Search

CN-121986341-A - Custom layout recommendation using machine learning

CN121986341ACN 121986341 ACN121986341 ACN 121986341ACN-121986341-A

Abstract

A processing device obtains an input (302), wherein the input specifies a set of devices to be placed and routed for a circuit design. In response to the input, the processing device executes a machine learning model (304) to calculate a probability distribution function over a library of historian placements that estimates suitability of each historian placement in the library of historian placements for placement and routing of the set of devices specified in the input. The processing device presents (306) a graphical representation of a defined number of historic device placements from the library of historic device placements estimated to be suitable for placement and routing of the set of devices based on the probability distribution function.

Inventors

  • S. Batriwala
  • P. Patil
  • NAIR ANIL

Assignees

  • 新思科技有限公司

Dates

Publication Date
20260505
Application Date
20240925
Priority Date
20230927

Claims (15)

  1. 1. A method, comprising: obtaining, by a processing device, an input, wherein the input specifies a set of devices to be placed and routed for a circuit design; Executing, by the processing device and in response to the input, a machine learning model to calculate probability distribution functions over a library of historian placements that estimate suitability of each historian placement in the library of historian placements for placement and routing of the set of devices specified in the input, and A graphical representation of a defined number of historic device placements from the library of historic device placements estimated to be suitable for placement and routing of the set of devices based on the probability distribution function is provided by the processing device.
  2. 2. The method of claim 1, wherein the input comprises a vector, and the vector concatenates, for each device in the set of devices to be placed and routed, a digital tuple of values representing attributes of the each device and a digital identifier representing a unique connection graph of connectivity of the each device.
  3. 3. The method of claim 2, wherein the attribute comprises at least one of whether the each device is an n-type metal oxide semiconductor device or a p-type metal oxide semiconductor device, a total channel width of the each device, a channel length of the each device, a number of fingers in the each device, a multiplier of the each device, or a number of vector bits in the each device.
  4. 4. The method of claim 2, wherein the vector is automatically constructed by the processing device when the processing device detects that a placement tool has been launched on the set of devices and the set of devices has not been placed or routed.
  5. 5. The method of claim 1, wherein the machine learning model comprises a sequential neural network that has been trained on a plurality of data points, and wherein each of the data points represents a historian placement from the historian placement library and a set of historians corresponding to the historian placement from the historian placement library.
  6. 6. The method of claim 1, wherein each historian placement in the library of historian placements comprises a device placement corresponding to a circuit design whose device placement was submitted at a time prior to the acquisition.
  7. 7. The method of claim 1, wherein the providing further comprises providing, for each of the defined number of historic device placements, at least one of a device match metric or a netlist match metric, wherein the device match metric comprises a percentage indicating a degree of match between a device of the set of devices specified in the input and a device of the each of the defined number of historic device placements, and wherein the netlist match metric comprises a percentage indicating a degree of match between a graph of a netlist corresponding to the set of devices specified in the input and a graph of a netlist corresponding to the each of the defined number of historic device placements.
  8. 8. The method as recited in claim 1, further comprising: receiving, by the processing device, a signal indicative of a user selection of one of the defined number of historian placements, and Loading, by the processing device, the one of the defined number of historian placements in a symbol editor canvas of the circuit design in response to the signal.
  9. 9. The method of claim 1, wherein the performing comprises filtering the historian placement library to remove any historian placement in the historian placement library that a user has indicated should not be considered from consideration by the machine learning model.
  10. 10. A system, comprising: a memory storing instructions, and A processing device coupled with the memory and executing the instructions that, when executed, cause the processing device to: building a historical device placement library, wherein each data point in the library comprises a set of devices for circuit design and historical device placements generated for the set of devices, and A machine learning model is trained using the historian placement library to calculate probability distribution functions over the historian placement library that estimate suitability of each historian placement in the historian placement library for placement and routing of a set of devices for a new circuit design.
  11. 11. The system of claim 10, wherein at least one data point in the library is automatically collected in response to the processing device detecting that a user of a simulation design tool has submitted a new placement into a main layout of a circuit design being developed.
  12. 12. The system of claim 10, wherein the machine learning model comprises a sequential neural network model.
  13. 13. A non-transitory computer-readable medium comprising stored instructions that, when executed by a processing device, cause the processing device to: Obtaining an input, wherein the input specifies a set of devices to be placed and routed for a circuit design; Executing a machine learning model in response to the input to calculate a probability distribution function over a library of historian placeholders that estimates suitability of each historian placement in the library for placement and routing of the set of devices specified in the input, and A graphical representation of a defined number of historian placements from the library of historian placements estimated to be suitable for placement and routing of the set of devices based on the probability distribution function is provided.
  14. 14. The non-transitory computer-readable medium of claim 13, wherein the instructions further cause the processing device to filter the historian placement library to remove any historian placements that a user has indicated should not be considered from consideration by the machine learning model.
  15. 15. The non-transitory computer-readable medium of claim 13, wherein the machine learning model comprises a sequential neural network that has been trained on a plurality of data points, and wherein each of the plurality of data points represents a historian placement from the historian placement library and a set of historian corresponding to the historian placement from the historian placement library.

Description

Custom layout recommendation using machine learning Technical Field The present disclosure relates generally to electronic design automation, and more particularly to machine learning-based techniques for recommending custom layouts for simulated designs. Background Analog designs consist of well-defined building blocks representing devices such as differential pairs, current mirrors, custom digital cells, amplifiers, and the like. These devices are captured in a schematic design from which a netlist is extracted and used for simulation in order to ensure that the design meets specifications. Next, a layout of the schematic design is created, in which devices are placed and routed, and simulation is performed from the post-layout netlist with parasitics. The placement and routing of devices in a layout can be refined until the post-layout simulation meets design specifications. Disclosure of Invention In one example, a processing device may obtain an input, where the input specifies a set of devices to be placed and routed for a circuit design. In response to the input, the processing device may execute a machine learning model to calculate a probability distribution function over a library of historian placements that estimates suitability of each historian placement in the library of historian placements for placement and routing of the set of devices specified in the input. The processing device may present a graphical representation of a defined number of historic device placements from the library of historic device placements estimated to be suitable for placement and routing of the set of devices based on the probability distribution function. In another example, a system may include a memory storing instructions and a processing device coupled with the memory and executing the instructions. The instructions, when executed, cause the processing device to construct a historian placement library, wherein each data point in the library includes a set of devices for circuit design and historian placements generated for the set of devices. The instructions may further cause the processing device to train a machine learning model using the historian placement library to calculate a probability distribution function over the historian placement library that estimates suitability of each historian placement in the historian placement library for placement and routing of a set of devices of a new circuit design. In another example, a non-transitory computer-readable medium may include stored instructions. The stored instructions, when executed by a processing device, may cause the processing device to obtain an input, where the input specifies a set of devices to be placed and routed for a circuit design. In response to the input, the processing device may execute a machine learning model to compute as output a probability distribution function over a library of historian placements that estimates suitability of each historian placement in the library of historian placements for placement and routing of the set of devices specified in the input. The processing system may then present, via a graphical user interface, a graphical representation of a predefined number of historic device placements from the library of historic device placements estimated to be most suitable for placement and routing of the set of devices based on the probability distribution function. Drawings The present disclosure will be understood more fully from the detailed description given below and from the accompanying drawings of embodiments of the disclosure. The drawings are intended to provide an understanding and appreciation of the embodiments of the disclosure and are not to be construed as limiting the scope of the disclosure to these particular embodiments. In addition, the figures are not necessarily drawn to scale. FIG. 1 illustrates an example method for training a machine learning model to recommend custom layouts for a simulated design in accordance with this disclosure. FIG. 2 illustrates an example sequential neural network that has been trained to receive as input a set of devices to be placed and routed for custom designs and to calculate as output probability distribution functions over a library of historic device placements that estimate the suitability of each historic device placement in the library of historic device placements for placing and routing the set of devices that are input. FIG. 3 illustrates an example method for recommending historical device placement for placement and routing of a set of devices for a new custom design using machine learning. Fig. 4 illustrates a flow chart of various processes used during design and manufacture of an integrated circuit, according to some embodiments of the present disclosure. FIG. 5 illustrates a diagram of an example computer system in which embodiments of the present disclosure may operate. Detailed Description Aspects of the present disclosure relate to machin