Dynamic reconfigurable method and device for on-chip optical network

Abstract

The embodiment of the invention provides a dynamic reconfigurable method and device for an on-chip optical network. The method comprises the following steps: receiving task data; based on the task data, selecting a target topological structure, and determining nodes and links forming the target topological structure; generating a global routing table based on the target topological structure and nodes and links forming the target topological structure; and issuing the global routing table, so that the on-chip optical network forwards the task data according to the global routing table. The method can adapt to diversified task requirements, improve the flexibility and adaptability, and give full play to the performance and potential of the system.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of communication technologies, and in particular, to a dynamic reconfiguration method and apparatus for an on-chip optical network. Background Art

[0002] Optical network chips have significant advantages such as high bandwidth, low latency, and low power consumption, and can effectively realize the interconnection between various processing cores, thereby obtaining higher performance transmission. With the increasing demand for high communication bandwidth and high-performance computing, the on-chip optical network using wavelength-division multiplexing technology can effectively improve the communication bandwidth by coupling and multiplexing multiple optical signals with different wavelengths into a single waveguide for transmission, opening up a new path for future high-performance on-chip network communication requirements.

[0003] In an on-chip optical network, with the continuous emergence of various complex tasks, the configuration of network nodes and links needs to be continuously adjusted to adapt to the communication load and data traffic of different tasks. The traditional static network architecture has been difficult to meet the efficient processing requirements. And the reconfigurable topology technology mainly has problems such as limited flexibility in topology switching and insufficient ability to perceive task loads. Summary of the Invention

[0004] In view of this, the purpose of the embodiments of the present application is to propose a dynamic reconfiguration method and apparatus for an on-chip optical network to solve the problem of reconfiguring the topological structure based on tasks.

[0005] Based on the above purpose, the embodiments of the present application provide a dynamic reconfiguration method for an on-chip optical network, including:

[0006] Receiving task data;

[0007] Based on the task data, selecting a target topological structure and determining the nodes and links that make up the target topological structure;

[0008] Generating a global routing table based on the target topological structure and the nodes and links that make up the target topological structure;

[0009] Issuing the global routing table so that the on-chip optical network forwards the task data according to the global routing table.

[0010] Optionally, the task data includes task priority, data volume, execution time, and task parameters; based on the task data, selecting a target topological structure and determining the nodes and links that make up the target topological structure includes:

[0011] Determining the task type according to the task priority, data volume, execution time, and task parameters;

[0012] Selecting a target topological structure corresponding to the task type according to the task type;

[0013] Obtain the resource status of all nodes;

[0014] Based on the target topology structure and the resource status of all nodes, determine the nodes and the links between nodes that form the target topology structure.

[0015] Optionally, based on the target topology structure and the resource status of all nodes, determining the nodes and the links between nodes that form the target topology structure includes:

[0016] According to the resource status of all nodes and links, if nodes that form the target topology structure cannot be selected, according to the task type, re-select other target topology structures corresponding to the task type, and based on the other target topology structures and the resource status of all nodes, determine the nodes and the links between nodes that form the other target topology structures.

[0017] Optionally, after determining the nodes and links that form the target topology structure, it further includes:

[0018] Send an activation signal to the nodes, and send a deactivation signal to the nodes that do not form the target topology structure;

[0019] Send a conduction signal to the links.

[0020] Optionally, after sending a conduction signal to the links and a non-conduction signal to the links that do not form the target topology structure, it further includes:

[0021] Send a detection signal to the target topology structure;

[0022] If the feedback signal of the target topology structure is not received, or the transmission quality is evaluated to be lower than the preset quality threshold according to the feedback signal, optimize the link state by adjusting the parameters of the microring resonator.

[0023] An embodiment of the present application further provides a dynamically reconfigurable device for an on-chip optical network, including:

[0024] A receiving module, configured to receive task data;

[0025] A selection module, configured to select a target topology structure based on the task data, and determine the nodes and links that form the target topology structure;

[0026] A generation module, configured to generate a global routing table based on the target topology structure and the nodes and links that form the target topology structure;

[0027] A distribution module, configured to distribute the global routing table, so that the on-chip optical network forwards the task data according to the global routing table.

[0028] Optionally, the task data includes task priority, data volume, execution time, and task parameters;

[0029] The selection module is configured to determine a task type according to the task priority, data volume, execution time, and task parameters; select a target topology structure corresponding to the task type according to the task type; obtain the resource status of all nodes; and determine the nodes and links between nodes that form the target topology structure based on the target topology structure and the resource status of all nodes.

[0030] Optionally, the selection module is configured to, according to the resource status of all nodes and links, if nodes that form the target topology structure cannot be selected, reselect another target topology structure corresponding to the task type according to the task type, and determine the nodes and links between nodes that form the other target topology structure based on the other target topology structure and the resource status of all nodes.

[0031] Optionally, the apparatus further includes:

[0032] An activation module configured to send an activation signal to the nodes, send an inactivation signal to the nodes that do not form the target topology structure; and send a conduction signal to the links.

[0033] Optionally, the apparatus further includes:

[0034] A detection module configured to send a detection signal to the target topology structure; if a feedback signal of the target topology structure is not received, or if the transmission quality is evaluated to be lower than a preset quality threshold according to the feedback signal, optimize the link state by adjusting the parameters of the microring resonator.

[0035] As can be seen from the above, the dynamic reconfiguration method and apparatus for an on-chip optical network provided in the embodiments of the present application select a target topology structure based on task data, determine the nodes and links that form the target topology structure, generate a global routing table based on the target topology structure and the nodes and links that form the target topology structure, and issue the global routing table, so that the on-chip optical network forwards task data according to the global routing table. The present application can adapt to diverse task requirements, improve flexibility and adaptability, and give full play to the performance and potential of the system. Description of the Drawings

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0037] Figure 1 Schematic diagram of the method flow of the embodiment of the present application;

[0038] Figures 2A - 2E Schematic diagrams of five topological structures of the embodiment of the present application;

[0039] Figure 3 Schematic diagram of the structure of the microring resonator of the embodiment of the present application;

[0040] Figure 4 Schematic diagram of the connection structure of the on-chip optical network of the embodiment of the present application;

[0041] Figure 5 Schematic diagram of the process of task-driven topology configuration of the embodiment of the present application;

[0042] Figure 6 Block diagram of the device structure of the embodiment of the present application;

[0043] Figure 7 Block diagram of the structure of the electronic device of the embodiment of the present application. Detailed implementation manners

[0044] To make the purpose, technical solutions and advantages of the present disclosure clearer and more understandable, the following further describes the present disclosure in detail with reference to specific embodiments and the accompanying drawings.

[0045] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the ordinary meanings understood by those of ordinary skill in the field to which the present disclosure belongs. The "first", "second" and similar terms used in the embodiments of the present application do not indicate any order, quantity or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0046] In the related art, most of the architectures of on-chip optical networks mainly adopt fixed topologies, which are difficult to effectively cope with the dynamic changes of task requirements and the unbalanced distribution of loads. When facing diverse tasks, the low flexibility of the fixed topology makes it difficult to fully utilize the potential of hardware resources, resulting in performance bottlenecks in the system when dealing with multi-task environments. When facing sudden tasks, due to the lack of adaptive adjustment ability, the communication efficiency will be greatly reduced, and even phenomena such as system congestion and performance degradation will occur.

[0047] In view of this, the embodiments of the present application provide a dynamic reconfiguration method for an on-chip optical network, which can adaptively adjust the network topology according to tasks, ensure that the on-chip optical network can always maintain an efficient and stable operating state under different task scenarios, effectively improve task adaptability and network robustness, and provide strong network support and guarantee for the high-performance operation of optical network chips.

[0048] Hereinafter, the technical solution of the present application will be further described in detail through specific embodiments.

[0049] As Figure 1 shown, the embodiments of the present application provide a dynamic reconfiguration method for an on-chip optical network, including:

[0050] S101: Receive task data;

[0051] In this embodiment, the on-chip optical network system receives task data through a task receiving interface and transmits and processes the task data. Among them, the system can process different types of tasks, and the task types include tasks with high reliability and fault tolerance requirements, large-scale parallel computing tasks, tasks with low frequency, small data volume and low real-time requirements, tasks with high real-time requirements, tasks with a hierarchical structure and requiring centralized resource management, etc. The received task data includes task priority, data volume, execution time, task parameters. The execution time includes the time constraints of the task, such as the length of the execution time and the frequency of data update; the task parameters are specific parameters of various tasks, such as control instructions for control tasks, calculation parameters for calculation tasks, monitoring parameters for monitoring tasks, etc. According to the impact degree of the task on system security, timeliness, and resource consumption, different types of tasks correspond to different priorities. For example, tasks with high reliability and fault tolerance requirements have the highest priority, tasks with high real-time requirements are the second highest priority, large-scale parallel computing tasks are medium priority, tasks with a hierarchical structure and requiring centralized resource management are medium-low priority, and tasks with low frequency, small data volume and low real-time requirements have the lowest priority. When there are resource conflicts, low-priority tasks can be downgraded or delayed to ensure the stability of high-priority tasks.

[0052] S102: Based on the task data, select a target topology structure, and determine the nodes and links that make up the target topology structure;

[0053] In this embodiment, after receiving the task data, by analyzing the task data, a target topology structure suitable for executing the task is selected from a variety of supported topology structures, and the nodes and links that make up the target topology structure are selected.

[0054] Among them, based on the task data, selecting a target topology structure and determining the nodes and links that make up the target topology structure includes:

[0055] Determine the task type according to the task priority, data volume, execution time, and task parameters;

[0056] Select the target topology structure corresponding to the task type according to the task type;

[0057] Obtain the resource status of all nodes;

[0058] Determine the nodes and the links between nodes that make up the target topology structure based on the target topology structure and the resource status of all nodes.

[0059] In this embodiment, by parsing the task data, the task priority, data volume, execution time, task parameters, etc. are obtained. According to the high or low task priority, the size of the data volume, the length of the execution time, the frequency of data update, etc., the bandwidth and transmission frequency expected to be occupied by executing the task are calculated, the resources required for executing the task are comprehensively evaluated, and the task type to which it belongs is judged. For example, the data volume of the environmental monitoring task is small, only dozens of bytes of data are transmitted each time, and the transmission frequency is low. Therefore, the demand for bandwidth is low, and the nodes mainly perform data forwarding, without complex calculations, and have low requirements for memory occupancy. The energy consumption of the entire task is mainly concentrated on sensor data collection and short-distance transmission, and the overall demand for network energy consumption is small.

[0060] After determining the task type, select the target topology structure suitable for executing this type of task; at the same time, obtain the resource status of all nodes in the system, and select the nodes that make up the target topology structure according to the resource status of all nodes, as well as the links connecting the nodes according to the target topology structure. Among them, the resource status of the nodes includes the physical location of the nodes, the occupied resources, the remaining resources, the link status (conditions such as the availability, quality, and load of the links), etc. When selecting nodes, preferentially select nodes with close distances, more remaining resources, and link status meeting the target topology requirements, that is, preferentially select nodes that are convenient to connect and have low load, so as to ensure the quality and efficiency of task execution.

[0061] In this embodiment, for different task types, five topology structures that support the dynamic reconfiguration of the on-chip optical network system are provided, including torus topology, Mesh topology, Ring topology, star topology, and tree topology.

[0062] Such as Figure 2AAs shown in the figure, the torus topology has the characteristics of high fault tolerance and relatively short average path length, which can ensure reliable and efficient data transmission in complex network environments, effectively avoiding data loss and system performance degradation caused by link failures or transmission delays, and is suitable for performing tasks with high reliability and fault tolerance requirements. For example, in aerospace aircraft, various sensors and on-board devices need to continuously, stably and rapidly exchange data, and any interruption or error in data transmission may lead to serious consequences. Even if some links in the torus topology are interfered with or physically damaged, the data can still quickly bypass the fault point through redundant paths and accurately reach the destination node, thus providing strong guarantee for the communication network of the aircraft.

[0063] As Figure 2B shown in the figure, the Mesh (rectangular) topology has the ability of many-to-many connections with high bandwidth and low latency, enabling each node to communicate quickly with other nodes, realizing efficient data sharing and collaborative computing, and is suitable for performing large-scale parallel computing tasks.

[0064] As Figure 2C shown in the figure, the Ring topology has a simple structure and a fixed data transmission path, and is suitable for performing tasks with relatively small data volume, relatively low transmission frequency and not high requirements for real-time performance. For example, in an environmental monitoring system, multiple sensors periodically collect monitoring data (such as temperature, humidity, air quality, etc.) and transmit it to the central node for analysis and processing.

[0065] As Figure 2D shown in the figure, the star topology has the characteristic of low latency, which can ensure rapid data transmission between the central node and each endpoint, avoiding control errors caused by transmission delays, and is suitable for performing tasks with high real-time requirements. For example, in an autonomous driving vehicle, the data of sensors such as cameras and radars must be transmitted to the in-vehicle computer for processing in real time, and the control instructions of the computer also need to be quickly sent to the vehicle so that the vehicle can timely control the actuators to perform corresponding actions (such as steering, accelerating, braking, etc.) according to the control instructions. The star topology can guarantee high-speed and real-time data interaction and ensure driving safety.

[0066] As Figure 2E shown in the figure, the tree topology has a simple structure. The root node can centrally manage and control the entire network, facilitating centralized scheduling and management of resources, and usually has a short communication path and high data transmission efficiency, and is suitable for performing tasks with a hierarchical structure and requiring centralized resource management. For example, in a multi-level image recognition system, the image acquisition devices are located at the bottom layer, and the collected image data is transmitted to the upper-layer image preprocessing nodes for preliminary processing (such as noise reduction, edge detection, etc.), and then the processed data is transmitted to the higher-layer feature extraction nodes and classification nodes for final image recognition and analysis.

[0067] In some embodiments, determining the nodes and the links between the nodes that constitute the target topology based on the target topology and the resource status of all nodes includes:

[0068] According to the resource status of all nodes and links, if the nodes that constitute the target topology cannot be selected, other target topologies corresponding to the task type are reselected according to the task type, and based on the other target topologies and the resource status of all nodes, the nodes that constitute the other target topologies and the links between the nodes are determined.

[0069] In this embodiment, when selecting the nodes of the target topology, if each node that constitutes the target topology cannot be selected according to the resource status of all nodes, other target topologies suitable for executing the task need to be reselected, and the nodes that constitute the other target topologies are selected from all nodes, and the links between the nodes are connected according to the target topology. That is, if the target topology cannot be formed due to insufficient resources of some nodes or the positions of the nodes not conforming, the topology for executing the task needs to be re-determined, and the corresponding nodes are selected.

[0070] In some embodiments, for the situation where the target structure topology cannot be formed, corresponding alternative topology solutions are equipped for each task type. For example, the alternative topology for tasks with high reliability and fault tolerance requirements is the Mesh topology, the alternative topology for tasks with high real-time requirements is the tree topology, the alternative topology for large-scale parallel computing tasks is the Ring topology, the alternative topology for tasks with a hierarchical structure and centralized resource management requirements is the star topology, and the alternative topology for tasks with low frequency, small data volume, and low real-time requirements is the star topology. That is, when the target topology of a certain task type cannot be formed, the alternative topology structure solution of this type of task is selected, the nodes and links are reselected according to the alternative topology structure solution, and the task is completed using the alternative topology. Optionally, when both the target topology and the alternative topology of the task cannot be successfully formed, other topology forms can be selected, and when there are multiple selectable topologies, the relatively simple topology structure is preferably selected.

[0071] In some embodiments, since the Trous topology can not only ensure the execution of high-priority tasks but also quickly and flexibly switch to other topology structures, the system uses the pre-configured Trous topology as the basic topology structure. That is, before each new task arrives, the topology structure is first initialized to the Trous topology, and when the new task arrives, it is quickly switched to the optimal target topology structure, thereby realizing efficient resource reuse and improving the overall processing efficiency and task completion degree of the system.

[0072] In some embodiments, after determining the nodes and links that constitute the target topology, it further includes:

[0073] Send an activation signal to the nodes and an inactivation signal to the nodes that do not form the target topology structure;

[0074] Send a conduction signal to the link.

[0075] In this embodiment, after determining the target topology structure and selecting the nodes and links that form the target topology structure, the control unit sends an activation signal to the selected nodes, sends an inactivation signal to the nodes that do not form the target topology structure. The nodes that receive the activation signal set their status to activated, perform initialization operations, and enter the normal working state. The nodes that receive the inactivation signal set their status to inactivated and release the resources they occupy. At the same time, the control unit sends a conduction signal to the connection links between the nodes. After receiving the conduction signal, the optical router adjusts the switching state of the microring resonators to conduct or close the corresponding optical links to ensure that optical signals can be transmitted on the selected paths; and schedules the link conduction process through the control signaling layer to ensure the order and accuracy of signal transmission.

[0076] For example, for the Mesh topology structure, by enabling multiple horizontal and vertical links, ensure that multi-to-multi data transmission can be carried out between nodes; for the Ring topology structure, only conduct the links on the ring path and close other redundant links to reduce power consumption. The link conduction process is scheduled through the control signaling layer, and the activation of the microring resonators is triggered by the control signal to ensure that optical signals can be transmitted unobstructed on the selected paths. In some ways, in order to cope with the transient impact and optical signal reflection problems during link conduction, a short delay mechanism can be adopted to improve the smoothness of link switching and the continuity of data transmission.

[0077] In some ways, the routing table isolation is ensured by dynamically generating and incrementally updating, so that data is only transmitted on the effective paths composed of activated nodes and conducted links, excluding invalid nodes and links. The precise control of the microring resonators blocks the invalid links at the physical layer to prevent signal leakage and ensure the reliability of optical transmission.

[0078] In some embodiments, after sending a conduction signal to the link and an un-conduction signal to the link that does not form the target topology structure, it further includes:

[0079] Send a detection signal to the target topology structure;

[0080] If the feedback signal of the target topology structure is not received, or the transmission quality is evaluated to be lower than the preset quality threshold according to the feedback signal, optimize the link state by adjusting the parameters of the microring resonators.

[0081] In this embodiment, after all nodes are activated and all links are connected, an optical signal of a specific wavelength is sent from the optical router along the planned link to the control unit to feedback that the target topology has been established. After the target topology is established, the control unit sends a detection signal to the target topology to test whether the links of the target topology are normal, and detects the transmission quality of the target topology by means of statistical bit error rate, etc. If the feedback signal of the target topology is not received, or the transmission quality does not reach the quality threshold, it indicates that the quality of the established target topology is not high, and the link state is optimized by adjusting the parameters of the microring resonator.

[0082] In some ways, the method of adjusting the parameters of the microring resonator to optimize the link state can be to adjust the magnitude of the bias voltage to adjust the splitting ratio (the initial value is 1), and then adjust the amount of data leading to the target node. As Figure 3 shown, when an appropriate bias voltage is applied to the PIN diode, the microring resonator operates in a transient state, guiding α part of the light to the drop port, and at the same time forwarding the remaining (1 - α) part of the light to the through port. At this time, the splitting ratio is α / (1 - α). By adjusting the bias voltage within the range of [0, 5V], different splitting ratios within the range of [0.4, 1.8] can be obtained. Optionally, the bias voltage can be adjusted by a digital-to-analog converter. If a splitting ratio exceeding the range of [0.4, 1.8] is required, multiple microring resonators can be cascaded to obtain it.

[0083] After adjustment, if the feedback signal still cannot be received or the transmission quality does not reach the quality threshold, the node re-selection process is triggered and the link configuration is reconstructed based on the re-selected nodes, that is, the nodes and links are re-selected to reconstruct a topology structure that meets the quality requirements.

[0084] As Figure 4 shown, in some embodiments, the on-chip optical network system includes a control signaling layer, an optical network layer, and a multi-core processor. Among them, the control signaling layer includes a router and a telecommunication channel, the optical network layer includes an optical router and a transmission waveguide, the 16-core processor is connected in a 4×4 grid network, each node includes an IP core and a router, the horizontal direction is set as the X-axis direction, the vertical direction is set as the Y-axis direction, a two-dimensional coordinate system is established, and the coordinate position of each node in the coordinate system is determined. For example, the coordinate of the bottom-left node is (0, 0), the coordinate of the top-left node is (0, 3), the coordinate of the bottom-right node is (3, 0), and the coordinate of the top-right node is (3, 3).

[0085] As Figure 5As shown in the figure, after the on-chip optical network system receives task data, it parses the task data and evaluates resources to determine the task type, and determines a suitable target topology according to the task type. If the target topology is a ring topology, it further selects the nodes that can form the ring topology according to the resource status of all nodes, such as the nodes with coordinates (0, 0), (0, 1), (0, 2), (0, 3), (1, 3), (2, 3), (3, 3), (3, 2), (3, 1), (3, 0), (2, 0), (1, 0). The status of these nodes is set to active as the valid nodes forming the ring topology, and the status of other nodes is set to inactive. At the same time, the links between the nodes are turned on, thus constructing the target topology.

[0086] S103: Generate a global routing table based on the target topology and the nodes and links forming the target topology;

[0087] S104: Send down the global routing table so that the on-chip optical network forwards task data according to the global routing table.

[0088] In this embodiment, after determining the target topology and selecting the nodes and links forming the target topology, a global routing table is generated based on the selected nodes and links, and the global routing table is sent to each node, so that each node forwards and processes task data according to the global routing table. After the global routing table is sent down, the topology reconstruction process of the on-chip optical network system is completed. In some ways, when distributing the global routing table, an error detection and retransmission mechanism is adopted to ensure that the global routing table is accurately transmitted to each node. The routing information of the global routing table is generated according to a preset routing algorithm based on the selected nodes and links; to reduce the delay caused by routing table updates, an incremental routing update strategy is adopted, and only the changed routing information is updated, improving the update efficiency of the routing table and ensuring the data transmission efficiency and stability after topology switching.

[0089] The dynamic reconfigurable method of the on-chip optical network provided in this embodiment determines the task type by parsing the task data and evaluating resources, selects a suitable target topology, selects nodes and links according to the target topology, activates the nodes and turns on the links, constructs and sends down the global routing table of the selected nodes and links, and the network executes tasks according to the target topology. Reconstructing the topology based on task drive can adapt to diverse task requirements, improve flexibility and adaptability, and fully exert the system performance and potential. By pre-configuring the topology of on-chip links and nodes, it is ensured that the optimal topology can be quickly switched when a burst task arrives, which can improve the overall processing efficiency and task completion degree of the system; in addition, the method of this application is used for network layer resource allocation, and will not bring additional internal interference factors to subsequent optical transmission, and has strong adaptability.

[0090] It should be noted that the method of the embodiment of the present application can be executed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In such a distributed scenario, one of the multiple devices can only execute one or more steps of the method of the embodiment of the present application, and these multiple devices will interact with each other to complete the described method.

[0091] It should be noted that the above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] As Figure 6 shown, the embodiment of the present application provides a dynamically reconfigurable device for an on-chip optical network, including:

[0093] A receiving module, configured to receive task data;

[0094] A selecting module, configured to select a target topology structure based on the task data and determine the nodes and links constituting the target topology structure;

[0095] A generating module, configured to generate a global routing table based on the target topology structure and the nodes and links constituting the target topology structure;

[0096] A sending module, configured to send the global routing table so that the on-chip optical network forwards the task data according to the global routing table.

[0097] For the convenience of description, when describing the above device, it is divided into various modules according to functions and described separately. Of course, when implementing the embodiment of the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0098] The device in the above embodiment is used to implement the corresponding method in the foregoing embodiment and has the beneficial effects of the corresponding method embodiment, which will not be elaborated here.

[0099] Figure 7 Fig. shows a more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. Among them, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other inside the device through the bus 1050.

[0100] The processor 1010 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0101] The memory 1020 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0102] The input / output interface 1030 is used to connect to the input / output module to implement information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. Among them, the input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0103] The communication interface 1040 is used to connect to a communication module (not shown in the figure) to implement communication and interaction between this device and other devices. Among them, the communication module can implement communication through a wired method (such as USB, network cable, etc.) or can also implement communication through a wireless method (such as a mobile network, WIFI, Bluetooth, etc.).

[0104] The bus 1050 includes a path for transmitting information between various components of the device (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0105] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, this device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solution of the embodiments of this specification and does not necessarily include all the components shown in the figure.

[0106] The electronic device of the above embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be elaborated here.

[0107] The computer-readable medium of this embodiment includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information that can be accessed by a computing device.

[0108] Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is only exemplary, and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples; within the concept of the present disclosure, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present application as described above, and they are not provided in detail for the sake of brevity.

[0109] In addition, for the sake of simplicity of description and discussion, and in order not to make the embodiments of the present application difficult to understand, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. In addition, the devices may be shown in block diagram form in order to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present application are to be implemented (i.e., these details should be fully within the understanding of those skilled in the art). In the case where specific details (such as circuits) are set forth to describe the exemplary embodiments of the present disclosure, it will be apparent to those skilled in the art that the embodiments of the present application can be implemented without these specific details or with variations of these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0110] Although the present disclosure has been described in connection with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0111] Embodiments of the present application are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the appended claims. Accordingly, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the embodiments of the present application shall be included within the protection scope of the present disclosure.

Claims

1. A dynamic reconfiguration method for an on-chip optical network, characterized in that, It includes: Receiving task data; Based on the task data, selecting a target topology structure, and determining the nodes and links that make up the target topology structure; Based on the target topology structure and the nodes and links that make up the target topology structure, generating a global routing table; Issuing the global routing table so that the on-chip optical network forwards the task data according to the global routing table.

2. The method according to claim 1, wherein The task data includes task priority, data volume, execution time, and task parameters; Based on the task data, selecting a target topology structure, and determining the nodes and links that make up the target topology structure, including: Determining the task type according to the task priority, data volume, execution time, and task parameters; Selecting a target topology structure corresponding to the task type according to the task type; Obtaining the resource status of all nodes; Based on the target topology structure and the resource status of all nodes, determining the nodes that make up the target topology structure and the links between the nodes.

3. The method according to claim 2, wherein Based on the target topology structure and the resource status of all nodes, determining the nodes that make up the target topology structure and the links between the nodes, including: According to the resource status of all nodes and links, if the nodes that make up the target topology structure cannot be selected, according to the task type, re-selecting other target topology structures corresponding to the task type, and based on the other target topology structures and the resource status of all nodes, determining the nodes that make up the other target topology structure and the links between the nodes.

4. The method according to claim 1, characterized in that After determining the nodes and links that make up the target topology structure, it further includes: Sending an activation signal to the nodes, and sending a non-activation signal to the nodes that do not make up the target topology structure; Sending a conduction signal to the links.

5. The method according to claim 4, wherein After sending a conduction signal to the links and sending a non-conduction signal to the links that do not make up the target topology structure, it further includes: Sending a detection signal to the target topology structure; If the feedback signal of the target topology structure is not received, or if the transmission quality is evaluated to be lower than the preset quality threshold according to the feedback signal, optimizing the link state by adjusting the parameters of the microring resonator.

6. A dynamic reconfigurable device for an on-chip optical network, characterized in that, It includes: A receiving module for receiving task data; A selection module for selecting a target topology structure based on the task data and determining the nodes and links that make up the target topology structure; A generation module for generating a global routing table based on the target topology structure and the nodes and links that make up the target topology structure; A distribution module for distributing the global routing table so that the on-chip optical network forwards the task data according to the global routing table.

7. The device according to claim 6, characterized in that, The task data includes task priority, data volume, execution time, and task parameters; The selection module is used to determine the task type according to the task priority, data volume, execution time, and task parameters; select a target topology structure corresponding to the task type according to the task type; obtain the resource status of all nodes; and determine the nodes that make up the target topology structure and the links between the nodes based on the target topology structure and the resource status of all nodes.

8. The apparatus according to claim 7, wherein The selection module is configured to, according to the resource status of all nodes and links, if nodes that can form the target topology cannot be selected, re-select other target topologies corresponding to the task type according to the task type, and determine the nodes and the links between the nodes that form the other target topologies based on the other target topologies and the resource status of all nodes.

9. The device according to claim 6, characterized in that It further includes: The activation module is configured to send an activation signal to the nodes and an inactivation signal to the nodes that do not form the target topology; and send a conduction signal to the links.

10. The device according to claim 9, characterized in that, It further includes: The detection module is configured to send a detection signal to the target topology; If the feedback signal of the target topology is not received, or if the transmission quality is evaluated to be lower than a preset quality threshold according to the feedback signal, the link state is optimized by adjusting the parameters of the microring resonator.

Images