System and method for generating a network using physical personal data of images from a

By loading and converting digital layout planning diagrams, detecting blocks and generating corresponding second layout planning diagrams, displaying NoC's blocks and maximum available areas, the difficulty of chip layout planning diagram modification and performance optimization is solved, and more efficient design process and resource utilization.

CN119067057APending Publication Date: 2024-12-03ATRIS CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410689802.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-05-30
Filing Date
2024-05-30
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Modification and performance optimization of chip layout planning diagrams are a difficult and time-consuming task when designing network on chip (NoC) for multiprocessor systems, especially when designing multiple performance requirements and frequent layout planning changes. The teacher needs to repeat the task multiple times.

Method used

By loading the digital layout planning diagram of the chip, converting it into a grayscale image, detecting the block area, and generating the corresponding second layout planning diagram to display the block and maximum available area of ​​the NoC, design using machine learning models and interactive tools Optimize and edit to reduce the use of computing resources.

Benefits of technology

This method simplifies the NoC planning process, reduces the use of computing resources, improves design efficiency, and further optimizes the design through feedback training models to ensure the feasibility and performance of the NoC design.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067057A_ABST
    Figure CN119067057A_ABST
Patent Text Reader

Abstract

The invention relates to a system and method for generating a network using physical perception data from images of a chip layout plan. The layout planning of the semiconductor chip comprises loading an image of a first layout planning of the chip; converting the digital image into a grayscale image; detecting blocks in the grayscale image; and generating a second layout planning map corresponding to the first layout planning map. The second plan view shows a representation of blocks and a maximum available area of a network-on-chip (NoC).
Need to check novelty before this filing date? Find Prior Art

Description

[0001] Priority claim

[0002] This application claims the benefit of U.S. Provisional Application No. 63 / 469,548, filed on May 30, 2023, by Amir CHARIF et al., entitled “SYSTEM AND METHOD FOR PHYSICAL AWARENESSDATA FROM AN IMAGE, SYNCHRONIZING CHANGE LISTS, INTERACTIVE DATAFLOW AND CHANGE LIST INTERPRETERS, AND FOR DEADLOCK DETECTION,” and U.S. Provisional Application No. 63 / 469,826, filed on May 30, 2023, by Christopher PEZLEY et al., entitled “SYSTEM AND METHOD FOR PHYSICAL AWARENESSDATA FROM AN IMAGE, SYNCHRONIZING CHANGE LISTS, INTERACTIVE DATAFLOW AND CHANGE LIST INTERPRETERS.” Technical Field

[0003] The present technology relates to electronic system design, and more particularly, to analysis and modification of floorplans of semiconductor devices including a network-on-chip (NoC). Background Art

[0004] Multiprocessor systems have been implemented in systems on a chip (SoC) that include a NoC. The SoC includes instances of intellectual property (IP), such as an initiator IP and a target IP that communicate via the NoC. Transactions in packet form are sent from an initiator to one or more targets using an industry standard protocol. The initiator sends a request transaction to the target using an address to select the target. The NoC decodes the address and transmits the request from the initiator to the target. The target processes the transaction and sends a response transaction, which is transmitted back to the initiator by the NoC.

[0005] NoC can include basic network functions such as network interface units, switches, adapters, and buffers. These basic functions can communicate with each other using internal NoC transport protocols, usually packet-based transmission. The network interface unit can convert the protocol used by the connected SoC unit to the transmission protocol used inside the NoC. Switches can be used to route traffic flows between sources and destinations. Adapters can be used to handle various conversions between data width, clock, and power domains. Buffers can be used to insert pipeline units to span long distances, or to store packets to handle rate adaptation between fast senders and slow receivers, and vice versa.

[0006] As used herein, a chip floorplan refers to a schematic representation of the tentative placement of the major functional blocks of a chip. When a NoC is implemented on a SoC, the various elements of the NoC have a location on the chip floorplan.

[0007] The NoC design may have to meet different performance requirements, such as connectivity and latency between sources and destinations, the frequency of various components, the maximum area available for NoC logic and its associated routing (wiring), the minimum throughput between sources and destinations, power consumption requirements, and the location on the chip floorplan. For chip designers, it is a difficult and time-consuming task to design a floorplan that meets multiple performance requirements with the least amount of logic and wiring. Multiple draft floorplans can be generated until different performance requirements are met. For each floorplan, the maximum area available for the NoC can change.

[0008] In the case of changing the chip floorplan, the task becomes more difficult and time-consuming. Examples of changes include modification of the chip floorplan, addition or deletion of IP components, and modification of expected performance. As a result, the task can be repeated frequently over the design time of the chip. Summary of the invention

[0009] According to an embodiment of the present invention, a computer-implemented method or floorplanning of a semiconductor chip includes loading a digital image of a first floorplan of the chip; converting the digital image to a grayscale image; detecting a block in the grayscale image; and generating a second floorplan corresponding to the first floorplan. The second floorplan shows a representation of the maximum available area of ​​the block and the NoC.

[0010] According to an embodiment of the present invention, a computer system includes a processor and a computer memory configured with a layout planning tool, wherein the layout planning tool is used to load a digital image of a first layout plan of a semiconductor chip; convert the digital image into a grayscale image; detect blocks in the grayscale image; and generate a second layout plan corresponding to the first layout plan. The second plan view shows a representation of blocks and maximum available areas of an on-chip network (NoC).

[0011] According to an embodiment of the present invention, an article of manufacture includes a computer readable memory configured with instructions that, when executed, cause a processor to load a digital image of a first floorplan of a semiconductor chip; convert the digital image to a grayscale image; detect a block in the grayscale image; and generate a second floorplan corresponding to the first floorplan. The second floorplan shows a representation of the maximum available area of ​​the block and the NoC.

[0012] The method, computer system, and article of manufacture reduce the use of computer resources for NoC planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A computer-implemented method for a chip floorplan diagram according to various aspects and embodiments of the present disclosure is shown.

[0014] Figure 2 The present disclosure shows various aspects and embodiments of the present disclosure. Figure 1 Simple example of a chip floorplan and blocks detected by our approach.

[0015] Figure 3 An interactive chip floorplanning diagram tool according to various aspects and embodiments of the present disclosure is shown.

[0016] Figure 4 A computer system according to various aspects and embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0017] Various examples of the present technology that illustrate various aspects and embodiments of the present disclosure are described below. In general, examples can use the described aspects in any combination. All statements of narration principles, aspects and embodiments and their specific examples herein are intended to cover both their structural and functional equivalents. In addition, these equivalents are intended to include currently known equivalents and equivalents developed in the future, i.e., any element developed to perform the same function, regardless of structure.

[0018] It should be noted that, as used herein, the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. Reference throughout the specification to "an aspect", "an aspect", "some aspects", "various aspects", or similar language means that a particular aspect, feature, structure, or characteristic described in connection with any embodiment is included in at least one embodiment of the present disclosure.

[0019] The appearance of the phrases "in one embodiment," "in at least one embodiment," "in an embodiment," "in certain embodiments," and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment or similar embodiments. In addition, the aspects and embodiments of the disclosure described herein are merely exemplary and should not be construed as limiting the scope or spirit of the disclosure as understood by those of ordinary skill in the art. The disclosed invention is effectively made or used in any embodiment including any novel aspect described herein. All statements describing the principles, aspects, and embodiments of the disclosure herein are intended to cover their structural and functional equivalents. These equivalents include currently known equivalents and equivalents developed in the future.

[0020] As used herein, a transaction can be a request transaction or a response transaction. Examples of request transactions include write requests and read requests.

[0021] As used herein, a node is defined as a distribution point or communication endpoint that can create, receive and / or send information on a communication path or channel. A node may refer to any of the following: a switch, a splitter, a merger, a buffer, and an adapter. As used herein, splitters and mergers are switches, but not all switches are splitters or mergers. As used herein and in accordance with various aspects and embodiments of the present disclosure, the term "splitter" describes a switch with a single inlet port and multiple outlet ports. As used herein and in accordance with various aspects and embodiments of the present disclosure, the term "merger" describes a switch with a single outlet port and multiple inlet ports.

[0022] According to various aspects of the present disclosure, a SoC includes multiple clock domains and multiple power domains. A clock domain is defined by all logic fed by a given clock input. The clock input is characterized by parameters including the clock frequency. A power domain is defined by all logic that obtains power from the same power supply. According to various aspects of the present disclosure, power supplies are gated so that power domains can be turned on or off or isolated from other power domains. Therefore, the designer provides a set of clock domain and power domain constraints as part of the initial design.

[0023] refer to Figure 1 , which shows a computer-implemented method according to various aspects and embodiments of the present disclosure. In box 110, a digital image of a first chip layout plan is loaded or presented to a design tool. The layout plan can be discretized into small square units of a given size (i.e., resolution). According to various aspects and embodiments of the present disclosure, the first chip layout plan contains the main functional blocks of the chip, including initiators and targets. According to various aspects and embodiments of the present disclosure, if the layout plan is an earlier draft, it may also include elements of the NoC.

[0024] At block 120, the digital image is converted from a color image to a grayscale image to make blockage areas ("blockage") easier to detect. Blockage refers to areas on the chip floorplan where NoC logic and its associated wiring cannot be located.

[0025] At blocks 130 and 140, blocks in the grayscale image are detected. At block 130, a custom filter may be applied to the grayscale image to highlight the edges of the main functional blocks, thereby making shape detection easier. In addition, noise shapes may be filtered.

[0026] A shape detection algorithm may then be applied to identify blocks, at block 140. At least some of the main functional blocks will be classified as blocks.

[0027] According to various aspects and embodiments of the present disclosure, a trained machine learning model can be used to replace the shape detection algorithm, allowing a neural network or artificial intelligence (AI) module to perform detection and identification. For example, a neural network or support vector machine can be trained on a block image in a chip floorplan to allow the tool to detect block areas and implement the process.

[0028] At block 150, according to aspects and embodiments of the present disclosure, a second floorplan and representation of the blocks are generated or created based on the detected geometric shapes and displayed to the user in a graphical user interface. The second floorplan corresponds to the first floorplan and shows the blocks and the maximum available area for routing and placing the NoC. The boundaries of these blocks may be represented by rectangles or other geometric shapes. The space between the geometric shapes represents the maximum available space for routing and placement to generate the NoC.

[0029] In editing the second floorplan, a digital image of the chip floorplan may be included as a background for the second floorplan at block 160. Although the representation of the blocks on the second floorplan identifies the maximum available area for placing the NoC, the background provides additional information to the NoC designer, such as the placement of specific components such as a network interface unit (NIU).

[0030] At block 170, the representation of the block may be edited by the user. The context may provide additional information about blocks or block regions that were inaccurately identified and blocks that may not have been detected. According to various aspects and embodiments of the present disclosure, the machine learning model receives feedback about these regions that were not previously detected to further train the machine learning model to detect these regions. The feedback may come from the designer, or the feedback may come from an adversarial machine learning model that provides feedback to the machine learning model to improve and train tools using the machine learning model. In addition, the NoC designer may use this additional information to edit the representation of the block.

[0031] The tool computes an estimate of the maximum available area. This estimate can be used during NoC design to ensure that the resulting NoC gates will be placeable, i.e., they will fit into the area in the floorplan allocated to the NoC.

[0032] At block 180, the NoC is added to the floorplan according to aspects and embodiments of the present disclosure. Elements of the NoC may be inserted within the maximum available space. If elements of the NoC from a previous draft exist, these elements may be moved within the maximum available area.

[0033] refer to Figure 2 , which shows a simple example of a second floorplan 210 when a NoC is added. The representation of the block 212 is represented by the shaded area. The largest available area 214 is unshaded. The elements of the NoC are located within the largest available area 214. These elements include NIU 220 and switch 222.

[0034] refer to Figure 3 , which shows an interactive software tool 300 for manipulating NoC designs. A first module 310 of the tool 300 may be configured to perform Figure 1 According to various aspects and embodiments of the present disclosure, the tool 300 includes a machine learning model as part of the first module 310.

[0035] The tool 300 may include a second module 320 that provides a fully fledged layout plan editor. According to various aspects and embodiments of the present disclosure, module 320 interacts with the machine learning model to allow and make changes to the layout plan diagram. The layout plan editor can be used to model the interior of the NoC as a set of network elements (switches, network interfaces, etc.), connections, and routes. The layout plan editor can be used to add and remove elements, update routes, etc. The layout plan editor can be used to transform the network design, which can be a basic transformation (e.g., moving a network element to a different location), or a complex transformation performed by an automated process (e.g., inserting multiple network elements at once and changing routes accordingly). According to various aspects and embodiments of the present disclosure, an adversarial machine learning model is part of module 310, and in order to further train the machine learning model, feedback is provided to the machine learning model on the layout plan diagram edits.

[0036] The floorplan editor can also be used to edit the properties of network elements. It can show the NoC designer several displays reflecting the current state of the network and a table listing the properties of network elements. In addition, tool 300 can periodically create a backup of the NoC design to a remote database via a network connection.

[0037] The tool 300 may include a third module 330 configured to enable the NoC designer to undo a previous command to restore a previous network state. A command is an object that describes a basic transformation performed on a model of a NoC or object. For example, the tool 300 may define a command to create a switch in a network. For each command object, the tool 300 has a command to undo (restore) itself. The tool 300 may generate a new command that performs the opposite action to undo.

[0038] The third module 330 may include a change list. A change list is an ordered list of commands (scripts). Complex transformations on a model may be represented by a change list that includes many commands. The change list may be restored by generating a new change list that contains the restored commands (opposite commands) in the reverse order of the original change list. According to various aspects and embodiments of the present disclosure, the information generated in the change list may be provided as input or feedback to a machine learning model.

[0039] The third module 330 may also include at least one change list interpreter. A change list interpreter is an object that knows how to process each command of a change list and interprets the command as a specific effect on a specific part of the software. Each software component (graphic view, model, network database) may embed a corresponding change list interpreter. According to various aspects and embodiments of the present disclosure, the model of the network is not modified directly.

[0040] According to various aspects and embodiments of the present disclosure, each basic transformation, transformation generated by a machine learning model, or automatic batch transformation generates a reversible change list and broadcasts it to all active change list interpreters. Each interpreter uses the change list and interprets each command in a way that has a specific effect on the corresponding software component. For example, a network database change list interpreter can generate a network transaction to communicate with the database in order to modify the field corresponding to the current command being interpreted.

[0041] According to various aspects and embodiments of the present disclosure, the change list can be stored in a stack. When the NoC designer (or a tool using AI based on a machine learning model) issues an "undo" action, the change list at the top of the stack is restored, and the restored change list is broadcast and interpreted, effectively restoring the transformations performed by the original change list.

[0042] According to various aspects and embodiments of the present disclosure, the tool 300 includes a fourth module 340 for preventing deadlock. The fourth module 340 can generate a dependency graph including routing and socket dependencies. A flow control directed graph can be constructed from the routing. Each routing segment is a node of the graph. For example, if there is a route with A and then with B, two nodes A and B are connected. For example, for the route a->b->c->d, the tool will create 3 edges or links (a->b), (b->c) and (c->d). Then, the fourth module 340 can create two segments (a->b) to (b->c) and (b->c) to (c->d). According to various aspects and embodiments of the present disclosure, the tool uses AI based on a trained machine learning model to determine the route. The effectiveness of the route determination is provided as feedback to further train the AI.

[0043] The initiator (the first node of the route) and the target (the last node of the route) can be linked to a socket, and the socket has a list of other sockets as dependencies. According to aspects and embodiments of the present disclosure, the fourth module 340 can create segments in the flow control graph to link the topology segments from the target to all topology segments from the initiator that are linked to the socket in the dependency list. The fourth module 340 can create these dependencies only for the requesting network. If there is a loop in the flow control graph, the fourth module 340 can determine that there is a deadlock.

[0044] According to various aspects and embodiments of the present disclosure, the tool 300 may include a fifth module 350 for converting a network so as to reduce the number of wires used between switches while maintaining performance requirements (e.g., minimum throughput between initiators and targets). According to various aspects and embodiments of the present disclosure, any master switch or node in a NoC design may be decomposed into a cascade of splitters, each of which is placed at a branch point of a routing graph. Any master switch may be further decomposed into a cascade of mergers, each of which is placed at a branch point of a merged routing graph of an additional target. The branch point of a routing graph is defined by the fact that a path is divided into two or more branches. The process of decomposing a splitter in a splitter cascade retains the original splitter function, because the number of inputs to the cascade is still 1, and the number of outputs of the cascade is the same as the number of outputs of the original splitter. The process of decomposing a merger in a merger cascade retains the original merger function, because the number of outputs of the cascade is still 1, and the number of inputs of the cascade is the same as the number of inputs of the original merger. The effect of this process, in accordance with various aspects of the present disclosure, is to obtain a set of basic switches, represented by combiners and splitters, placed physically close to where actual connections between switches are needed.

[0045] An expansion of the clock and power domains on the floorplan is provided, and each component is tested to ensure that it is within the boundaries of the specified clock and power domains. If the test fails, the component is moved until an appropriate location is found where the test passes. Once a suitable location is found for each component, each connection between the components is routed. The routing process will find a suitable path for the group of wires that form the connection between the components. After routing is completed, if necessary, pipeline elements that span the distance are inserted on the link using the information provided about the technology capabilities based on how long it takes for the signal to cover the specified distance.

[0046] Wiring reduction is described in more detail in assignee's U.S. Patent No. 11,121,933 (application serial number No. 16 / 728,335), which was published on September 14, 2021 in the name of Moez Cherif et al., the entire disclosure of which is incorporated herein by reference.

[0047] The tool 300 may include a sixth module 360 ​​for providing information about the generated NoC. The information may include a list of network elements with their configuration (e.g., data width, clock domain); the location of each generated network element on the floorplan; and a set of routes through the network elements that implement connectivity. As used herein, a route is an ordered list of network elements, one network element per pair (initiator, target), and one network element per pair (target, initiator). Routes represent how traffic between pairs will flow and through which units.

[0048] The information may also include metrics about the generated NoC. Examples of metrics may include a histogram of line length distribution, the number of switches, and a histogram of switch sizes.

[0049] The sixth module 360 ​​can provide information in a computer file in a well-defined format to capture information. An example of such a format is XML. Another example of such a format is JSON.

[0050] Reference now Figure 4, which shows elements of a computer system 410 configured with an interactive design tool 300 according to various aspects and embodiments of the present disclosure. The computer system 410 includes a processing unit 420 and a computer readable memory 430. The computer readable memory 430 stores the tool 300 in the form of executable instructions, which, when executed, cause the processing unit 420 to perform various functions of the tool 300. The tool 300 interacts with or may include a graphical user interface for selecting each module 310 to 360. For example, when the first module 310 is selected, the processing unit 420 receives a digital image of a chip floorplan from a network (via a network interface 440). According to various aspects and embodiments of the present disclosure, the machine learning model guides the processing unit 420, and it loads the digital image, converts the digital image to a grayscale image, detects blocks in the grayscale image, and generates and visually displays (on a display 450) a floorplan showing a representation of the block. According to various aspects and embodiments of the present disclosure, the AI ​​of the tool 300 edits or modifies the NoC design. According to various aspects and embodiments of the present disclosure, the displayed floorplan diagram can be edited by the designer to further add or modify the NoC, and the edits are provided to the machine learning model as feedback for training the AI ​​using the machine learning model.

[0051] Certain methods according to aspects of the present disclosure may be performed by instructions stored on a non-transitory computer-readable medium. The non-transitory computer-readable medium stores code including instructions that, when executed by one or more processors, will cause a system or computer to perform the steps of the methods described herein. Examples of the non-transitory computer-readable medium include: a rotating magnetic disk, a rotating optical disk, a flash random access memory (RAM) chip, and other mechanically movable or solid-state storage media. Any type of computer-readable medium is suitable for storing code including instructions according to the various examples.

[0052] Certain examples have been described herein, and it will be noted that different combinations of different components from different examples are possible. Highlighted features are given to better explain the examples; however, it is apparent that certain features may be added, modified and / or omitted without modifying the functional aspects of the examples described.

[0053] Various examples are methods of behavior using one of the machines or a combination thereof. Method examples are complete anywhere in the world where most of the constituent steps occur. For example, according to various aspects and embodiments of the present disclosure, IP elements or units include: processors (e.g., CPUs or GPUs), RAM (e.g., off-chip dynamic RAM or DRAM), network interfaces for wired or wireless connections (e.g., Ethernet, Wi-Fi, 3G, 4G Long Term Evolution (LTE), 5G), and other wireless interface standard radios. The IP may also include various I / O interface devices required for different peripherals, such as touch screen sensors, geolocation receivers, microphones, speakers, Bluetooth peripherals, and USB devices, such as keyboards and mice, etc.

[0054] Some examples are one or more non-transitory computer-readable media arranged to store such instructions for the methods described herein. An example can be implemented regardless of what machine holds the non-transitory computer-readable medium including any necessary code. Some examples can be implemented as: physical devices such as semiconductor chips; hardware description language representations of the logical or functional behavior of such devices; and one or more non-transitory computer-readable media arranged to store such hardware description language representations. The description of the principles, aspects, and embodiments described herein covers both their structural and functional equivalents. Elements described herein as coupled have an effective relationship that can be achieved by direct connection or indirectly with one or more other intermediate elements.

[0055] Those skilled in the art will recognize many modifications and variations. Modifications and variations include any relevant combination of the disclosed features. The description of the principles, aspects, and embodiments described herein encompasses both structural and functional equivalents thereof. Elements described herein as "coupled" or "communicatively coupled" have an effective relationship that can be achieved by direct or indirect connection using one or more other intermediate elements. Embodiments described herein as "communicating" or "communicating with" another device, module, or element include any form of communication or link and include an effective relationship. For example, a wired connection, a wireless protocol, a near field protocol, or an RFID can be used to establish a communication link.

[0056] To the extent that the terms "includes," "comprising," "has," "possessing," "having," or variations thereof are used in the detailed description and claims, these terms are intended to be inclusive in a manner similar to the term "comprising."

[0057] Therefore, the scope of the present disclosure is not limited to the exemplary embodiments shown and described herein. Rather, the scope and spirit of the present disclosure are embodied by the appended claims.

Claims

1. A computer-implemented method for performing layout planning on a semiconductor chip, the method comprising: Loading a digital image of a first layout plan of the chip; converting the digital image into a grayscale image; Detecting blocks in the grayscale image; as well as A second floorplan is generated corresponding to the first floorplan, the second floorplan showing a representation of the block and a maximum available area for a network on chip (NoC). 2 . The method of claim 1 , wherein detecting the block comprises filtering the grayscale image to highlight edges of major functional blocks of the chip.

3. The method of claim 2, wherein detecting the blocks further comprises using an algorithm or a trained machine learning model to classify at least some of the main functional blocks as blocks. 4 . The method of claim 1 , wherein the second floorplan illustrates at least some representations of the blocks without illustrating initiators and targets of the first floorplan.

5. The method of claim 4, further comprising superimposing the second floorplan over the digital image of the first floorplan to display the initiator and the target within the representations of the volumes of the initiator and the target. The method of claim 1 , further comprising editing the second floorplan to generate the NoC within the maximum available area.

7. A computer system comprising a processor and a computer memory configured with a chip layout planning tool, wherein the chip layout planning tool is used to load a digital image of a first layout planning diagram of a semiconductor chip; convert the digital image into a grayscale image; detect blocks in the grayscale image; and generate a second layout planning diagram corresponding to the first layout planning diagram, wherein the second layout planning diagram shows the blocks and the maximum available area for an on-chip network (NoC). 8 . The system of claim 7 , wherein detecting the blocks comprises filtering the grayscale image to highlight edges of major functional blocks of the chip.

9. The system of claim 8, wherein detecting the blocks further comprises using an algorithm or a trained machine learning model to classify at least some of the main functional blocks as blocks.

10. The system of claim 7, wherein the second floorplan shows a representation of the block without showing an initiator and a target of the first floorplan. 11 . The system of claim 10 , wherein the chip floorplan tool is configured to overlay the second floorplan diagram on the digital image of the first floorplan diagram to display the initiator and the target within the representation of the block.

12. The system of claim 7, wherein the computer memory is further configured with a chip floorplanning editor for generating a NoC within the maximum available area.

13. A non-transitory computer readable memory configured with instructions that, when executed, cause a processor to: loading a digital image of a first layout plan of a semiconductor chip; converting the digital image into a grayscale image; detecting blocks in the grayscale image; and A second floorplan is generated corresponding to the first floorplan, the second floorplan showing a representation of the block and a maximum available area for a network on chip (NoC). 14 . The non-transitory computer readable memory of claim 13 , wherein detecting the block comprises filtering the grayscale image to highlight edges of major functional blocks of the chip.

15. The non-transitory computer readable memory of claim 14, wherein detecting the blocks further comprises using an algorithm or a trained machine learning model to classify at least some of the primary functional blocks as blocks.

16. The non-transitory computer readable memory of claim 13, wherein the second floorplan shows representations of the blocks without showing initiators and targets of the first floorplan.

17. The non-transitory computer readable memory of claim 16, wherein the computer readable memory is further configured with additional instructions that, when executed, cause the processor to superimpose the second floorplan over the digital image of the first floorplan to display the initiator and the target within the representation of the block.

18. The non-transitory computer readable memory of claim 13, wherein the computer readable memory is further configured with additional executable instructions that, when executed, cause the processor to provide a chip floorplanning editor for adding a NoC to the maximum available area.