Temperature calibration method and system for photoelectric hybrid computing system based on table lookup

Abstract

The invention provides a photoelectric hybrid computing system temperature calibration method and system based on table lookup, and the method comprises the steps: setting a plurality of standard inputs, and obtaining a plurality of ideal outputs of a photoelectric hybrid computing system to be calibrated under the plurality of standard inputs; acquiring a plurality of actual outputs corresponding to the plurality of standard inputs on the plurality of temperature points of the photoelectric hybrid computing system to be calibrated according to a set temperature step length; acquiring a compensation relation from actual output compensation to ideal output on each temperature point; constructing a matching table and storing the matching table in the system; when the photoelectric hybrid computing system to be calibrated runs, searching a corresponding compensation relation in the matching table according to the current system temperature; and compensating the system output by using the compensation relationship. The photoelectric hybrid computing system to be calibrated is regarded as a'black box ', and only the final output of the photoelectric hybrid computing system is calibrated at a system level, so that the calibration difficulty is greatly reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of optical chips, and in particular relates to a temperature calibration method and system for an optoelectronic hybrid computing system based on table lookup. Background Art

[0002] In the process of AI calculation, electronic chips play an important role in data transmission and calculation. The whole process of artificial neural algorithm contains a large number of matrix multiplication operations, and the CPU based on traditional computer architecture is very laborious to process these operations, and the calculation efficiency is low. Therefore, academia and industry have turned their attention to new hardware structures specifically used for artificial neural networks and deep learning, such as GPU, ASIC and FPGA. However, no matter what kind of technical architecture, it is designed and manufactured using traditional microelectronics technology. The improvement of AI chip performance is inseparable from the improvement of microelectronics integration. However, at the beginning of the 21st century, it was difficult for microelectronics technology to develop according to the prediction of Moore's Law, and the difficulty of improving chip integration continued to increase.

[0003] Compared with electrons, photons have many unique properties: photons have no rest mass, no interaction between photons, and almost no interference; different wavelengths of light can be used for multi-channel simultaneous communication, and at a modulation frequency of tens of hertz, photons can still obtain stable modulation and information transmission, while electrical signals face the problem of radiation loss at high frequencies; in addition, optical signals are not affected by electromagnetic fields and have strong confidentiality. Even more unique is that by using some specific optical structures, photons can perform some mathematical operations with zero energy consumption. Therefore, the use of photons can achieve ultra-high-speed, low-energy or even zero-energy computing, thereby breaking through the performance and cost bottlenecks of traditional microelectronic chips.

[0004] As the semiconductor industry gradually enters the post-Moore era, the development of integrated circuits continues to evolve in different directions. On the one hand, the development of new semiconductor materials, especially carbon nanotubes and two-dimensional semiconductor materials, continues the essence of Moore's Law and continues to reduce the size of devices or chips, that is, "More Moore"; on the other hand, for specific application fields, the development of new architectures and heterogeneous integrated chips, such as neuromorphic chips, optoelectronic chips, quantum chips, etc., achieves "More than Moore".

[0005] Among them, photonic computing chips based on silicon-based optoelectronic technology use materials and processes compatible with integrated circuits to integrate micron and nanoscale photonics, electronics and optoelectronic devices on the same silicon substrate to achieve functional integration and complementary advantages of microelectronic devices and optoelectronic devices, and obtain optoelectronic chips with superior performance, which is an effective way to solve the performance bottleneck and information congestion faced by traditional integrated circuits. Thanks to the mature application of optical fiber communication, photons, as information carriers, have more multiplexing dimensions than electrons, such as amplitude, phase, wavelength, mode, etc., and thus have larger bandwidth, faster speed and lower energy consumption. Early silicon-based optoelectronic chips were designed to replace copper interconnect technology and solve the bottleneck of interconnection communication between the processor core and memory of microelectronic chips. The microprocessor and storage unit are realized by microelectronic devices, while the photonic devices mainly complete signal transmission and information transmission. With the increasing maturity of silicon photonic technology and the huge advantages of optical communication, people's attention to silicon photonic computing chips has gradually shifted from information transmission to information processing, including analog computing, quantum computing, brain-like computing and other cutting-edge application fields.

[0006] The computing process of the photonic computing chip includes the generation of optical signals, optical conditioning, logical operations of optical signals, and detection and decoding of optical signals. The entire process requires tens of thousands or even hundreds of thousands of optical devices to work together. Some of these optical devices will be affected by temperature, and their characteristics will change accordingly at different temperatures. For example, the output of a directional coupler will drift under different temperature conditions; the photoelectric conversion responsiveness of a photodetector will also change under different temperature conditions. In the actual application environment of a photonic computing chip, its temperature cannot be completely controlled, so that the above changes will affect the accuracy of the final output of the photonic computing chip. Summary of the invention

[0007] The object of the present invention is to provide a method and system for temperature calibration of an optoelectronic hybrid computing system based on table lookup, which partially solves or alleviates the above-mentioned deficiencies in the prior art and can calibrate the temperature drift of the optoelectronic hybrid computing system.

[0008] In order to solve the above-mentioned technical problems, the present invention specifically adopts the following technical solutions: a temperature calibration method of an optoelectronic hybrid computing system based on table lookup, comprising: Setting a number of standard inputs and obtaining a number of ideal outputs of the optoelectronic hybrid computing system to be calibrated under the number of standard inputs; According to the set temperature step, a plurality of actual outputs corresponding to a plurality of standard inputs of the optoelectronic hybrid computing system to be calibrated at a plurality of temperature points are obtained; Obtaining a compensation relationship from actual output compensation to ideal output at each temperature point according to a plurality of actual outputs and a plurality of ideal outputs; A matching table is constructed using the obtained temperature points corresponding to each other of the optoelectronic hybrid computing system to be calibrated and the compensation relationship at the temperature points and stored in the system; When the optoelectronic hybrid computing system to be calibrated is running, according to the current system temperature, a corresponding compensation relationship is searched in the matching table; The compensation relationship is used to compensate the system output.

[0009] As an improvement, the compensation relationship from actual output compensation to ideal output at each temperature point is obtained according to several actual outputs and several ideal outputs, including: Fitting a compensation function from actual output to ideal output at each temperature point according to a plurality of actual outputs and a plurality of ideal outputs; or / and, calculating a compensation coefficient from actual output to ideal output at each temperature point according to a plurality of actual outputs and a plurality of ideal outputs.

[0010] As an improvement, the steps of setting the temperature step include: Calculate the initialization temperature step length according to the operating temperature range of the optoelectronic hybrid computing system to be calibrated and the available storage space; The system temperature is adjusted according to the initialization temperature step, and the actual output of the optoelectronic hybrid computing system to be calibrated under the standard input is obtained at each temperature point; If the absolute value of the difference is less than the difference threshold range, the current step size plus the preset incremental step size will be used as the step size for the next adjustment; if the absolute value of the difference is within the difference threshold range, the step size remains unchanged; if the absolute value of the difference is greater than the difference threshold range, the current step size minus the incremental step size will be used as the step size for the next adjustment.

[0011] As an improvement, the step of calculating the initialization temperature step length according to the operating temperature range of the optoelectronic hybrid computing system to be calibrated and the available storage space includes: The result of dividing the available storage space by the space occupied by the data of a single temperature point is taken as the number of temperature points; The result of dividing the operating temperature range by the number of temperature points is used as the initialization temperature step size.

[0012] As an improvement, the system temperature is adjusted upward from the lower limit of the normal operating temperature range of the optoelectronic hybrid computing system to be calibrated, or the system temperature is adjusted downward from the upper limit of the normal operating temperature range of the optoelectronic hybrid computing system to be calibrated.

[0013] As an improvement, the steps of fitting the compensation function from the actual output compensation to the ideal output at each temperature point include: The fitting takes the actual output at a certain temperature point as the independent variable and the ideal output as the compensation function of the dependent variable; the compensation function of this temperature point is: y=a0c 2 +a1c+a2; Among them, y is the ideal output, c is the actual output, a0, a1, a2 are coefficients; The objective function is: ; in is the i-th ideal output at this temperature point, is the ith actual output at this temperature point, is the weight of the ith one, and n is the number of ideal outputs.

[0014] As an improvement, the steps of solving the coefficients include: Build the model ; The coefficient a is solved by weighted least square method, specifically: a=(C T WC) -1 C T WY g ; Among them, Y g is the ideal input matrix, a is the coefficient, C T is the transpose of the actual output matrix, W is the weight vector matrix, and C is the actual output matrix.

[0015] As an improvement, using formula S n =b(y i / c i ) calculates the compensation coefficient; where S n is the compensation coefficient at temperature point n, y i is the i-th ideal output at this temperature point, c i is the ith actual output at this temperature point, and b is the adjustment coefficient.

[0016] As an improvement, the system output to be calibrated is the output electrical signal of the PD module in the optoelectronic hybrid computing system to be calibrated.

[0017] The present invention also provides a temperature calibration system for an optoelectronic hybrid computing system based on table lookup, comprising: An ideal output acquisition module, used to set a number of standard inputs and obtain a number of ideal outputs of the optoelectronic hybrid computing system to be calibrated under the said number of standard inputs; The actual output acquisition module is used to obtain a number of actual outputs corresponding to a number of standard inputs of the optoelectronic hybrid computing system to be calibrated at a number of temperature points according to a set temperature step; A compensation relationship acquisition module, used for acquiring a compensation relationship from actual output compensation to ideal output at each temperature point according to a plurality of actual outputs and a plurality of ideal outputs; A matching table building module, used to build a matching table using the corresponding temperature points of the optoelectronic hybrid computing system to be calibrated and the compensation relationship at the temperature points and store it in the system; A search module, used to search for a corresponding compensation relationship in a matching table according to a current system temperature when the optoelectronic hybrid computing system to be calibrated is running; The compensation module is used to compensate the system output by using a compensation relationship.

[0018] Beneficial effect: The present invention first obtains several ideal outputs under several standard inputs, and then obtains the actual outputs under the standard inputs at several temperature points within the system operating temperature range according to the set temperature step. Then, the compensation relationship from the actual output to the ideal output is obtained based on the actual output and the ideal output, and a matching table is constructed. As a result, when the system is running after leaving the factory, once temperature drift occurs, the current temperature and the compensation relationship matching the current temperature can be found in the matching table, so as to perform temperature compensation on the system output.

[0019] In the present invention, the optoelectronic hybrid computing system to be calibrated is regarded as a "black box", and the specific optical components inside it will drift due to temperature and the amount of drift are not analyzed. Instead, the entire system is regarded as a whole, and only the final output is calibrated at a system level, which greatly reduces the difficulty of calibration.

[0020] The present invention provides two methods for obtaining compensation relationships. The first method is to obtain a compensation function, which has a relatively complex calculation process but high precision and is used in scenarios where the system precision requirements are high; the second method is to obtain a compensation coefficient, which has a relatively simple calculation process but correspondingly low precision and is used in scenarios where the system precision requirements are general. Both the compensation function and the compensation coefficient can compensate the actual output to the ideal output. There is no difference between the two, but there are differences in the usage scenarios, thereby providing users with more choices. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale. Obviously, the drawings described below are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without paying creative labor.

[0022] Figure 1 This is a flow chart of Embodiment 1 of the present invention; Figure 2 This is a structural diagram of the second embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0024] Herein, suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present invention, and have no specific meanings by themselves. Therefore, "module", "component" or "unit" can be used mixedly.

[0025] In this document, the terms "upper", "lower", "inner", "outer", "front", "back", "one end", "the other end" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0026] In this document, unless otherwise clearly specified and limited, the terms "installed", "provided with", "connected", etc. should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0027] Herein "and / or" includes any and all combinations of one or more of the associated listed items.

[0028] Herein, "plurality" means two or more than two, ie, it includes two, three, four, five, etc.

[0029] Embodiment 1: Prior art Chinese patent application CN202411380839.2 discloses a performance testing and calibration method for a photonic interconnect chip based on a deep machine learning algorithm, including calibrating the output of a light source, calculating the root mean square error of the light source power over time; considering the connection loss and alignment loss between the optical fiber and the chip, calculating the insertion loss and return loss; using a photonic chip deep learning analysis algorithm to analyze the chip's spectral response and phase response, and calculating the spectral response width; measuring the output signal of the photonic interconnect chip to generate an eye diagram, and calculating the signal-to-noise ratio and bit error rate; placing the photonic interconnect chip in an environment with adjustable temperature, introducing the influence of material thermal expansion to calculate the temperature coefficient, and establishing an optical output power model.

[0030] In the above-mentioned prior art, the photonic interconnect chip is placed in an environment with adjustable temperature, temperature data is collected in real time, the influence factor of material thermal expansion is introduced to calculate the temperature coefficient, and an optical output power model of output power, temperature change and wavelength change is established to analyze the optical output power change of the chip under different temperature conditions. It can be seen that the above-mentioned prior art only analyzes the impact of temperature on the output of the photonic computing chip, but does not calibrate the impact. In addition, the impact of ambient temperature on the system is different from the impact of the system (actual working) temperature generated by the operation of each component when the system is running.

[0031] In view of this, if Figure 1 As shown, the present invention provides a temperature calibration method for an optoelectronic hybrid computing system based on table lookup, comprising: S1 sets a number of standard inputs and obtains a number of ideal outputs of the optoelectronic hybrid computing system to be calibrated under the number of standard inputs.

[0032] For an optoelectronic computing system, the light source module that emits optical signals, the conditioner used to condition the optical signals, the computing module used to perform logical operations, the optoelectronic converter used to convert optical signals into electrical signals, etc., will all drift due to the influence of temperature, and the drift ratio of each component at each temperature is not the same. Therefore, it is extremely difficult to calibrate the temperature drift of each component. Moreover, even if each component is calibrated, the final output of the system (or the output of a node in the system, such as the output of the PD) is not necessarily the ideal output, or close to the ideal output.

[0033] In the present invention, on the contrary, the optoelectronic hybrid computing system to be calibrated is regarded as a "black box", and the specific optical components inside it are not analyzed to see which drifts will occur due to temperature and the amount of drift. Instead, the entire system is regarded as a whole, and only the final output is calibrated at a system level, which greatly reduces the difficulty of calibration.

[0034] The purpose of this step is to obtain the expected standard output of the optoelectronic hybrid computing system to be calibrated under different inputs, that is, under ideal conditions, without considering the influence of temperature, the ideal output value of the system under a certain standard output, and use the ideal output as the basis for calibration. For example, it can be obtained through a simulation system.

[0035] For the accuracy of the final calibration, this step does not necessarily provide only one standard output and a corresponding ideal output, but may also provide a set of different standard inputs and a set of corresponding ideal outputs.

[0036] S2 obtains a plurality of actual outputs corresponding to a plurality of standard inputs of the optoelectronic hybrid computing system to be calibrated at a plurality of temperature points according to the set temperature step.

[0037] Since the proportions of temperature effects on optical devices are not the same, for example, the change of a 10° increase is not necessarily twice that of a 5° increase.

[0038] Therefore, in this step, it is necessary to exhaustively enumerate the possible temperatures. It is understandable that the smaller the temperature step, the more temperature points are output, and the higher the accuracy of the final calibration. However, at the same time, more temperature points will increase the amount of calculation and cause greater system overhead.

[0039] Therefore, it is necessary to set a suitable temperature step length so that the difference between adjacent temperature points is within the system tolerance range and the number of temperature points should be reduced as much as possible. The steps for setting the temperature step length in this step include: S21 calculates an initialization temperature step length according to the operating temperature range of the optoelectronic hybrid computing system to be calibrated and the available storage space.

[0040] The optoelectronic hybrid computing system has a specified operating temperature range, such as [-5°C, 45°C], and each optoelectronic hybrid computing system to be calibrated also has a rated storage space, so the space that can be allocated for data storage is also limited. Therefore, when setting the initialization step length, the above two restrictions need to be fully considered. In this embodiment, the steps of calculating the initialization temperature step length according to the operating temperature range of the optoelectronic hybrid computing system to be calibrated and the available storage space include: S211 divides the available storage space by the space occupied by the data of a single temperature point as the number of temperature points.

[0041] First, the available storage space and the space occupied by each temperature point data can be estimated. For example, the space pre-allocated in the entire system for storing the temperature point data in the present invention is 10KB (of course, a portion of the margin will be reserved for storing other data). According to the estimate, the space occupied by each temperature point data is approximately 0.5KB, so it can be roughly estimated that all the data storage space used to store temperature data points can store data of approximately 20 temperature points.

[0042] S212 uses the result of dividing the operating temperature range by the number of temperature points as the initialization temperature step.

[0043] Theoretically, if 20 temperature points are to be distributed in a temperature range of 50°C, the temperature step should be 2.5°C. Therefore, 2.5°C can be used as the initial step size, and then the temperature step size can be further adjusted later.

[0044] S22 adjusts the system temperature according to the initialization temperature step, and obtains the actual output of the optoelectronic hybrid computing system under the standard input at each temperature point.

[0045] In this embodiment, the system operating temperature range can be adjusted downward from the upper limit, or upward from the lower limit. Continuing with the above example, the specified system operating temperature range is [-5°C, 45°C], and the initialization step is 2.5°C. If the adjustment starts from the lower limit, the output value at the input value of the range lower limit -5°C is first recorded, and then the output value at -2.5°C is recorded.

[0046] S23 compares the actual outputs of the optoelectronic hybrid computing system to be calibrated at adjacent temperature points of the system; if the absolute value of the difference is less than the difference threshold range, the current step size plus the preset incremental step size is used as the step size for the next adjustment; if the absolute value of the difference is within the difference threshold range, the step size remains unchanged; if the absolute value of the difference is greater than the difference threshold range, the current step size minus the incremental step size is used as the step size for the next adjustment.

[0047] In this embodiment, the step size is not fixed, but will be adaptively adjusted. Comparing the actual outputs at two adjacent temperature points under the same standard input, if the absolute value of the difference between the two is less than the difference threshold range, it is considered that the difference between the actual outputs at the two temperature points is not within the tolerance range of the system and is too dense. In this embodiment, incremental compensation is preset. In the above case, the current compensation step size plus the incremental step size is used as the step size of the next step.

[0048] If the absolute value of the difference between the two is within the difference threshold range, it is considered that the difference between the actual outputs at the two temperature points is tolerable by the system. During calibration, even if there is no temperature point of -2.5°C, the output of -5°C is within the allowable deviation range of the system. In the above case, the current step size remains unchanged.

[0049] Of course, if the absolute value of the difference between the two exceeds the difference threshold range, it is considered that the two are irreplaceable and interpolation is required. Therefore, the step size should be shortened to obtain a more densely distributed output value. In the above case, the current complement step size minus the incremental step size is used as the step size of the next step.

[0050] In addition, the incremental step size itself is not fixed. In order to reach the difference threshold range as quickly as possible, the next incremental step size can be set to 1 / 2 of the previous incremental step size.

[0051] The above rules are repeated until the entire operating temperature range of the system is traversed.

[0052] S3 obtains a compensation relationship from actual output compensation to ideal output at each temperature point according to a plurality of actual outputs and a plurality of ideal outputs.

[0053] Through step S2, several ideal outputs and actual outputs under several standard inputs at each temperature point within the system working range can be obtained. Through this data, the compensation relationship from actual output to ideal output at each temperature point can also be determined.

[0054] Specifically, a compensation function for compensating from actual output to ideal output at each temperature point is fitted according to several actual outputs and several ideal outputs; or / and, a compensation coefficient for compensating from actual output to ideal output at each temperature point is calculated according to several actual outputs and several ideal outputs.

[0055] That is to say, this step provides two methods for obtaining the compensation relationship. The first is to obtain the compensation function, which has a relatively complex calculation process but high precision and is used in scenarios with high system precision requirements. The second is to obtain the compensation coefficient, which has a relatively simple calculation process but correspondingly low precision and is used in scenarios with general system precision requirements.

[0056] More specifically, the steps of fitting the compensation function from the actual output compensation to the ideal output at each temperature point include: The fitting takes the actual output at a certain temperature point as the independent variable and the ideal output as the compensation function of the dependent variable; the compensation function at this temperature point is: y=a0c 2 +a1c+a2; Among them, y is the ideal output, c is the actual output, a0, a1, a2 are coefficients; The objective function is: ; in is the i-th ideal output at this temperature point, is the ith actual output at this temperature point, is the weight of the ith one, and n is the number of ideal outputs or ideal inputs.

[0057] The steps of solving the coefficients include: Build the model ; The coefficient a is solved by weighted least square method, specifically: a=(C T WC) -1 C T WY g ; Among them, Y g is the ideal input matrix, a is the coefficient, C T is the transpose of the actual output matrix, W is the weight vector matrix, and C is the actual output matrix.

[0058] The steps of calculating the compensation coefficient from the actual output to the ideal output at each temperature point according to the actual outputs and the ideal outputs include: Using formula S n =b(y i / c i ) calculates the compensation coefficient; where S n is the compensation coefficient at temperature point n, y i is the i-th ideal output at this temperature point, c i is the ith actual output at this temperature point, and b is the adjustment coefficient.

[0059] Both the compensation function and the compensation coefficient can compensate the actual output to the ideal output. There is no difference between the two, but there are differences in usage scenarios.

[0060] S4 constructs a matching table using the acquired temperature points corresponding to each other of the optoelectronic hybrid computing system to be calibrated and the compensation relationship at the temperature points and stores the table in the system.

[0061] After traversing all the temperature points within the entire system operating temperature range, the temperature points and the compensation relationships at the temperature points are compiled into a table. It is foreseeable that the elements in the matching table include temperature points and corresponding compensation relationships (including compensation functions or compensation coefficients), for example, temperature: 30°C; compensation relationship: y=a0c 2 +a1c+a2.

[0062] S5 searches for a corresponding compensation relationship in a matching table according to the current system temperature when the optoelectronic hybrid computing system to be calibrated is running.

[0063] When the system is running, once it is detected that the system has migrated due to the influence of temperature, the compensation coefficient or compensation function from the actual output to the ideal output at the current temperature can be queried according to the matching table constructed in the previous step.

[0064] S6 uses the compensation relationship to compensate the system output.

[0065] After obtaining the compensation relationship, when the compensation relationship is a compensation function, the actual output is substituted into the compensation function as the independent variable, and its dependent variable is the ideal output at that temperature point, thereby compensating the system output to the ideal output. When the compensation relationship is a compensation coefficient, the ideal output can be obtained by adjusting the actual output using the compensation coefficient.

[0066] In this embodiment, the output of the system to be calibrated is the output electrical signal of the PD (Photodiode photoelectric conversion) module in the optoelectronic hybrid computing system to be calibrated. The reason is that the PD module is the last optical device in the entire photonic computing chip, and its function is to convert the optical signal into an electrical signal. The error of the optical signal in the entire system caused by temperature will eventually accumulate in the PD module, and the PD module itself is also affected by temperature and has a large drift. Therefore, in this embodiment, the output of the PD module is used as the object of calibration.

[0067] In other embodiments, the storage space and the system operating temperature range are considered when setting the step size, and the step size is not a fixed value, but is adaptively adjusted using a preset incremental step size; on the other hand, since the calibration is not performed on a single component within the system, but the entire system is treated as a "black box" for system-level calibration, any failure in any component within the system or in the link between the components may affect the adjustment of the step size. Therefore, in order to ensure the accuracy and reliability of the calibration, the calibrated temperature value needs to be verified. Specifically, at the specified multiple test temperatures T k (k is the serial number of the test temperature), M standard inputs P1-P are given for each temperature N , so as to obtain the actual output I of the system at each test temperature k1 '—I kM ', and the ideal output I after calibration by the calibration model k1 ''—I kM '', and then compare the calibrated ideal output I k1 ''—I kM The variance of '' is the ideal output I corresponding to the corresponding standard input obtained in step S1 11 —I 1MIf the average relative error between the data sets is less than the preset error threshold, it means that the ideal output data set after calibration is not much different from the ideal output data set in step S1 as a whole, or the ideal data set after calibration is closer to the ideal output data set in step S1 as a whole. Therefore, it is determined that the verification is passed, and the temperature step set in step S2 is not only reasonable but also meets the accuracy requirements; on the contrary, if the average relative error is greater than or equal to the preset error threshold, it is determined that the verification is not passed, and accordingly, the incremental step in step S23 needs to be adjusted. For example, the incremental step is reduced.

[0068] Embodiment 2: Figure 2 As shown, the present invention also provides a temperature calibration system for an optoelectronic hybrid computing system based on table lookup, comprising: An ideal output acquisition module, used to set a number of standard inputs and obtain a number of ideal outputs of the optoelectronic hybrid computing system to be calibrated under the said number of standard inputs; The actual output acquisition module is used to obtain a number of actual outputs corresponding to a number of standard inputs of the optoelectronic hybrid computing system to be calibrated at a number of temperature points according to a set temperature step; A compensation relationship acquisition module, used for acquiring a compensation relationship from actual output compensation to ideal output at each temperature point according to a plurality of actual outputs and a plurality of ideal outputs; A matching table building module, used to build a matching table using the corresponding temperature points of the optoelectronic hybrid computing system to be calibrated and the compensation relationship at the temperature points and store it in the system; A search module, used to search for a corresponding compensation relationship in a matching table according to a current system temperature when the optoelectronic hybrid computing system to be calibrated is running; The compensation module is used to compensate the system output by using a compensation relationship.

[0069] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0070] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a computer terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0071] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A temperature calibration method for an optoelectronic hybrid computing system based on table lookup, characterized in that include: Setting a number of standard inputs and obtaining a number of ideal outputs of the optoelectronic hybrid computing system to be calibrated under the number of standard inputs; According to the set temperature step, a plurality of actual outputs corresponding to a plurality of standard inputs of the optoelectronic hybrid computing system to be calibrated at a plurality of temperature points are obtained; Obtaining a compensation relationship from actual output compensation to ideal output at each temperature point according to a plurality of actual outputs and a plurality of ideal outputs; A matching table is constructed using the obtained temperature points corresponding to each other of the optoelectronic hybrid computing system to be calibrated and the compensation relationship at the temperature points and stored in the system; When the optoelectronic hybrid computing system to be calibrated is running, according to the current system temperature, a corresponding compensation relationship is searched in the matching table; The compensation relationship is used to compensate the system output.

2. The method for temperature calibration of an optoelectronic hybrid computing system based on table lookup according to claim 1, characterized in that The compensation relationship from actual output compensation to ideal output at each temperature point is obtained based on several actual outputs and several ideal outputs, including: Fitting a compensation function from actual output to ideal output at each temperature point according to a plurality of actual outputs and a plurality of ideal outputs; or / and, calculating a compensation coefficient from actual output to ideal output at each temperature point according to a plurality of actual outputs and a plurality of ideal outputs.

3. The method for temperature calibration of an optoelectronic hybrid computing system based on table lookup according to claim 1, characterized in that The steps to set the temperature step size include: Calculate the initialization temperature step length according to the operating temperature range of the optoelectronic hybrid computing system to be calibrated and the available storage space; The system temperature is adjusted according to the initialization temperature step, and the actual output of the optoelectronic hybrid computing system to be calibrated under the standard input is obtained at each temperature point; Compare the actual outputs of the optoelectronic hybrid computing system to be calibrated at adjacent temperature points of the system; if the absolute value of the difference is less than the difference threshold range, add the current step size to the preset incremental step size as the step size for the next adjustment; if the absolute value of the difference is within the difference threshold range, the step size remains unchanged; if the absolute value of the difference is greater than the difference threshold range, subtract the incremental step size from the current step size as the step size for the next adjustment.

4. The method for temperature calibration of an optoelectronic hybrid computing system based on table lookup according to claim 3, characterized in that The steps of calculating the initialization temperature step length according to the operating temperature range of the optoelectronic hybrid computing system to be calibrated and the available storage space include: The result of dividing the available storage space by the space occupied by the data of a single temperature point is taken as the number of temperature points; The result of dividing the operating temperature range by the number of temperature points is used as the initialization temperature step size.

5. The method for temperature calibration of an optoelectronic hybrid computing system based on table lookup according to claim 3, characterized in that: The system temperature is adjusted upward from the lower limit of the normal operating temperature range of the optoelectronic hybrid computing system to be calibrated, or the system temperature is adjusted downward from the upper limit of the normal operating temperature range of the optoelectronic hybrid computing system to be calibrated.

6. The method for temperature calibration of an optoelectronic hybrid computing system based on table lookup according to claim 1, characterized in that The steps to fit the compensation function from actual output compensation to ideal output at each temperature point include: The fitting takes the actual output at a certain temperature point as the independent variable and the ideal output as the compensation function of the dependent variable; the compensation function of this temperature point is: y=a0c 2 +a1c+a2; Among them, y is the ideal output, c is the actual output, a0, a1, a2 are coefficients; The objective function is: ; in is the i-th ideal output at this temperature point, is the ith actual output at this temperature point, is the weight of the ith one, and n is the number of ideal outputs.

7. The method for temperature calibration of an optoelectronic hybrid computing system based on table lookup according to claim 6, characterized in that The steps of solving the coefficients include: Build the model ; The coefficient a is solved by weighted least square method, specifically: a=(C T WC) -1 C T WY g ; Among them, Y g is the ideal input matrix, a is the coefficient, C T is the transpose of the actual output matrix, W is the weight vector matrix, and C is the actual output matrix.

8. The method for temperature calibration of an optoelectronic hybrid computing system based on table lookup according to claim 1, characterized in that: Using formula S n =b(y i / c i ) calculates the compensation coefficient; where S n is the compensation coefficient at temperature point n, y i is the i-th ideal output at this temperature point, c i is the ith actual output at this temperature point, and b is the adjustment coefficient.

9. The method for temperature calibration of an optoelectronic hybrid computing system based on table lookup according to claim 1, characterized in that: The system output to be calibrated is the output electrical signal of the PD module in the optoelectronic hybrid computing system to be calibrated.

10. The temperature calibration system of the optoelectronic hybrid computing system based on table lookup according to claim 1, characterized in that include: An ideal output acquisition module, used to set a number of standard inputs and obtain a number of ideal outputs of the optoelectronic hybrid computing system to be calibrated under the said number of standard inputs; The actual output acquisition module is used to obtain a number of actual outputs corresponding to a number of standard inputs of the optoelectronic hybrid computing system to be calibrated at a number of temperature points according to a set temperature step; A compensation relationship acquisition module, used for acquiring a compensation relationship from actual output compensation to ideal output at each temperature point according to a plurality of actual outputs and a plurality of ideal outputs; A matching table building module, used to build a matching table using the corresponding temperature points of the optoelectronic hybrid computing system to be calibrated and the compensation relationship at the temperature points and store it in the system; A search module, used to search for a corresponding compensation relationship in a matching table according to a current system temperature when the optoelectronic hybrid computing system to be calibrated is running; The compensation module is used to compensate the system output by using a compensation relationship.

Images