Pre-characterization mixed-signal design, placement, and routing using machine learning
Systems, methods, and devices are disclosed herein for developing a cell design. Operations of a plurality of electrical cells are simulated to collect a plurality of electrical parameters. A machine learning model is trained using the plurality of electrical parameters. The trained machine learning model receives data having cell layout design constraints. The trained machine learning model determines a cell layout for the received data based on the plurality of electrical parameters. The cell layout is provided for further characterization of electrical performance within the cell layout design constraints.
1. A computer-implemented method comprising:
simulating operations of a plurality of electrical cells to collect a plurality of electrical parameters;
training a machine learning model using the plurality of electrical parameters;
receiving, by the trained machine learning model, data comprising cell layout design constraints;
determining, by the trained machine learning model, a cell layout for the received data based on the plurality of electrical parameters by:
positioning at least two electrical cells of the plurality of electrical cells within the cell layout; and
generating at least transition cells surrounding the at least two electrical cells, each transition cell surrounding an electrical cell; and
providing the cell layout for further characterization of electrical performance within the cell layout design constraints.
2. The computer-implemented method of claim 1 , wherein the simulating further comprises:
simulating, at a first time, operations of a first electrical cell under a first set of operational conditions to determine a first set of electrical parameters; and
simulating, at a second time, operations of a second electrical cell under a second set of operational conditions to determine a second set of electrical parameters,
wherein the plurality of electrical cells comprises the first electrical cell and the second electrical cell and the plurality of electrical parameters comprises the first set of electrical parameters and the second set of electrical parameters.
3. The computer-implemented method of claim 1 , wherein the simulating further comprises simultaneously simulating operations of the plurality of electrical cells.
4. The computer-implemented method of claim 1 , wherein the cell layout comprises metal routing of one or more metal lines and the plurality of electrical parameters comprises at least one of: metal spacing, metal width, metal direction, a pin name, a voltage, a current, a mismatch, or a delta voltage.
5. The computer-implemented method of claim 1 , wherein the cell layout is an analog cell layout.
6. The computer-implemented method of claim 1 , wherein an empty region exists between the at least two transition cells.
7. The computer-implemented method of claim 6 , wherein the at least two analog cells are positioned horizontally with respect to each other.
8. The computer-implemented method of claim 6 , wherein the at least two analog cells are positioned vertically with respect to each other.
9. The computer-implemented method of claim 6 , wherein the empty region comprises a width less than about 100 nanometers.
10. The computer-implemented method of claim 6 , further comprising generating metal routing on top of the at least two transition cells.
11. A computer-implemented method comprising:
receiving, by a trained machine learning model, data comprising cell layout design constraints, wherein the trained machine learning model is trained using a plurality of electrical parameters collected by simulated operations of a plurality of electrical cells;
determining, by the trained machine learning model, a cell layout for the received data based on the plurality of electrical parameters by:
positioning at least two electrical cells of the plurality of electrical cells within the cell layout; and
generating at least transition cells surrounding the at least two electrical cells, each transition cell surrounding an electrical cell; and
providing the cell layout for further characterization of electrical performance within the cell layout design constraints.
12. The computer-implemented method of claim 11 , wherein the simulated operations comprises:
simulating, at a first time, operations of a first electrical cell under a first set of operational conditions to determine a first set of electrical parameters; and
simulating, at a second time, operations of a second electrical cell under a second set of operational conditions to determine a second set of electrical parameters,
wherein the plurality of electrical cells comprises the first electrical cell and the second electrical cell and the plurality of electrical parameters comprises the first set of electrical parameters and the second set of electrical parameters.
13. The computer-implemented method of claim 11 , wherein the simulated operations further comprises simultaneously simulating operations of the plurality of electrical cells.
14. The computer-implemented method of claim 11 , wherein the cell layout comprises metal routing of one or more metal lines and the plurality of electrical parameters comprises at least one of: metal spacing, metal width, metal direction, a pin name, a voltage, a current, a mismatch, or a delta voltage.
15. The computer-implemented method of claim 11 , wherein the cell layout is an analog cell layout.
16. The computer-implemented method of claim 11 , further comprising:
generating metal routing on top of the at least two transition cells, wherein an empty region exists between the at least two transition cells.
17. The computer-implemented method of claim 15 , wherein the at least two analog cells are positioned horizontally with respect to each other.
18. The computer-implemented method of claim 15 , wherein the at least two analog cells are positioned vertically with respect to each other.
19. The computer-implemented method of claim 15 , wherein the empty region comprises a width less than about 100 nanometers.
20. A computer-implemented method comprising:
simulating operations of a plurality of electrical cells to collect a plurality of electrical parameters; and
training a machine learning model using the plurality of electrical parameters, wherein the trained machine learning model is used to generate a cell layout based on the plurality of the electrical parameters and cell layout design constraints, wherein the cell layout is generated by:
positioning at least two electrical cells of the plurality of electrical cells within the cell layout; and
generating at least transition cells surrounding the at least two electrical cells, each transition cell surrounding an electrical cell.