the N group members associated with a different sub-array S_iIn association, the switch module is the sub-array S_iIs a member of (1).

14. The optoelectronic switch of claim 12, wherein the active switches are located on and connected to an optical backplane, the optical backplane further comprising a plurality of optical links for providing connections between switch modules and active switches, the switch modules sharing a subarray S with active switches_i。

15. The optoelectronic switch of claim 12, wherein the active switch is an optical active switch or an electronic active switch.

16. The optoelectronic switch of claim 15, wherein the active switch is a mach-zehnder interferometer (MZI) cascade switch comprising a plurality of MZIs, each MZI having: two arms split at the input coupler and feeding the split paths into the output coupler where they are recombined; and two output sections, the plurality of MZIs arranged to provide a path from each input to each output of the MZI cascaded switch.

17. The optoelectronic switch of claim 15, wherein each electronic active switch further comprises:

an opto-electrical converter at each input for converting the multiplexed fabric output signal from an optical signal to an electronic active switching signal; and

an electro-optical converter at each output for converting the electronic active switching signal into an optical signal in the form of the multiplexed fabric input signal;

wherein the electronic active switch is configured to R the electronic active switch signal from_iTo which any one of the inputs is switched_iAny one of the output terminals, and

wherein:

the photoelectric converter includes: a demultiplexer for demultiplexing the multiplexed fabric output signal into a first plurality of intermediate optical signals, and a corresponding plurality of photo-detectors for converting each of the intermediate optical signals into an intermediate electronic active switching signal for switching to a desired output, and

the electro-optical converter is configured to convert a plurality of converted intermediate electronic active switching signals into a second plurality of intermediate optical signals, and further comprises a multiplexer for multiplexing the second plurality of intermediate optical signals to form the multiplexed fabric input signal.

18. The optoelectronic switch of claim 12, wherein each subarray S of the switch module_iFurther comprising an arbiter configured to control the sub-array S based on destination information stored in a data packet to be exchanged_iThe operation of the active switch included in (1).

19. The optoelectronic switch of claim 18, wherein the arbiter is connected to the sub-array S_iAt least one of a transmit side packet processor and a receive side packet processor on each switch module in the network and configured to receive requests from each of the transmit side packet processors to which the arbiter is connected.

20. An N-dimensional optoelectronic switch for transmitting optical signals from an input device to an output device, the optoelectronic switch comprising a plurality of switch modules according to claim 1, the switch modules being interconnected, wherein:

each subarray S_iFurther comprising one or more active switches arranged to provide connections between all of the switch modules in the sub-array;

Each of the one or more active switches is configured to direct a multiplexed fabric output signal from any switch module of the sub-array to any other switch module of the sub-array based on destination information contained in the first electronic signal received at the transmit side input of the switch module from which the active switch receives the multiplexed fabric output signal.

21. The optoelectronic switch of claim 20, wherein R_iSub-arrays of switch modules comprising only R_iAn input terminal and R_iA single active switch at each output, and:

the switchEach of the modules is configured to receive the R from the active switch_iA multiplexed configuration of one of the outputs constituting an output signal, an

The active switch is configured to multiplex a fabric output signal from its R based on the destination information contained in the first electronic signal received at the transmit-side input of the switch module_iAny one of the input ends is led to the R_iAny one of a plurality of outputs, the active switch receiving the multiplexed fabric output signal from the switch module.

22. The optoelectronic switch of claim 20, wherein R_iAt least one sub-array of a switch module includes a plurality of P_subActive switch, the plurality of P_subThe active switches are arranged to form a network connecting each switch module in the sub-array with each other switch module in the sub-array.

23. The optoelectronic switch of claim 22, wherein:

P_subthe value of (c) is the same for all sub-arrays comprising a plurality of active switches, and/or R_iAll of the switch modules of the at least one sub-array of switch modules have the same number of client ports, and P_subIs equal to the number of client ports on each of the switch modules.

24. The optoelectronic switch of claim 22, wherein each switch module in a given sub-array is connected to an active switch via an intermediate switch.

25. The optoelectronic switch of claim 24, wherein the intermediate switch is one of an optical active switch, an electronic active switch, and an electronic packet switch.

26. The optoelectronic switch of claim 24, wherein the intermediate switch is bidirectional.

27. The optoelectronic switch of any one of claims 24 to 26, wherein the switch modules, intermediate switches, and active switches are arranged in one of: a folded claus network, an expanded claus network, a partially folded claus network, or a claus-like network.