Process aware compact representation of integrated circuits
A technique for designing circuits including receiving a data object representing a circuit for a first process technology, the circuit including a first sub-circuit, the first sub-circuit including a first electrical component and a second electrical component arranged in a first topology; identifying the first sub-circuit in the data object by comparing the first topology to a stored topology, the stored topology associated with the first process technology; identifying a first set of physical parameter values associated with first electrical component and the second electrical component of the first sub-circuit; determining a set of performance parameter values for the first sub-circuit based on a first machine learning model of the first sub-circuit and the identified set of physical parameters; converting the identified first sub-circuit to a second sub-circuit for the second process technology based on the determined set of performance parameter values; and outputting the second sub-circuit.
1. A method comprising:
receiving a first set of sub-circuit physical parameters for electrical components of a sub-circuit, and an indication of a first process technology;
determining a first variation of sub-circuit physical parameters for the electrical components of the sub-circuit, the first variation including at least one sub-circuit physical parameter that vary from sub-circuit physical parameters of the first set of sub-circuit physical parameters;
simulating the first variation of sub-circuit physical parameters in the first process technology to generate a first set of sub-circuit performance parameter values associated with the first variation;
training a machine learning (ML) model of the sub-circuit based on a set of variations, the set of variations including the first variation and set of sub-circuit physical parameters associated with the first variation, for the first process technology; and
storing the trained ML model.
2. The method of claim 1 , wherein determining the first variation of sub-circuit physical parameters for the electrical components of the sub-circuit is based on a practical range of sub-circuit physical parameter values for the first process technology.
3. The method of claim 1 , wherein the ML model of the sub-circuit comprises one of a linear regression, large margin classifier, principle component analysis, tree based, or neural network machine learning model.
4. The method of claim 1 , wherein training the ML model includes identifying a set of variables for input to the ML model.
5. The method of claim 4 , wherein the set of variables for input to the ML model is based on:
one of: the sets of sub-circuit physical parameters or generated sub-circuit performance parameters, and
one of: the one or more parameters associated with the first process technology or one or more parameters associated with a second process technology.
6. The method of claim 1 , wherein the sets of variations of sub-circuit physical parameters are identified to show non-linear behavior of the sub-circuit.
7. The method of claim 1 , wherein sets of variations of sub-circuit physical parameters for the sub-circuit are simulated using a simulation program with integrated circuit emphasis (SPICE) circuit model of the sub-circuit.
8. The method of claim 1 , wherein the trained ML model of the sub-circuit is stored in a library of trained ML models for the first process technology.
9. The method of claim 8 , wherein the library of trained ML models includes a trained ML model for each structural sub-circuit of a set of predetermined structural sub-circuits.
10. A non-transitory program storage device comprising instructions stored thereon to cause one or more processors to:
receive a first set of sub-circuit physical parameters for electrical components of a sub-circuit, and an indication of a first process technology;
determine a first variation of sub-circuit physical parameters for the electrical components of the sub-circuit, the first variation including at least one sub-circuit physical parameter that vary from sub-circuit physical parameters of the first set of sub-circuit physical parameters;
simulate the first variation of sub-circuit physical parameters in the first process technology to generate a first set of sub-circuit performance parameter values associated with the first variation;
train a machine learning (ML) model of the sub-circuit based on a set of variations, the set of variations including the first variation and set of sub-circuit physical parameters associated with the first variation, for the first process technology; and
store the trained ML model.
11. The non-transitory program storage device of claim 10 , wherein determining the first variation of sub-circuit physical parameters for the electrical components of the sub-circuit is based on a practical range of sub-circuit physical parameter values for the first process technology.
12. The non-transitory program storage device of claim 10 , wherein the ML model of the sub-circuit comprises one of a linear regression, large margin classifier, principle component analysis, tree based, or neural network machine learning model.
13. The non-transitory program storage device of claim 10 , wherein training the ML model includes identifying a set of variables for input to the ML model.
14. The non-transitory program storage device of claim 13 , wherein the set of variables for input to the ML model is based on:
one of: the sets of sub-circuit physical parameters or generated sub-circuit performance parameters, and
one of: the one or more parameters associated with the first process technology or one or more parameters associated with a second process technology.
15. The non-transitory program storage device of claim 10 , wherein the sets of variations of sub-circuit physical parameters are identified to show non-linear behavior of the sub-circuit.
16. The non-transitory program storage device of claim 10 , wherein sets of variations of sub-circuit physical parameters for the sub-circuit are simulated using a simulation program with integrated circuit emphasis (SPICE) circuit model of the sub-circuit.
17. The non-transitory program storage device of claim 10 , wherein the trained ML model of the sub-circuit is stored in a library of trained ML models for the first process technology.
18. The non-transitory program storage device of claim 17 , wherein the library of trained ML models includes a trained ML model for each structural sub-circuit of a set of predetermined structural sub-circuits.
19. An electronic device, comprising:
a memory; and
one or more processors operatively coupled to the memory, wherein the one or more processors are configured to execute instructions causing the one or more processors to:
receive a first set of sub-circuit physical parameters for electrical components of a sub-circuit, and an indication of a first process technology;
determine a first variation of sub-circuit physical parameters for the electrical components of the sub-circuit, the first variation including at least one sub-circuit physical parameter that vary from sub-circuit physical parameters of the first set of sub-circuit physical parameters;
simulate the first variation of sub-circuit physical parameters in the first process technology to generate a first set of sub-circuit performance parameter values associated with the first variation;
train a machine learning (ML) model of the sub-circuit based on a set of variations, the set of variations including the first variation and set of sub-circuit physical parameters associated with the first variation, for the first process technology; and
store the trained ML model.
20. The electronic device of claim 19 , wherein determining the first variation of sub-circuit physical parameters for the electrical components of the sub-circuit is based on a practical range of sub-circuit physical parameter values for the first process technology.