Method, computer device and storage medium for optimizing digital logic circuit layout

By obtaining and utilizing the density, location and attribute information in the netlist and layout files of digital logic circuits, accurately estimate the winding length between nodes, solving the problem of poor layout optimization effect in the existing technology, and achieving the following Good layout optimization effect.

CN118627434BActive Publication Date: 2024-12-03X TIMES DESIGN AUTOMATION CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411091642.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-12-03
Estimated Expiration
2044-08-09

AI Technical Summary

Technical Problem

When optimizing the layout of digital logic circuits, it is difficult to accurately calculate the winding length between nodes, resulting in poor layout optimization effect. Especially when there are many nodes, the approximate calculation of the line length model will lead to actual winding. The length is quite different from the calculation results.

Method used

By obtaining the netlist and layout files of the digital logic circuit, the density information of the area where the netlist is located, the position information and attribute information of each node in the node list are determined, and the winding length between nodes is estimated based on this feature information. More precise winding length optimizes circuit layout.

Benefits of technology

The accuracy of winding length is improved and the layout of digital logic circuits is better. Compared with the calculation of line length model, the accuracy of winding length is increased by 7%, thereby improving the layout quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118627434B_ABST
    Figure CN118627434B_ABST
Patent Text Reader

Abstract

The present application provides a method, computer device and storage medium for optimizing the layout of digital logic circuits. The method includes: obtaining a netlist and layout file of the digital logic circuit, the netlist including a node list, determining the density information of the area where the netlist is located, the first position information and attribute information of each node in the node list according to the layout file and the netlist, obtaining the first winding length between each node in the node list according to the density information, the first position information and the attribute information, and optimizing the layout of the digital logic circuit according to the first winding length. The winding length obtained according to multiple features by the above method is more accurate, so that the effect of optimizing the layout of the digital logic circuit according to the more accurate winding length is better.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of digital logic circuits, and in particular to a method, a computer device, and a storage medium for optimizing the layout of digital logic circuits. Background Art

[0002] Electronic Design Automation (EDA) refers to a design method that uses computer-aided design (CAD) software to complete the functional design, synthesis, verification, physical design (including layout, routing, layout, design rule checking, etc.) of very large-scale integrated circuit (VLSI) chips.

[0003] As modern digital logic circuits become larger and more complex, users have higher and higher requirements for circuit timing, power consumption or area (Performance Power Area, PPA). Chip designers need EDA tools to perform floorplanning for digital logic circuits. The quality of floorplanning directly affects the timing and wiring quality of the overall design. Therefore, how to optimize the layout of digital logic circuits is an urgent problem to be solved. Summary of the invention

[0004] In view of this, the purpose of the present application is to propose a method, a computer device and a storage medium for optimizing the layout of a digital logic circuit, so as to solve or partially solve the above-mentioned problem.

[0005] Based on the above objectives, in a first aspect, the present application provides a method for optimizing the layout of a digital logic circuit, comprising:

[0006] Obtaining a netlist and a layout file of the digital logic circuit, wherein the netlist includes a node list;

[0007] Determine density information of the area where the netlist is located, first position information and attribute information of each node in the node list according to the layout file and the netlist;

[0008] Obtaining a first winding length between each node in the node list according to the density information, the first position information and the attribute information;

[0009] The layout of the digital logic circuit is optimized according to the first winding length.

[0010] In a second aspect of the present application, a computer device is provided, including:

[0011] one or more processors, memory; and

[0012] one or more programs;

[0013] The one or more programs are stored in the memory and executed by the one or more processors, and the programs include instructions for executing the method according to the first aspect.

[0014] According to a third aspect of the present application, a non-volatile computer-readable storage medium containing a computer program is provided. When the computer program is executed by one or more processors, the processors execute the method described in the first aspect.

[0015] From the above, it can be seen that the present application provides a method, computer equipment and storage medium for optimizing the layout of digital logic circuits. The method includes: obtaining a netlist and a layout file of the digital logic circuit, the netlist including a node list, determining the density information of the area where the netlist is located, the first position information and attribute information of each node in the node list according to the layout file and the netlist, obtaining the first winding length between each node in the node list according to the density information, the first position information and the attribute information, and optimizing the layout of the digital logic circuit according to the first winding length. The winding length obtained according to multiple features by the above method is more accurate, so that the effect of optimizing the layout of the digital logic circuit according to a more accurate winding length is better. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A schematic flowchart of a design and manufacturing process of an exemplary digital logic circuit according to an embodiment of the present application is shown.

[0018] Figure 2 A schematic diagram of an exemplary computer device according to an embodiment of the present application is shown.

[0019] Figure 3 A schematic diagram showing an exemplary application scenario according to an embodiment of the present application is shown.

[0020] Figure 4 A schematic diagram showing a layout area of ​​an exemplary chip according to an embodiment of the present application.

[0021] Figure 5 A flow chart of an exemplary method for optimizing digital logic circuit layout according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0023] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0024] It is understandable that before using the technical solutions of each embodiment of the present application, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0025] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to the electronic device, application, server, storage medium or other software or hardware that performs the operation of the technical solution of the present application according to the prompt message.

[0026] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0027] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation method of this application. Other methods that meet relevant laws and regulations may also be applied to the implementation method of this application.

[0028] Figure 1 A schematic flowchart of a design and manufacturing process 100 of an exemplary digital logic circuit according to an embodiment of the present application is shown.

[0029] The design and manufacturing process 100 begins with specification formulation 110. In the stage of specification formulation 110, the functional and performance requirements that the digital logic circuit needs to achieve are determined. Then, in the stage of design 120, the circuit design 122 is first performed with the help of EDA tools. After the circuit is determined, the layout and wiring of the circuit units in the digital logic circuit are determined by performing physical design 124, thereby obtaining a circuit layout. After obtaining the circuit layout, mask making 126 can be performed to obtain a mask for forming the designed circuit on a wafer. Subsequently, in the stage of manufacturing 130, the digital logic circuit is formed on the wafer through processes such as lithography, etching, ion implantation, thin film deposition, and polishing. In the stage of packaging 140, the wafer is cut to obtain a bare die, and the bare die is packaged to obtain a chip through processes such as pasting, welding, and mold sealing. The obtained chip is tested in the stage of testing 150 to ensure that the performance of the finished chip meets the requirements determined in the specification formulation 110. Finally, the chip 160 that passes the test can be delivered to the customer.

[0030] Physical design 124 mainly includes steps such as partitioning, layout planning, layout, clock tree synthesis, and wiring, and involves evaluation indicators such as routability, delay, power consumption, area, and manufacturability. Layout is an important part of physical design. As described in the background technology, as the scale of modern digital logic circuits becomes larger and larger, and the functions become more and more complex, users have higher and higher requirements for the timing, power consumption, or area (Performance Power Area, PPA) of circuits. Chip designers need EDA tools to perform floorplanning on digital logic circuits. The quality of the layout planning directly affects the timing and wiring quality of the overall design. Therefore, how to optimize the layout of digital logic circuits is an urgent problem to be solved.

[0031] Figure 2 A schematic diagram of an exemplary computer device 200 according to an embodiment of the present application is shown.

[0032] like Figure 2 As shown, the computer device 200 may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040 and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030 and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0033] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0034] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0035] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0036] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0037] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 ).

[0038] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0039] Figure 3 A schematic diagram of an exemplary application scenario 300 according to an embodiment of the present application is shown.

[0040] like Figure 3 As shown, the application scenario 300 may include a computer device 200. In some embodiments, the computer device 200 may be a device with computing functions such as a personal computer, a workstation, a server, etc., which is not limited in the present application.

[0041] The computer device 200 may obtain a netlist 302 of a chip and a layout file 304 storing an initial layout of the chip as input. The chip may include, for example, a plurality of circuit elements. In some embodiments, the plurality of circuit elements include at least one group of movable circuit elements. In some embodiments, the plurality of circuit elements may also include a group of fixed circuit elements.

[0042] It should be noted that, in the context of the present application, a "movable circuit element" refers to a circuit element whose position can be changed in the layout method according to each embodiment of the present application. In some embodiments, the movable single-path element can be, for example, a standard element such as a gate circuit. It should be understood that the movable circuit element can also be any other suitable element whose position is set to be changeable, and the present application does not limit this.

[0043] It should also be noted that, in the context of the present application, "fixed circuit element" means a circuit element whose position has been predetermined and cannot be changed in the layout method according to each embodiment of the present application. In some embodiments, the fixed circuit element may be, for example, a macro cell. "Macro cell" refers to a predefined logic function implementation unit composed of a trigger, an arithmetic logic unit, etc., which has a higher level of abstraction relative to a logic gate. It should be understood that the fixed circuit element may also be any other suitable element whose position is set to be unchangeable, and the scope of the present application is not limited in this respect. In the present application, since the layout optimization is optimized for movable circuit elements, if it is not explicitly stated as a "fixed circuit element" or an immovable circuit element, "circuit element" is generally used to refer to a "movable circuit element" for ease of description.

[0044] In some embodiments, the netlist 302 may at least indicate the size of multiple circuit elements in the chip, the connection relationship of multiple circuit elements, and the pin information contained in each circuit element. The pin information may be represented by a node and stored in the netlist 302 in the form of a node list. In some embodiments, the netlist 302 may also indicate information such as the layout area and process parameters of the chip, which is not limited in this application.

[0045] In some embodiments, the layout file 304 may indicate the positions of multiple circuit elements of the chip in the layout area, for example, the coordinates of each circuit element. In some embodiments, the layout file 304 may be a layout obtained by overall layout, wherein a certain degree of overlap exists between some circuit elements. It should be understood that the layout file 304 may also be any other suitable layout to be optimized, and the present application does not limit this.

[0046] In some embodiments, the netlist 302 and the layout file 304 may be input into the computer device 200 by a user. In some embodiments, the netlist 302 and the layout file 304 may have been pre-stored in the computer device 200. In some embodiments, the computer device 200 may also be communicatively coupled to other devices to obtain the netlist 302 and the layout file 304 from the other devices, which is not limited in the present application. It should be noted that although in Figure 3 The netlist 302 and the layout file 304 are shown as two independent files, but the netlist 302 and the layout file 304 may also be integrated into one file, which is not limited in the present application.

[0047] The method of optimizing the layout of digital logic circuits in EDA tools is usually to minimize the half-perimeter wirelength (HPWL) under the condition of density constraints, and optimize the layout of digital logic circuits based on the minimized half-perimeter wirelength. The half-perimeter wirelength can be calculated using the wirelength model.

[0048] Figure 4 A schematic diagram of a layout area 400 of an exemplary chip according to an embodiment of the present application is shown.

[0049] The layout area 400 of the chip may include a plurality of circuit elements, which may be considered as rectangular in shape for the purpose of illustration and simplicity. Figure 4 As shown, the layout area 400 of the chip may include a first component 404 , a second component 406 , a third component 408 , and a fourth component 410 .

[0050] When using the line length model to approximate the actual routing of the router, such as Figure 4 As shown, the approximated half-circle length is the length of a line surrounding the rectangular boundary. For example, the half-circle length 402 is a winding line connecting the first pin 4042 of the rectangle corresponding to the first component 404, the second pin 4062 of the rectangle corresponding to the second component 406, and the fourth pin 4102 of the rectangle corresponding to the fourth component 410. The winding length of the netlist is approximated by the half-circle length.

[0051] However, when there are many nodes in the netlist, the winding length approximated by the wire length model deviates greatly from the actual winding length. Figure 4 As shown in the figure, when there is a pin (node) corresponding to the third component 408 in the netlist, since the third component 408 is not at a relatively marginal position, the wire length model will not calculate the wire length connected to the third component 408 when calculating the half-circle wire length, but will only calculate the winding length of the connecting component at the marginal position in the netlist. Therefore, the actual winding length will be greater than the half-circle wire length calculated by the wire length model.

[0052] The effect on boundary points during the optimization process is much stronger than other internal points. In the process of optimizing wire length, optimization is usually performed by calculating the gradient of the model, which requires the original wire length model to be differentiable. No matter which optimization method is used, more attention will be paid to the boundary points, especially if there are many nodes in the netlist, the optimization effect of internal nodes will be smaller. Because the optimization goal of the wire length model is to make the enclosing rectangular boundary as small as possible, the position of the internal point has little effect on its objective function.

[0053] In view of this, the present application provides a method, computer device and storage medium for optimizing the layout of digital logic circuits. The method includes: obtaining a netlist and layout file of the digital logic circuit, the netlist including a node list, determining the density information of the area where the netlist is located, the first position information and attribute information of each node in the node list according to the layout file and the netlist, obtaining the first winding length between each node in the node list according to the density information, the first position information and the attribute information, and optimizing the layout of the digital logic circuit according to the first winding length. The winding length obtained by the above method according to multiple features (for example, density information, position information and attribute information) is more accurate, so that the effect of optimizing the layout of the digital logic circuit according to a more accurate winding length is better.

[0054] After obtaining the netlist and layout file, in some embodiments, the density information of the area where the netlist is located, the first position information and attribute information of each node in the node list of the netlist can be determined according to the netlist and layout file. Among them, the first position information can be the relative position information between nodes. The density information, the first position information and the attribute information are used as constraints to estimate the first winding length between nodes, and the layout of the digital logic circuit is optimized based on the winding length. The winding length obtained based on multiple features (for example, position information, density information and attribute information) is more accurate. Compared with the half-circle wire length calculated using the wire length model, the accuracy of the winding length obtained by the method of the embodiment of the present application can be improved by 7%. Furthermore, the effect of optimizing the digital logic circuit based on a more accurate winding length is better.

[0055] In some embodiments, the netlist may further include a component list, and the density information may be the density of the nodes in the node list, the density of the netlist, or the density of the components in the component list. Density information is used as a constraint for winding. When winding, the area with lower density can be selected according to the density information for routing, thereby avoiding the routing being too dense and affecting the signal transmission effect. In practical applications, the user can select different density information according to design needs, and the present application does not limit this. In some embodiments, the attribute information may include the ratio of the number of pins of each component in the component list to the total number of components, so that when winding, the ratio is used as a constraint, and components with relatively fewer pins and relatively unconcentrated pins can be selected for routing, thereby avoiding the routing being too dense and affecting the signal transmission effect.

[0056] In some embodiments, the first winding length can be estimated by a target model, and the target model can be a trained deep neural network. In some embodiments, the target model can use a diffusion model as the basic framework, first construct an encoding model in the form of stacked multi-layer convolutional networks and transformer networks, and then a decoding model. Compared with the method of using a wire length model to approximate the half-circle wire length for winding estimation, the use of a neural network model to estimate the wire length can obtain a more accurate estimation result because the model inputs more features (for example, density information, location information, and attribute information).

[0057] After training the constructed diffusion model, in some embodiments, the density information (e.g., target density information) of the area where the netlist (e.g., target netlist) is located can be used as the first image data, so that the image data can better reflect the density information; the position information (e.g., target position information) and attribute information (e.g., target attribute information) of each node in the node list (e.g., target node list) can be used as the first sequence data, so that the sequence data can more accurately reflect the position information and attribute information. The first image data and the first sequence data are used as training data to train the diffusion model, thereby obtaining the target model.

[0058] In some embodiments, the winding results of the netlist generated by the winding tool according to the actual design case can be used as the winding label. The winding tool can be, for example, a wiring engine. In this way, the winding results generated by the winding tool according to the actual design case are used as the winding label. In the supervised learning of the model, the winding label provides the corresponding relationship between the input and output required for the training model, so that the trained model can accurately estimate the winding length.

[0059] Taking into account the characteristics of the picture data and the sequence data, in some embodiments, the first picture data and the first sequence data can be input into the encoding model, so as to encode the first picture data and the first sequence data to obtain the second picture data corresponding to the first picture data and the second sequence data corresponding to the first sequence data. The second picture data and the second sequence data are input into the decoding model for decoding.

[0060] For the diffusion model, in the related art, the diffusion model is used to generate images. However, in layout optimization, the image cannot accurately reflect the winding length. In view of this, in some embodiments, the image output of the decoding model can be converted into a sequence output. The third sequence data is output according to the second image data and the second sequence data. The third sequence data is used to represent the second winding length between the nodes. In this way, the estimated winding length can be accurately represented by the output sequence data.

[0061] The encoding model may include a convolutional network and a transformer network. In some embodiments, for image data, the features of the first image data are extracted through the convolutional network to obtain the second image data, and for sequence data, the features of the first sequence data are extracted through the transformer network to obtain the second sequence data. In this way, according to the characteristics of different input data, the corresponding network is selected for feature extraction, which is conducive to improving the efficiency and accuracy of the model in data processing.

[0062] After the first winding length is estimated by the model, in some embodiments, the estimated result of the model can be reversed to all nodes of the netlist, thereby optimizing the layout of the digital logic circuit. For example, if the first winding length can be further optimized, the model can output the moving direction and moving distance of the node corresponding to the first winding length, thereby obtaining the second position information of the optimized component based on the moving direction and moving distance, and moving the component of the digital logic circuit based on the second position information. In this way, since the winding length estimated by the model is more accurate, optimizing the digital logic circuit according to the winding length can also obtain better layout optimization results.

[0063] Figure 5 FIG. 5 is a flow chart of an exemplary method 500 for optimizing the layout of a digital logic circuit according to an embodiment of the present application. The method 500 may be executed by a computer device 200. Figure 5 As shown, method 500 may include the following steps.

[0064] In step 502 , the computer device 200 may obtain a netlist and a layout file of the digital logic circuit, wherein the netlist includes a node list.

[0065] In step 504, the computer device 200 may determine density information of the area where the netlist is located, first position information and attribute information of each node in the node list according to the layout file and the netlist.

[0066] In some embodiments, the netlist also includes a component list, and the density information includes the density of nodes in the node list, the density of the netlist, or the density of components in the component list. Density information is used as a constraint condition for winding. When winding, a region with a smaller density can be selected for routing according to the density information, thereby avoiding too dense routing that affects the signal transmission effect.

[0067] In some embodiments, the attribute information includes the ratio of the number of pins of each component in the component list to the total number of components in the component list. In this way, when routing, the ratio is used as a constraint condition, and components with relatively fewer pins and relatively less concentrated pins can be selected for routing, thereby avoiding too dense routing that affects the signal transmission effect.

[0068] In step 506, the computer device 200 may obtain a first winding length between each node in the node list according to the density information, the first position information and the attribute information.

[0069] In step 508 , the computer device 200 may optimize the layout of the digital logic circuit according to the first wiring length.

[0070] In some embodiments, the optimizing the layout of the digital logic circuit according to the first winding length further includes: obtaining the moving direction and moving distance of the node corresponding to the first winding length according to the first winding length; obtaining second position information according to the moving direction and the moving distance based on the first position information; optimizing the layout of the digital logic circuit according to the second position information. In this way, since the winding length estimated by the model is more accurate, optimizing the digital logic circuit according to the winding length can also obtain better layout optimization results.

[0071] In some embodiments, the digital logic circuit includes a target netlist, the target netlist includes a target node list, the moving direction and the moving distance are obtained according to a target model, and the target model is trained by the following method: obtaining training data, the training data includes first image data and first sequence data, the first image data includes target density information of the area where the target netlist is located, and the first sequence data includes target position information and target attribute information of each node in the target node list; using the training data to train a pre-built diffusion model to obtain the target model. Using image data can better reflect density information, and using sequence data can more accurately reflect position information and attribute information.

[0072] In some embodiments, the training data also includes a winding label, and the winding label represents the winding result of the target netlist. In this way, the winding result generated by the winding tool according to the actual design case is used as the winding label. In the supervised learning of the model, the winding label provides the corresponding relationship between the input and output required for the training model, so that the trained model can accurately estimate the winding length.

[0073] In some embodiments, the pre-built diffusion model includes an encoding model and a decoding model, and the training of the pre-built diffusion model using the training data further includes: inputting the first picture data and the first sequence data into the encoding model to obtain the second picture data corresponding to the first picture data and the second sequence data corresponding to the first sequence data; inputting the second picture data and the second sequence data into the decoding model to obtain the third sequence data according to the second picture data and the second sequence data, and the third sequence data is used to represent the second winding length between each node in the target node list. In this way, the output sequence data can accurately represent the estimated winding length.

[0074] In some embodiments, the encoding model includes a convolutional network and a transformer network, and the step of inputting the first image data and the first sequence data into the encoding model to obtain the second image data corresponding to the first image data and the second sequence data corresponding to the first sequence data further includes: extracting features of the first image data using the convolutional network to obtain the second image data; and extracting features of the first sequence data using the transformer network to obtain the second sequence data. In this way, selecting the corresponding network for feature extraction according to the characteristics of different input data is conducive to improving the efficiency and accuracy of the model in data processing.

[0075] The present application provides a method, computer device and storage medium for optimizing the layout of digital logic circuits. The method includes: obtaining a netlist and layout file of the digital logic circuit, the netlist including a node list, determining the density information of the area where the netlist is located, the first position information and attribute information of each node in the node list according to the layout file and the netlist, obtaining the first winding length between each node in the node list according to the density information, the first position information and the attribute information, and optimizing the layout of the digital logic circuit according to the first winding length. The winding length obtained according to multiple features by the above method is more accurate, so that the effect of optimizing the layout of the digital logic circuit according to the more accurate winding length is better.

[0076] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0077] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0078] Based on the same technical concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-volatile computer-readable storage medium containing a computer program, wherein the non-volatile computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute method 500.

[0079] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0080] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the method 500 described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0081] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0082] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power / ground connections to the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device may be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present application are to be implemented (that is, these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or with changes in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0083] Although the present application has been described in conjunction with specific embodiments of the present application, many alternatives, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the discussed embodiments.

[0084] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A method for optimizing the layout of a digital logic circuit, characterized in that: include: Obtaining a netlist and a layout file of the digital logic circuit, wherein the netlist includes a node list; Determine, according to the layout file and the netlist, density information of the layout area corresponding to the netlist, first position information and attribute information of each node in the node list, wherein the density information includes the density of nodes in the node list, the density of the netlist, or the density of components in the component list; Obtaining a first winding length corresponding to each node in the node list according to the density information, the first position information and the attribute information, wherein the first winding length is obtained through a target model; According to the first winding length, obtaining a moving direction and a moving distance of a node corresponding to the first winding length; Elements of the digital logic circuit are moved based on the moving direction and the moving distance to optimize the layout of the digital logic circuit.

2. The method according to claim 1, characterized in that The step of moving the elements of the digital logic circuit based on the moving direction and the moving distance to optimize the layout of the digital logic circuit further includes: Based on the first position information and the target model, second position information is obtained according to the moving direction and the moving distance; Elements of the digital logic circuit are moved according to the second position information to optimize the layout of the digital logic circuit.

3. The method according to claim 2, characterized in that The digital logic circuit includes a target netlist, the target netlist includes a target node list, and the target model is trained by the following method: Acquire training data, the training data including first image data and first sequence data, the first image data including target density information of the layout area corresponding to the target netlist, the first sequence data including target position information and target attribute information of each node in the target node list; The pre-built diffusion model is trained using the training data to obtain the target model.

4. The method according to claim 3, characterized in that The training data also includes a routing label, where the routing label indicates a routing result of the target netlist.

5. The method according to claim 3, characterized in that The pre-built diffusion model includes an encoding model and a decoding model, and the training of the pre-built diffusion model using the training data further includes: Inputting the first picture data and the first sequence data into the coding model to obtain second picture data corresponding to the first picture data and second sequence data corresponding to the first sequence data; The second image data and the second sequence data are input into the decoding model to obtain third sequence data according to the second image data and the second sequence data, wherein the third sequence data is used to represent the second winding length corresponding to each node in the target node list.

6. The method according to claim 5, characterized in that The encoding model includes a convolutional network and a transformer network, and the step of inputting the first picture data and the first sequence data into the encoding model to obtain second picture data corresponding to the first picture data and second sequence data corresponding to the first sequence data further includes: Extracting features of the first picture data using the convolutional network to obtain the second picture data; The transformer network is used to extract features of the first sequence data to obtain the second sequence data.

7. The method according to claim 1, characterized in that The netlist also includes a component list, and the density information includes the density of nodes in the node list, the density of the netlist, or the density of components in the component list.

8. The method according to claim 7, characterized in that The attribute information includes a ratio of the number of pins of each component in the component list to the total number of components in the component list.

9. A computer device, characterized in that: include: One or more processors, memory; as well as one or more programs; The one or more programs are stored in the memory and executed by the one or more processors, and the programs include instructions for executing the method according to any one of claims 1-8.

10. A non-volatile computer-readable storage medium containing a computer program, characterized in that: When the computer program is executed by one or more processors, the processors are caused to perform the method according to any one of claims 1 to 8.

Citation Information

Patent Citations

  • FPGA layout-based optimization method

    CN106021722A

  • System and method for optimizing chip layout based on deep reinforcement learning

    CN114154412A

  • Chip layout optimization method capable of being driven by differential time sequence

    CN114861591A

  • Chip layout optimization method and related equipment

    CN116822452A