Data processing system and method

Through the data packet and multi-processor parallel operation of the digital signal processing system, the problem of low mode computing performance and high resource consumption in the cryptographic analysis equipment is solved, and efficient data processing and flexible mode computing are realized, which is suitable for multiple type of data.

CN118713814BActive Publication Date: 2024-11-12OPEN SECURITY RES INC
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411186640.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-11-12
Estimated Expiration
2044-08-28

AI Technical Summary

Technical Problem

In existing password analysis equipment, the LUT module has low performance when used for mode computing, and requires a large amount of hardware resources when processing large data volumes, resulting in large hardware area occupancy, high resource consumption, and difficulty in adapting to multiple mode computing types.

Method used

The digital signal processing system is adopted to receive data processing requests through the controller, determine data processing parameters, including data packet ratio and data flow information, perform packaged packet processing, and use multiple digital signal processors to perform mode calculation processing to reduce the hardware area. Improve processing efficiency.

Benefits of technology

It improves data processing performance, reduces hardware area and resource consumption, enhances the flexibility and scope of application of the data processing system, can process higher frequency data, and improves processing accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118713814B_ABST
    Figure CN118713814B_ABST
Patent Text Reader

Abstract

The embodiment of the present application provides a data processing system and method, which relates to the field of data processing technology. The system is applied to a cryptographic analysis device, and includes: a controller, a data processing module, and a digital signal processing array; wherein the data processing module is used for packing and grouping processing; the digital signal processing array includes at least one digital signal processor; the digital signal processor is used for pattern operation processing. The system is used to achieve the effect of reducing the hardware area of ​​the data processing system while maintaining data processing performance.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data processing system and method. Background Art

[0002] In cryptanalysis equipment, efficient pattern operations can be used to assist cryptanalysis. With the increasing real-time requirements for pattern operation processing and the increasing data rate of data for pattern operation, how to efficiently implement pattern operations on data has become a technical problem that needs to be solved urgently.

[0003] In the existing system architecture, the LUT module in the FPGA is usually used to implement pattern operations, thereby improving the versatility of the system that performs pattern operations. However, the LUT module has limited data processing capabilities, resulting in low performance when implementing pattern operations through the LUT module. At the same time, when the data that needs to be operated on is large and the data volume is large, more LUT modules are required, which in turn requires a larger hardware area and consumes more resources. Summary of the invention

[0004] The embodiments of the present application provide a data processing system and method for achieving the effect of reducing the hardware area of ​​the data processing system while maintaining data processing performance.

[0005] In a first aspect, an embodiment of the present application provides a data processing system, which is applied to a cryptographic analysis device, and the system includes: a controller, a data processing module, and a digital signal processing array; wherein the data processing module is used for performing packaging and grouping processing; the digital signal processing array includes at least one digital signal processor; the digital signal processor is used for performing pattern operation processing;

[0006] The controller is used to determine data processing parameters matching the data processing request after receiving the data processing request; wherein the data processing request is used to request pattern operation processing of data; the data processing parameters include data grouping ratio, data flow information and data acquisition quantity; the data grouping ratio and data acquisition quantity included in the data processing parameters are sent to the data processing module, and the data flow information is sent to the digital signal processing array;

[0007] The data processing module is used to obtain a plurality of first processed data matching the data acquisition quantity; and after receiving the data grouping ratio, according to the data grouping ratio, the plurality of first processed data are packaged and grouped to obtain a plurality of groups of second processed data; and each group of the second processed data is sent to each of the digital signal processors included in the digital signal processing array;

[0008] The digital signal processing array is used to obtain the operation reference data corresponding to each group of the second processed data, and according to the received data flow information, input the second processed data received by each digital signal processor and the operation reference data corresponding to each group of the second processed data into the corresponding digital signal processor for pattern operation processing to obtain a pattern operation result.

[0009] In a possible implementation manner, the data processing parameter includes the data grouping ratio; the data processing request includes identification information indicating a digital signal processor for performing data processing; after receiving the data processing request, determining the data processing parameter matching the data processing request includes:

[0010] Determine a first data bit width of data processed by a digital signal processor matching the identification information; and determine a second data bit width corresponding to the first processed data;

[0011] The data grouping ratio is determined based on a ratio of the first data bit width to the second data bit width.

[0012] In a possible implementation, the data processing parameters include the data flow direction information; the data processing request includes a data processing method; the data processing method indicates a mode operation type; after receiving the data processing request, determining the data processing parameters matching the data processing request includes:

[0013] Determining a data processing path based on the mode operation type indicated by the data processing method;

[0014] Based on the data processing path, the data flow information is determined.

[0015] In a possible implementation manner, the data processing parameters further include a data quantization ratio; the data quantization ratio indicates a ratio of quantization processing performed on the first processed data; after receiving the data processing request, determining the data processing parameters matching the data processing request includes:

[0016] Determining a data processing scenario that matches the data processing request;

[0017] The data quantization ratio is determined based on the processing accuracy requirement corresponding to the data processing scenario.

[0018] In a possible implementation manner, the controller is further configured to:

[0019] Sending the data quantization ratio to the data processing module;

[0020] The data processing module is also used for:

[0021] The data quantization ratio is received, and after obtaining the first processed data, the first processed data is quantized according to the data quantization ratio to obtain the quantized first processed data.

[0022] In one possible implementation, the pattern operation processing includes multiple levels of operations; the data flow information includes intra-layer feedback flow; wherein the intra-layer feedback flow indicates that the output result of the previous level of operation is transmitted again to the digital signal processor as input data for the next level of operation.

[0023] In a possible implementation, according to the received data flow direction information, the second processed data received by each digital signal processor and the operation reference data corresponding to each group of the second processed data are input into the corresponding digital signal processor for pattern operation processing to obtain a pattern operation result, including:

[0024] determining input data for a primary operation based on the second processed data and the operation reference data;

[0025] Inputting the input data of the primary operation into the digital signal processor for primary operation processing to obtain a primary operation result;

[0026] Determine the input data of the first-level operation as the input data of the previous-level operation; and determine the result of the first-level operation as the result of the previous-level operation;

[0027] Repeat the following steps for each group of the second processed data and the operation reference data corresponding to each group of the second processed data until the operation result of the last level of operation is determined to obtain the pattern operation result: determine the input data of the next level of operation according to the operation result of the previous level, and input the input data of the next level of operation into the digital signal processor for the next level of operation according to the feedback flow direction within the layer included in the received data flow direction information, so as to obtain the operation result of the next level of operation.

[0028] In one possible implementation, the digital signal processing array includes a plurality of digital signal processing layers, each of which is used to implement a first-level operation; the data flow information includes an inter-layer cascade flow direction; wherein the inter-layer cascade flow direction indicates that an output result of a previous data processing signal layer is input into a next data processing signal layer.

[0029] In a possible implementation, according to the received data flow direction information, the second processed data received by each digital signal processor and the operation reference data corresponding to each group of the second processed data are input into the corresponding digital signal processor for pattern operation processing to obtain a pattern operation result, including:

[0030] determining input data for a primary operation based on the second processed data and the operation reference data;

[0031] Inputting the input data of the primary operation into the digital signal processor of the first digital signal processing layer to perform the primary operation and obtain the primary operation result;

[0032] Determine the input data of the first-level operation as the input data of the previous-level operation; and determine the result of the first-level operation as the result of the previous-level operation;

[0033] Repeat the following steps for each group of the second processed data and the operation reference data corresponding to each group of the second processed data until the operation result of the last level of operation is determined to obtain the pattern operation result: determine the input data of the next level of operation according to the operation result of the previous level, and input the input data of the next level of operation into the digital signal processor of the next digital signal processing layer for the next level of operation according to the inter-layer cascade flow direction included in the received data flow direction information, so as to obtain the operation result of the next level of operation.

[0034] In a possible implementation, after receiving the data processing request, determining data processing parameters matching the data processing request includes:

[0035] Determining a data processing scenario that matches the data processing request;

[0036] Based on the matched data processing scenario, determining preset parameters corresponding to the matched data processing scenario from a preset relationship mapping table; wherein the preset relationship mapping table includes an association relationship between the data processing scenario and the data processing parameters;

[0037] The preset parameters are determined as data processing parameters that match the data processing request.

[0038] In a second aspect, an embodiment of the present application provides a data processing method, which is applied to a data processing system; the system includes: a controller, a data processing module and a digital signal processing array; the method includes:

[0039] Receiving a data processing request; wherein the data processing request is used to request a pattern operation processing to be performed on the data;

[0040] After receiving the data processing request, determining data processing parameters matching the data processing request; wherein the data processing parameters include data grouping ratio, data flow information and data acquisition quantity;

[0041] Acquire a plurality of first processed data matching the data acquisition quantity, and perform packaging and grouping processing on the plurality of first processed data according to the data grouping ratio to obtain a plurality of groups of second processed data;

[0042] Obtain operation reference data corresponding to each group of the second processed data; and perform pattern operation processing on each group of the second processed data and the operation reference data corresponding to each group of the second processed data according to the data flow information to obtain a pattern operation result.

[0043] In a possible implementation manner, the data processing parameters further include a data quantization ratio; and the method further includes:

[0044] After acquiring a plurality of first processed data matching the data acquisition quantity, each of the first processed data is quantized according to the data quantization ratio to obtain quantized first processed data.

[0045] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0046] The memory stores computer-executable instructions;

[0047] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above second aspect and / or various possible implementations of the second aspect.

[0048] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the above second aspect and / or various possible implementations of the second aspect.

[0049] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above second aspect and / or various possible implementations of the second aspect.

[0050] The data processing system and method provided in the embodiment of the present application can determine the data processing parameters matching the data processing request after receiving the data processing request through the controller. At this time, the data processing parameters include but are not limited to: data grouping ratio, data flow information and data acquisition quantity. At this time, multiple first processing data can be obtained according to the data processing parameters, and the obtained multiple first processing data are packaged and grouped to obtain multiple groups of second processing data. At this time, the simultaneous processing of multiple first processing data can be achieved by processing the second processing data, thereby improving the processing efficiency. Afterwards, the operation reference data corresponding to each group of second processing data can be obtained, and the operation reference data corresponding to each group of second processing data and each group of second processing data can be input into the corresponding digital signal processor for pattern operation processing to obtain the pattern operation result. At this time, the pattern operation processing can be performed simultaneously by multiple digital signal processors, so that the data processing system can simultaneously observe / process a larger range of data, thereby improving the bandwidth and processing efficiency of the data processed by the data processing system. At this time, while improving the processing efficiency of the data processing system, it is equivalent to improving the frequency of the data processing system processing data, so that higher frequency data can be processed, and the accuracy of data processing is improved. At the same time, the mode operation method using a digital signal processor greatly reduces the hardware area and resource consumption compared to the mode operation method based on LUT, achieving the effect of reducing the hardware area while maintaining data processing performance. In addition, the mode operation processing method using a digital signal processor can achieve different mode operation types by designing data flow information without adding additional hardware equipment, making the data processing system more flexible and applicable to a wider range of applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0052] Figure 1 A schematic diagram of performing a mode operation on collected real-time signal data provided by an embodiment of the present application;

[0053] Figure 2 A schematic diagram of analysis and processing in a side channel analysis scenario provided in an embodiment of the present application;

[0054] Figure 3 A schematic diagram of analysis and processing in a fault injection scenario provided in an embodiment of the present application;

[0055] Figure 4 A schematic diagram of the structure of a LUT module provided in an embodiment of the present application;

[0056] Figure 5A schematic diagram of the structure of an adder provided in an embodiment of the present application;

[0057] Figure 6 A schematic diagram of the architecture of a data processing system provided in an embodiment of the present application;

[0058] Figure 7 A schematic diagram of data flow information when a single-layer digital signal processing layer performs pattern operation processing provided by an embodiment of the present application;

[0059] Figure 8 A schematic diagram of the architecture of another digital processing system provided in an embodiment of the present application;

[0060] Fig. 9 A schematic diagram of data flow information when pattern operation processing is performed through multiple digital signal processing layers provided in an embodiment of the present application;

[0061] Fig.10 A flowchart of a data processing method provided in an embodiment of the present application;

[0062] Fig.11 A flowchart of another data processing method provided in an embodiment of the present application;

[0063] Fig.12 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0064] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0065] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of systems and devices consistent with some aspects of the present application as detailed in the appended claims.

[0066] First, some terms involved in this application are explained.

[0067] Pattern operation: One of the input data is a type of operation used for reference. For example, the pattern operation type corresponding to the pattern operation may be the sum of absolute differences, mean square error, Pearson correlation coefficient, etc.

[0068] LUT: The full name is Look-Up-Table, which is essentially a RAM that can write data into the RAM in advance. At this time, each time a signal data is input, it is equivalent to inputting an address to look up the table, and after finding the content corresponding to the address, it is output, thereby obtaining the calculation result corresponding to the input signal data.

[0069] SIMD: The full name is Single Instruction Multiple Data, which is a technology for achieving data-level parallelism. It can perform the same operation on each group of data corresponding to multiple data streams.

[0070] FPGA: The full name is Field Programmable Gate Array, field programmable logic gate array.

[0071] DSP: Digital Signal Processor, a digital signal processor, is a microprocessor specifically used to implement signal processing algorithms, with calculation functions such as multiplication and addition.

[0072] The cryptographic analysis device involved in the embodiments of the present application may indicate tools and instruments for analyzing and cracking cryptographic systems. At this time, various cryptographic analysis techniques (e.g., side channel analysis, fault injection, etc.) may be performed in the cryptographic analysis device to discover weaknesses in the cryptographic system, thereby improving the security of the cryptographic system.

[0073] When executing various cryptanalysis techniques in a cryptanalysis device, cryptanalysis can be performed by collecting real-time signal data when the cryptanalysis device performs encryption operations, as well as corresponding reference signal data, and matching the real-time signal data and the reference signal data (that is, performing pattern operation processing).

[0074] For an example, see Figure 1 , Figure 1 A schematic diagram of performing a mode operation on collected real-time signal data provided by an embodiment of the present application. Assume that the collected data is as follows Figure 1 The real-time signal data shown in the figure can be obtained based on the preset sliding window (such as Figure 1 The sliding window shown in the figure is used to obtain the reference signal data within the sliding window range, and according to the reference signal data within the sliding window range, the real-time signal data within the sliding window range is subjected to pattern operation processing to obtain the pattern operation result, so as to obtain the matching degree between the reference signal and the real-time signal data, so as to carry out the next step of analysis and processing when it is determined that the real-time signal data and the reference signal data match.

[0075] Among them, the real-time signal data and the reference signal data can determine the specific signal data type according to the actual application scenario. For example, in the side channel analysis scenario, the real-time signal data can indicate the power consumption information of the cryptographic device when performing encryption operations, and at this time, the reference signal data can indicate the power consumption information of the cryptographic device when performing encryption operations according to the assumed key.

[0076] See also Figure 2 , Figure 2 A schematic diagram of analysis and processing in a side channel analysis scenario provided by an embodiment of the present application. In the side channel analysis scenario, after pattern operation processing is performed on the reference signal data and the real-time signal data and the pattern operation result is obtained, the sliding window with the highest matching degree between the real-time signal data and the reference signal data can be determined according to the pattern operation result. For example, the sliding window with the highest matching degree is Figure 2 The sliding window 1 shown. At this time, the reference signal data corresponding to the sliding window 1 can be analyzed and processed, for example, the assumed key corresponding to the reference signal data in the sliding window 1 can be determined, and the accuracy of the assumed key can be determined, so as to determine whether the encryption device has a key leakage phenomenon.

[0077] For another example, in a fault injection scenario, the real-time signal data may indicate the power consumption signal of the cryptographic device when performing a first operation; the reference signal data may indicate the power consumption information of the cryptographic device when performing a second operation, wherein the second operation may indicate the operation performed by the cryptographic device before performing the first operation.

[0078] It should be noted here that the above-mentioned real-time signal data can be understood as the first processed data (or second processed data) in the embodiment of the present application, and the reference signal data can be understood as the calculation reference data in the embodiment of the present application. The specific meanings of the first processed data (or second processed data) and the calculation reference data will not be described in detail below.

[0079] See also Figure 3 , Figure 3 A schematic diagram of analysis and processing in a fault injection scenario provided by an embodiment of the present application. In a fault injection scenario, after pattern operation processing is performed on reference signal data and real-time signal data to obtain a pattern operation result, a sliding window with the highest matching degree between the real-time signal data and the reference signal data can be determined based on the pattern operation result. For example, the sliding window with the highest matching degree is Figure 3 The sliding window 2 shown. At this time, the fault injection entry point can be determined based on the sliding window 2. For example, the fault can be injected into the encryption device at the end position of the sliding window, and the encryption device after the fault injection is analyzed and processed to determine the security of the encryption device.

[0080] In the existing system architecture, the LUT module in the FPGA is usually used to implement pattern operations, thereby improving the versatility of the system that performs pattern operations. However, the LUT module has limited data processing capabilities, resulting in low performance when implementing pattern operations through the LUT module. At the same time, when the data that needs to be operated on is large and the data volume is large, more LUT modules need to be integrated, which in turn requires a larger hardware area and consumes more resources.

[0081] See also Figure 4 , Figure 4 A schematic diagram of the structure of a LUT module provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the LUT module has a 6-input 2-output structure, which is also represented as LUT6-2. At this time, the LUT6-2 can be implemented by two LUT5, where LUT5 represents a 5-input 1-output structure. At this time, the two LUT5 share the first 5 inputs, for example, Figure 4 The output results of two LUT5s are obtained by using the I0~I4 shown in the figure. At this time, the multiplexer in LUT6-2 can be used to select the output of the 6th input (i.e. Figure 4 As shown in I5), the output result of the first LUT5 or the output result of the second LUT5 is selected to be output, and the output result O6 is obtained. At this time, the output result of the second LUT5 can also be directly output to obtain the output result O5, thereby making LUT6-2 more flexible.

[0082] Based on this, according to Figure 4 When the LUT module shown is used to implement an adder, an auxiliary CARRY module is required. Figure 5 A schematic diagram of the structure of an adder provided in an embodiment of the present application is shown in FIG. Figure 5 As shown, when an 8-bit adder is implemented according to the LUT module and the CARRY carry module, the 8-bit adder can be composed of the eight LUT6-2 and three CARRY carry modules (that is, Figure 5 The carry module shown in the figure is cascaded and composed of 9 flip-flops. This part is the prior art and will not be described in detail here.

[0083] In combination with the above scenario, it can be seen that in the prior art, the LUT module in the FPGA is used to implement pattern operations, which easily occupies a large hardware area. Moreover, if it is to be applicable to pattern operations of various types of pattern operations, then the hardware area needs to be further increased. At the same time, this implementation method requires a large number of logic levels to be deployed when implementing complex pattern operations, which in turn limits the improvement of data processing performance.

[0084] The data processing system provided in the present application reduces the hardware area by using DSP for pattern calculation. At the same time, it utilizes the SIMD capability of DSP to package and combine multiple data for processing, thereby increasing the throughput of data calculation and improving data processing efficiency and performance, thereby solving the above-mentioned technical problems.

[0085] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0086] See also Figure 6 , Figure 6 A schematic diagram of the architecture of a data processing system provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the system can be applied to a cryptographic analysis device, and includes: a controller 601, a data processing module 602 and a digital signal processing array 603.

[0087] The data processing module 602 is used for performing packaging and grouping processing; the digital signal processing array 603 includes at least one digital signal processor 604; and the digital signal processor 604 is used for performing pattern operation processing.

[0088] The controller 601 is used to determine the data processing parameters that match the data processing request after receiving the data processing request; wherein the data processing request is used to request pattern operation processing on the data; the data processing parameters include data grouping ratio, data flow information and data acquisition quantity; the data grouping ratio and data acquisition quantity included in the data processing parameters are sent to the data processing module, and the data flow information is sent to the digital signal processing array.

[0089] Among them, the data processing request may include the data type of the data requested for processing, the data processing time, the data processing scenario, the data processing method, the digital signal processor for data processing, etc. There is no specific limitation on the content included in the data processing request here, which shall be subject to the implementation.

[0090] In one example, the data grouping ratio may indicate the number of data packages. For example, when the data grouping ratio is 4, 4 data may be packaged into one group of data. The data flow direction information may indicate the processing path of the data to be processed by pattern operation in the digital signal processor. At this time, the data may be processed by pattern operation according to the data flow direction information to obtain the pattern operation result.

[0091] In one example, the data acquisition quantity is associated with the data processing capability of the digital signal processing array. For example, if the digital signal processing array can process 8 data at a time, the data acquisition quantity is 8. If the digital signal processing array can process 32 data at a time, the data acquisition quantity is 32, etc. The data processing capability of the digital signal processing array is associated with the number of digital signal processors included in the digital signal processing array. The more digital signal processors included in the digital signal processing array, the stronger the data processing capability of the digital signal processing array.

[0092] The data processing module 602 is used to obtain multiple first processed data matching the data acquisition quantity; and after receiving the data grouping ratio, the multiple first processed data are packaged and grouped according to the data grouping ratio to obtain multiple groups of second processed data; and each group of second processed data is sent to each digital signal processor included in the digital signal processing array.

[0093] like Figure 6 As shown, the data processing module 602 can obtain a plurality of first processed data from a data source. At this time, the data source may include real-time signal data collected from an encryption device.

[0094] In an example, if the data grouping ratio is 4, then 4 first processed data may be packaged and grouped to obtain a group of second processed data. At this time, the group of second processed data includes 4 first processed data.

[0095] In one example, the number of digital signal processors included in the digital signal processing array may be N (eg Figure 6 The digital signal processors 604-1, ..., 604-N shown, where the digital signal processor 604-1 represents the first digital signal processor and the digital signal processor 604-N represents the Nth digital signal processor), where N is an integer greater than or equal to 1, and in this case, the value of N is associated with the number of groups of the second processed data, for example, the value of N is equal to the number of groups of the second processed data.

[0096] The digital signal processing array 603 is used to obtain the operation reference data corresponding to each group of second processed data, and according to the received data flow information, input the second processed data received by each digital signal processor and the operation reference data corresponding to each group of second processed data into the corresponding digital signal processor for pattern operation processing to obtain the pattern operation result.

[0097] like Figure 6As shown, the digital signal processing array 603 can obtain computational reference data from a data source. At this time, the computational reference data may indicate reference signal data directly obtained from the data source, or may indicate data after the reference signal data in the data source is processed by the data processing module 602 (the processing process is the same as the processing process of the first processed data). At this time, the data source may also include pre-stored reference signal data.

[0098] like Figure 6 As shown, after the pattern operation result is obtained, the pattern operation result can be transmitted to the subsequent logic for analysis and processing, for example, side channel analysis or fault injection.

[0099] It can be known from the above description that the embodiment of the present application can determine the data processing parameters matching the data processing request after receiving the data processing request through the controller. At this time, the data processing parameters include but are not limited to: data grouping ratio, data flow information and data acquisition quantity. At this time, multiple first processing data can be obtained according to the data processing parameters, and the obtained multiple first processing data are packaged and grouped to obtain multiple groups of second processing data. At this time, the simultaneous processing of multiple first processing data can be achieved by processing the second processing data, thereby improving the processing efficiency. Afterwards, the operation reference data corresponding to each group of second processing data can be obtained, and the operation reference data corresponding to each group of second processing data and each group of second processing data can be input into the corresponding digital signal processor for pattern operation processing to obtain the pattern operation result. At this time, the pattern operation processing can be performed simultaneously by multiple digital signal processors, so that the data processing system can simultaneously observe / process a larger range of data, thereby improving the bandwidth and processing efficiency of the data processed by the data processing system. At this time, while improving the processing efficiency of the data processing system, it is equivalent to improving the frequency of the data processing system processing data, so that higher frequency data can be processed, and the accuracy of data processing is improved. At the same time, the mode operation method using a digital signal processor greatly reduces the hardware area and resource consumption compared to the mode operation method based on LUT, achieving the effect of reducing the hardware area while maintaining data processing performance. In addition, the mode operation processing method using a digital signal processor can achieve different mode operation types by designing data flow information without adding additional hardware equipment, making the data processing system more flexible and applicable to a wider range of applications.

[0100] In a possible implementation manner, when the data processing parameter includes a data grouping ratio and the data processing request includes identification information indicating a digital signal processor for performing data processing, the above-mentioned: after receiving the data processing request, determining the data processing parameter matching the data processing request specifically includes the following steps:

[0101] Determine the first data bit width of the data processed by the digital signal processor matching the identification information; and determine the second data bit width corresponding to the first processed data; then, determine the data grouping ratio based on the ratio of the first data bit width to the second data bit width.

[0102] In an example, the first data bit width may be 48 bits or 52 bits, etc., and the value of the first data bit width is not limited here, and is subject to practicability.

[0103] The second data bit width may be 8 bits, or 16 bits, etc., and the value of the second data bit width is not limited here, and is subject to the data bit width corresponding to the specific first processed data.

[0104] In one example, an integer value smaller than the ratio of the first data bit width to the second data bit width may be used to determine the data grouping ratio. For example, when the ratio of the first data bit width to the second data bit width is 6, the data grouping ratio may be determined to be 5, or 4, etc. At this time, in order to improve data processing efficiency, an integer value smaller than and closest to the ratio of the first data bit width to the second data bit width may be used. For example, when the ratio of the first data bit width to the second data bit width is 6, the integer value 5 may be determined as the data grouping ratio.

[0105] This implementation can determine the data grouping ratio by using the first data bit width of the data processed by the digital signal processor performing the pattern operation, thereby improving the utilization rate of the digital signal processor, avoiding resource waste, and improving data processing efficiency.

[0106] In a possible implementation, when the data processing parameters include data flow information, the data processing request includes a data processing method, and the data processing method indicates a mode operation type, for the above: after receiving the data processing request, determining the data processing parameters that match the data processing request specifically includes the following steps:

[0107] Based on the mode operation type indicated by the data processing method, a data processing path is determined; then, based on the data processing path, data flow information is determined.

[0108] The data flow information may indicate the flow direction of data in the digital signal processor, that is, the processing path of data that needs to be processed by pattern operation in the digital signal processor.

[0109] In an example, the mode operation type may be the above-mentioned sum of absolute differences, mean square error, Pearson correlation coefficient, etc. The mode operation type is not limited here and is based on meeting actual needs.

[0110] This implementation can determine the data flow information based on the mode operation type of the mode operation requested by the data processing request, so that the digital signal processor can implement different mode operation processing according to different data flow information, thereby improving the flexibility and diversity of the data processing system and increasing the scope of applicability of the data processing system.

[0111] In a possible implementation, the data processing parameters may also include a data quantization ratio; the data quantization ratio indicates the proportion of quantization processing on the first processed data; at this time, after receiving the data processing request, when determining the data processing parameters that match the data processing request, you can first determine the data processing scenario that matches the data processing request; then, based on the processing accuracy requirements corresponding to the data processing scenario, determine the data quantization ratio.

[0112] In one example, data processing scenarios may include but are not limited to the following scenarios: enterprise system analysis scenario, Internet of Things analysis scenario, encryption algorithm evaluation scenario, financial system analysis scenario, etc. At this time, at least one accuracy requirement range may be divided according to the processing accuracy requirements of each data processing scenario, and a corresponding data quantization ratio may be set for each accuracy requirement range. At this time, different accuracy requirement ranges may correspond to different data quantization ratios.

[0113] For example, the first precision requirement range can be divided according to the processing precision requirements of the enterprise system analysis scenario and the Internet of Things analysis scenario, the second precision requirement can be divided according to the processing precision requirements of the encryption algorithm evaluation scenario, and the third precision requirement can be divided according to the processing precision requirements of the financial system analysis scenario. At this time, the data quantization ratio corresponding to the first precision requirement range can be preset to 3; the data quantization ratio corresponding to the second precision requirement range can be preset to 2; and the data quantization ratio corresponding to the third precision requirement range can be preset to 1. At this time, when the data quantization ratio is 1, it means that the processing precision requirement in this data processing scenario is the highest. At this time, the first processed data can be not quantized. When the data quantization ratio is 1, it can also be understood that the data processing parameters do not include the data quantization ratio.

[0114] Based on this, when the data processing parameters also include a data quantization ratio, the controller 601 may also send the data quantization ratio to the data processing module.

[0115] At this time, the data processing module 602 is also used to: receive the data quantization ratio, and after obtaining the first processed data, quantize the first processed data according to the data quantization ratio to obtain the quantized first processed data. At this time, the first processed data can be quantized according to the data quantization ratio, thereby reducing the computational complexity and the performance requirements of the mode operation, thereby further improving the data processing efficiency.

[0116] In a possible implementation, the pattern operation process has a certain degree of complexity, which results in the pattern operation process including multiple levels of operations.

[0117] For example, if the mode operation processing is a mean square error operation, the mode operation processing formula can refer to the following formula (1).

[0118] (1)

[0119] In the scenario of the embodiment of the present application, in the above formula (1), n ​​represents the amount of data for a single mode operation, that is, the amount of the first processed data included in the second processed data. represents the i-th first processed data in the second processed data, Represents the i-th operation reference data. At this time, and One to one correspondence.

[0120] At this time, the mean square error operation may include four levels of operations, wherein the first level operation may be a subtraction operation, the second level operation may be a multiplication operation, the third level operation may be an addition operation, and the fourth level operation may be a division operation.

[0121] When the pattern operation processing includes multiple levels of operations, the data flow information in the data processing parameters includes intra-layer feedback flow; wherein the intra-layer feedback flow indicates that the output result of the previous level of operation is transmitted again to the digital signal processor as input data for the next level of operation.

[0122] For example, for the above-mentioned mean square error operation, the output result of the first-level operation can be used as the input data of the second-level operation, and then input into the digital signal processor for processing again to obtain the output result of the second-level operation. Then, the output result of the second-level operation can be used as the input data of the third-level operation, and then input into the digital signal processor for processing again to obtain the output result of the third-level operation. Finally, the output result of the third-level operation can be used as the input data of the fourth-level operation, and then input into the digital signal processor for processing again to obtain the pattern operation result.

[0123] In the specific implementation, for the above: according to the received data flow information, the second processed data received by each digital signal processor and the operation reference data corresponding to each group of second processed data are input into the corresponding digital signal processor for pattern operation processing to obtain the pattern operation result, which specifically includes the following steps:

[0124] S11. Determine input data for a primary operation based on the second processed data and the operation reference data.

[0125] S12, inputting the input data of the primary operation into the digital signal processor for primary operation processing to obtain the primary operation result.

[0126] S13, determining the input data of the first-level operation as the input data of the previous-level operation; and determining the result of the first-level operation as the result of the previous-level operation.

[0127] S14. Repeat the following steps for each group of second processed data and the operation reference data corresponding to each group of second processed data until the operation result of the last level of operation is determined to obtain the pattern operation result: determine the input data of the next level of operation according to the operation result of the previous level, and input the input data of the next level of operation into the digital signal processor for the next level of operation according to the feedback flow direction within the layer included in the received data flow direction information, so as to obtain the operation result of the next level of operation.

[0128] For an example, see Figure 7 , Figure 7 A schematic diagram of data flow information when a single-layer digital signal processing layer performs pattern operation processing is provided in an embodiment of the present application. Figure 7 As shown, when performing the above mean square error operation, each group of second processed data can be input into each digital signal processor in the digital signal processing layer to perform pattern budget processing on each group of second processed data. Specifically, it is assumed that the data to be processed by pattern operation is described in the above formula (1): and , and, assuming n is 3. Then, we can respectively and , and , and As input data, it is input into the digital signal processor for primary operation processing (i.e. subtraction operation processing) to obtain the primary operation result, i.e. - , - , - After that, the input data of the next level operation can be determined according to the result of the first level operation (that is, the result of the previous level operation). At this time, the input data of the second level operation can be determined as - , - and - At this time, the input data of the determined secondary operation can be transmitted to the digital signal processor again according to the feedback flow direction within the layer, and the input data of the secondary operation can be multiplied by itself (that is, multiplication operation) to obtain the secondary operation result, that is, , and After that, the input data of the next level operation can be determined according to the result of the second level operation (that is, the result of the previous level operation). , and The input data of the three-level operation is determined, and according to the feedback flow direction within the layer, the input data of the three-level operation is transmitted to the digital signal processor again, and the input data of the three-level operation is added to obtain the three-level operation result, that is, + + Then, the input data of the next level operation can be determined according to the third level operation result (that is, the previous level operation result). + + The input data of the four-level operation is determined, and according to the feedback flow direction within the layer, the input data of the four-level operation is transmitted to the digital signal processor again, and the input data of the four-level operation is divided to obtain the result of the four-level operation, that is, [ + + ] / 3, at this time, the mode operation result of the second processed data can be obtained.

[0129] In one example, the data flow information may also include a direct output flow. In this case, after obtaining the pattern operation result, the pattern operation result may be input into the subsequent logic for analysis and processing according to the direct output flow direction.

[0130] like Figure 7 As shown, in the case where the number of the second processed data is multiple groups, a single digital signal processing layer may include multiple digital signal processors (for example, Figure 7 The digital signal processors 1, ..., digital signal processors N shown are each used for processing a set of second processing data.

[0131] This implementation can complete the pattern operation processing in a single digital signal processor, further reducing the hardware area and saving space resources. At the same time, multiple digital signal processors can be deployed in a single digital signal processing layer, which can increase the amount of data processed per unit time, thereby making the data processing system have a larger bandwidth for processing data, so that the digital processing system can process higher frequency data, so that the time point when the first processed data matches the operation reference data can be determined more accurately (that is, the time point when the real-time signal data is more similar to the reference signal data) can be determined, thereby improving the accuracy of the pattern operation processing.

[0132] In a possible implementation, when the pattern operation includes multiple levels of operation, multiple digital signal processors can be used to process the multiple levels of operation. For example, one level of operation can be processed in a single digital signal processor, or part of the level of operation can be processed in a single digital signal processor. In this case, the digital signal processing array may include multiple digital signal processing layers, each of which is used to process one level of operation or part of the level of operation. In this case, the process of processing data by each digital signal processor included in a single signal data layer can refer to the steps described in S11 to S14 above, which will not be described in detail here.

[0133] In the case where the digital signal processing array includes multiple digital signal processing layers, see Figure 8 , Figure 8 A schematic diagram of another digital processing system provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the system can be applied to a cryptographic analysis device, and includes: a controller 801, a data processing module 802 and a digital signal processing array 803.

[0134] The data processing module 802 is used for packet processing; the digital signal processing array 803 includes a plurality of digital signal processing layers 804 (for example, Figure 8 As shown, digital signal processing layers 804-1 to digital signal processing layers 804-L, where L is an integer greater than 1), each digital signal processing layer includes at least one digital signal processor 805 (here the number of digital signal processors 805 can be N); each digital signal processing layer 804 is used to perform one-level or partial-level operations; the digital signal processor 805 is used to perform operation processing.

[0135] The controller 801 is used to determine the data processing parameters that match the data processing request after receiving the data processing request; wherein the data processing request is used to request pattern operation processing on the data; the data processing parameters include data grouping ratio, data flow information and data acquisition quantity; the data grouping ratio and data acquisition quantity included in the data processing parameters are sent to the data processing module, and the data flow information is sent to the digital signal processing array.

[0136] The data processing module 802 is used to obtain a plurality of first processed data matching the data acquisition quantity; and after receiving the data grouping ratio, the plurality of first processed data are packaged and grouped according to the data grouping ratio to obtain a plurality of groups of second processed data; and each group of second processed data is sent to each digital signal processor included in the digital signal processing array.

[0137] like Figure 8As shown, the data processing module 802 can obtain a plurality of first processed data from a data source. At this time, the data source may include real-time signal data collected from an encryption device.

[0138] The digital signal processing array 803 is used to obtain the operation reference data corresponding to each group of second processed data, and according to the received data flow information, input the second processed data received by each digital signal processor and the operation reference data corresponding to each group of second processed data into the corresponding digital signal processor for pattern operation processing to obtain the pattern operation result.

[0139] like Figure 8 As shown, the digital signal processing array 803 can obtain computational reference data from a data source. At this time, the computational reference data may indicate reference signal data directly obtained from the data source, or may indicate data after the reference signal data in the data source is processed by the data processing module 802 (the processing process is the same as the processing process of the first processed data). At this time, the data source may also include pre-stored reference signal data.

[0140] like Figure 8 As shown, after the pattern operation result is obtained, the pattern operation result can be transmitted to the subsequent logic for analysis and processing, for example, side channel analysis or fault injection.

[0141] In one example, if a digital signal processing array includes multiple digital signal processing layers, and each digital signal processing layer is used to implement a first-level operation, then the data flow information in the data processing parameters includes an inter-layer cascade flow direction; wherein the inter-layer cascade flow direction indicates that the output result of the previous data processing signal layer is input into the next data processing signal layer.

[0142] For example, for the above-mentioned mean square error operation, the digital signal processing array may include four digital signal processing layers, and each digital signal processing layer may include at least one digital signal processor. At this time, the second processed data and the operation reference data corresponding to the second processed data can be first input into the digital signal processor in the first digital signal processing layer for operation processing to obtain the output result of the first-level operation. Then, the output result of the first-level operation is input into the digital signal processor in the second digital signal processing layer for operation processing to obtain the output result of the second-level operation. Next, the output result of the second-level operation is input into the digital signal processor in the third digital signal processing layer for operation processing to obtain the output result of the third-level operation. Finally, the output result of the third-level operation is input into the digital signal processor in the fourth digital signal processing layer for operation processing to obtain the output result of the fourth-level operation, that is, the pattern operation result.

[0143] At this time, if the second processed data received by each digital signal processor and the operation reference data corresponding to each group of second processed data are input into the corresponding digital signal processor for pattern operation processing according to the received data flow direction information, and the pattern operation result is obtained, the steps described below can be executed:

[0144] S21. Determine input data for a primary operation based on the second processed data and the operation reference data.

[0145] S22, inputting the input data of the primary operation into the digital signal processor of the first digital signal processing layer to perform the primary operation and obtain the primary operation result.

[0146] S23, determining the input data of the first-level operation as the input data of the previous-level operation; and determining the result of the first-level operation as the result of the previous-level operation.

[0147] S24. Repeat the following steps until the operation result of the last level of operation is determined to obtain the pattern operation result: determine the input data of the next level of operation according to the operation result of the previous level, and input the input data of the next level of operation into the digital signal processor of the next digital signal processing layer for the next level of operation according to the inter-layer cascade flow direction included in the received data flow direction information, to obtain the operation result of the next level of operation.

[0148] See also Fig. 9 , Fig. 9 A schematic diagram of data flow information when performing pattern operation processing through multiple digital signal processing layers provided in an embodiment of the present application. Fig. 9 As shown, there are four digital signal processing layers, namely digital signal processing layer 1, digital signal processing layer 2, digital signal processing layer 3 and digital signal processing layer 4. Then, when performing the above mean square error calculation, it is assumed that the data for pattern calculation processing is described in the above formula (1): and , and, assuming n is 3. Then, the following operations can be performed: and , and , and As input data, it is input into the digital signal processor in the first digital signal processing layer for primary operation processing (i.e., subtraction operation processing) to obtain the primary operation result, i.e., - , - , - After that, the input data of the next level operation can be determined according to the result of the first level operation (that is, the result of the previous level operation). At this time, the input data of the second level operation can be determined as - , - and - At this time, according to the inter-layer cascade flow direction, the input data of the determined secondary operation can be transmitted to the digital signal processor in the second digital signal processing layer, and the input data of the secondary operation can be multiplied by itself (that is, multiplication operation) to obtain the secondary operation result, that is, , and After that, the input data of the next level operation can be determined according to the result of the second level operation (that is, the result of the previous level operation). , and The input data of the three-level operation is determined, and according to the inter-layer cascade flow direction, the input data of the three-level operation is transmitted to the digital signal processor in the third digital signal processing layer, and the input data of the three-level operation is added to obtain the three-level operation result, that is, + + Then, the input data of the next level operation can be determined according to the third level operation result (that is, the previous level operation result). + + The input data of the four-level operation is determined, and according to the inter-layer cascade flow direction, the input data of the four-level operation is transmitted to the digital signal processor in the fourth digital signal processing layer, and the input data of the four-level operation is divided to obtain the four-level operation result, that is, [ + + ] / 3, at this time, the mode operation result of the second processed data can be obtained.

[0149] In one example, the data flow information may also include a direct output flow. In this case, after obtaining the pattern operation result, the pattern operation result may be input into the subsequent logic for analysis and processing according to the direct output flow direction.

[0150] This implementation method can complete pattern operation processing through multiple digital signal processing layers when hardware space resources permit. It can not only reduce the complexity of the digital signal processor, thereby reducing the error probability to further ensure the accuracy of the pattern operation results, but also improve the flexibility of data processing, thereby further accelerating the data processing speed and improving data processing efficiency.

[0151] In a possible implementation, a single-layer digital signal processing layer can perform partial-level operations. For example, for the above-mentioned mean square error operation, the first-level operation and the second-level operation can be completed in the first-layer digital signal processing layer, and the third-level operation and the fourth-level operation can be completed in the second-layer digital signal processing layer. For another example, the first-level operation and the third-level operation can be completed in the first-layer digital signal processing layer, and the second-level operation and the fourth-level operation can be completed in the second-layer digital signal processing layer. There is no limitation on the partial-level operations that can be completed by each digital signal processing layer, which is subject to what can be realized.

[0152] In one possible implementation, when there are multiple groups of second processed data, certain pattern operation types may require second processed data in different groups to participate in the operation processing when performing the pattern operation. At this time, the data flow direction information can be determined based on the data processing path under the pattern operation type. At this time, the data flow direction information can include an intra-layer cascade flow direction, wherein the intra-layer cascade flow direction is used to indicate that the data in the previous digital signal processor is transferred to the next digital signal processor (at this time, the previous digital signal processor and the next digital signal processor belong to the same digital signal processing layer).

[0153] Based on this, different data flow direction information may correspond to different data processing paths. At this time, the data flow direction information may include: input flow direction, output flow direction, intra-layer feedback flow direction, inter-layer cascade flow direction, and at least one of intra-layer cascade flow direction.

[0154] In one possible implementation, in addition to determining the data processing parameters that match the data processing parameters according to the process described above, the data processing parameters can also be pre-set for one or more fixed data processing scenarios, so that the above-mentioned mode operation logic can be implemented through hardware connection, thereby further accelerating the data processing speed and improving efficiency.

[0155] Based on this, after receiving the data processing request, determining the data processing parameters that match the data processing request specifically includes the following steps:

[0156] S31. Determine a data processing scenario that matches the data processing request.

[0157] In an example, the data processing scenario can be the above scenario or a customized scenario (for example, a mean square error calculation scenario, etc.). The data processing scenario is not limited here, and is subject to implementation.

[0158] S32: Based on the matched data processing scenario, determine preset parameters corresponding to the matched data processing scenario from a preset relationship mapping table.

[0159] The preset relationship mapping table includes the association relationship between the data processing scenarios and the data processing parameters.

[0160] S33: Determine the preset parameters as data processing parameters that match the data processing request.

[0161] The following briefly introduces the data processing method corresponding to the data processing system provided in the present application. The data processing method can be applied to the data processing system in any of the above embodiments.

[0162] See also Fig.10 , Fig.10 A flowchart of a data processing method provided in an embodiment of the present application is shown in FIG. Fig.10 As shown, the method includes:

[0163] S1001. Receive a data processing request.

[0164] The data processing request is used to request to perform pattern operation processing on the data.

[0165] S1002: After receiving a data processing request, determine data processing parameters that match the data processing request.

[0166] The data processing parameters include data grouping ratio, data flow information and data acquisition quantity.

[0167] S1003: Acquire a plurality of first processed data matching the data acquisition quantity, and perform packaging and grouping processing on the plurality of first processed data according to a data grouping ratio to obtain a plurality of groups of second processed data.

[0168] S1004, obtaining operation reference data corresponding to each group of second processed data; and performing pattern operation processing on each group of second processed data and the operation reference data corresponding to each group of second processed data according to the data flow information to obtain a pattern operation result.

[0169] This implementation method can package and group multiple first processed data obtained according to data grouping comparison to obtain multiple groups of second processed data, and perform pattern operation processing on each group of second processed data through multiple digital signal processors, so that the data processing system can simultaneously observe / process a wider range of data, thereby improving the bandwidth and processing efficiency of the data processed by the data processing system. At this time, while improving the processing efficiency of the data processing system, it is equivalent to improving the frequency of data processing by the data processing system, so that it can process data with a higher frequency and improve the accuracy of data processing.

[0170] See also Fig.11 , Fig.11A flow chart of another data processing method provided in an embodiment of the present application is as follows: Fig.11 As shown, the method includes:

[0171] S1101. Receive a data processing request.

[0172] The data processing request is used to request to perform pattern operation processing on the data.

[0173] S1102: After receiving the data processing request, determine data processing parameters that match the data processing request.

[0174] The data processing parameters include data grouping ratio, data flow information, data acquisition quantity and data quantization ratio.

[0175] S1103: Acquire a plurality of first processed data matching the data acquisition quantity.

[0176] S1104 , performing quantization processing on each first processed data according to the data quantization comparison to obtain quantized first processed data.

[0177] S1105 . Pack and group the plurality of first processed data according to the data grouping ratio to obtain a plurality of groups of second processed data.

[0178] S1106. Obtain operation reference data corresponding to each group of second processed data; and perform pattern operation processing on each group of second processed data and the operation reference data corresponding to each group of second processed data according to the data flow information to obtain a pattern operation result.

[0179] This implementation, in addition to improving data processing efficiency and accuracy based on the data grouping ratio and the digital signal processor, can also reduce the precision of the first processed data based on the data quantization ratio, thereby reducing the performance requirements of the pattern operation, which not only saves resources but also further improves data processing efficiency.

[0180] Fig.12 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Fig.12 As shown, the electronic device 1200 provided in this embodiment includes: at least one processor 1201 and a memory 1202. Optionally, the device 1200 also includes a communication component 1203. The processor 1201, the memory 1202 and the communication component 1203 are connected via a bus 1204.

[0181] In a specific implementation process, at least one processor 1201 executes the computer execution instructions stored in the memory 1202, so that at least one processor 1201 executes the above-mentioned data processing method.

[0182] The specific implementation process of the processor 1201 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0183] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0184] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0185] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0186] The present application also provides a computer program product, including a computer program, which implements the above-mentioned data processing method when executed by a processor.

[0187] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above-mentioned data processing method is implemented.

[0188] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0189] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0190] It should be noted that the above division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0191] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0192] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0193] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling an electronic device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0194] Those skilled in the art can understand that all or part of the steps of implementing the above embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk, etc., various media that can store program codes.

[0195] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A data processing system, characterized in that: Applied to a cryptographic analysis device, the system comprises: a controller, a data processing module and a digital signal processing array; wherein the data processing module is used for performing packaging and grouping processing; the digital signal processing array comprises at least one digital signal processor; the digital signal processor is used for performing pattern operation processing; The controller is used to determine data processing parameters matching the data processing request after receiving the data processing request; wherein the data processing request is used to request pattern operation processing of data; the data processing parameters include data grouping ratio, data flow information and data acquisition quantity; the data grouping ratio and data acquisition quantity included in the data processing parameters are sent to the data processing module, and the data flow information is sent to the digital signal processing array; The data processing module is used to obtain a plurality of first processed data matching the data acquisition quantity; and after receiving the data grouping ratio, according to the data grouping ratio, the plurality of first processed data are packaged and grouped to obtain a plurality of groups of second processed data; and each group of the second processed data is sent to each of the digital signal processors included in the digital signal processing array; The digital signal processing array is used to obtain the operation reference data corresponding to each group of the second processed data, and according to the received data flow information, input the second processed data received by each digital signal processor and the operation reference data corresponding to each group of the second processed data into the corresponding digital signal processor for pattern operation processing to obtain a pattern operation result.

2. The system according to claim 1, characterized in that The data processing parameters include the data grouping ratio; the data processing request includes identification information indicating a digital signal processor for data processing; after receiving the data processing request, determining the data processing parameters matching the data processing request includes: Determine a first data bit width of data processed by a digital signal processor matching the identification information; and determine a second data bit width corresponding to the first processed data; The data grouping ratio is determined based on a ratio of the first data bit width to the second data bit width.

3. The system according to claim 1, characterized in that The data processing parameters include the data flow information; the data processing request includes a data processing method; the data processing method indicates a mode operation type; After receiving the data processing request, determining data processing parameters matching the data processing request includes: Determining a data processing path based on the mode operation type indicated by the data processing method; Based on the data processing path, the data flow information is determined.

4. The system according to claim 1, characterized in that The data processing parameters also include a data quantization ratio; the data quantization ratio indicates a ratio of quantization processing of the first processed data; after receiving the data processing request, determining the data processing parameters matching the data processing request includes: Determining a data processing scenario that matches the data processing request; The data quantization ratio is determined based on the processing accuracy requirement corresponding to the data processing scenario.

5. The system according to claim 4, characterized in that The controller is further used for: Sending the data quantization ratio to the data processing module; The data processing module is further used for: The data quantization ratio is received, and after obtaining the first processed data, the first processed data is quantized according to the data quantization ratio to obtain the quantized first processed data.

6. The system according to any one of claims 1 to 5, characterized in that: The pattern operation processing includes multiple levels of operations; the data flow information includes intra-layer feedback flow; wherein the intra-layer feedback flow indicates that the output result of the previous level of operation is transmitted again to the digital signal processor as input data of the next level of operation.

7. The system according to claim 6, characterized in that According to the received data flow direction information, the second processed data received by each digital signal processor and the operation reference data corresponding to each group of the second processed data are input into the corresponding digital signal processor for pattern operation processing to obtain a pattern operation result, including: determining input data for a primary operation based on the second processed data and the operation reference data; Inputting the input data of the primary operation into the digital signal processor for primary operation processing to obtain a primary operation result; Determine the input data of the first-level operation as the input data of the previous-level operation; and determine the result of the first-level operation as the result of the previous-level operation; Repeat the following steps for each group of the second processed data and the operation reference data corresponding to each group of the second processed data until the operation result of the last level of operation is determined to obtain the pattern operation result: determine the input data of the next level of operation according to the operation result of the previous level, and input the input data of the next level of operation into the digital signal processor for the next level of operation according to the feedback flow direction within the layer included in the received data flow direction information, so as to obtain the operation result of the next level of operation.

8. The system according to claim 6, characterized in that The digital signal processing array includes multiple digital signal processing layers, each of which is used to implement a first-level operation; the data flow information includes an inter-layer cascade flow direction; wherein the inter-layer cascade flow direction indicates that the output result of the previous data processing signal layer is input into the next data processing signal layer.

9. The system according to claim 8, characterized in that According to the received data flow direction information, the second processed data received by each digital signal processor and the operation reference data corresponding to each group of the second processed data are input into the corresponding digital signal processor for pattern operation processing to obtain a pattern operation result, including: determining input data for a primary operation based on the second processed data and the operation reference data; Inputting the input data of the primary operation into the digital signal processor of the first digital signal processing layer to perform the primary operation and obtain the primary operation result; Determine the input data of the first-level operation as the input data of the previous-level operation; and determine the result of the first-level operation as the result of the previous-level operation; Repeat the following steps for each group of the second processed data and the operation reference data corresponding to each group of the second processed data until the operation result of the last level of operation is determined to obtain the pattern operation result: determine the input data of the next level of operation according to the operation result of the previous level, and input the input data of the next level of operation into the digital signal processor of the next digital signal processing layer for the next level of operation according to the inter-layer cascade flow direction included in the received data flow direction information, so as to obtain the operation result of the next level of operation.

10. The system according to any one of claims 1 to 5, characterized in that: After receiving the data processing request, determining data processing parameters matching the data processing request includes: Determining a data processing scenario that matches the data processing request; Based on the matched data processing scenario, determining preset parameters corresponding to the matched data processing scenario from a preset relationship mapping table; wherein the preset relationship mapping table includes an association relationship between the data processing scenario and the data processing parameters; The preset parameters are determined as data processing parameters that match the data processing request.

11. A data processing method, characterized in that: Applied to a cryptographic analysis device; the method comprises: Receiving a data processing request; wherein the data processing request is used to request a pattern operation processing to be performed on the data; After receiving the data processing request, determining data processing parameters matching the data processing request; wherein the data processing parameters include data grouping ratio, data flow information and data acquisition quantity; Acquire a plurality of first processed data matching the data acquisition quantity, and perform packaging and grouping processing on the plurality of first processed data according to the data grouping ratio to obtain a plurality of groups of second processed data; Obtain operation reference data corresponding to each group of the second processed data; and perform pattern operation processing on each group of the second processed data and the operation reference data corresponding to each group of the second processed data according to the data flow information to obtain a pattern operation result.

12. The method according to claim 11, characterized in that The data processing parameters also include a data quantization ratio; the method also includes: After acquiring a plurality of first processed data matching the data acquisition quantity, each of the first processed data is quantized according to the data quantization ratio to obtain quantized first processed data.

Citation Information

Patent Citations

  • Encryption and decryption circuit and method supporting multi-algorithm multi-grouping mode and SOC system

    CN118363925A

  • Game machine

    JP2020049126A

  • Aggregating metrics of network elements of a software-defined network for different applications based on different aggregation criteria

    US20240205119A1