A specification for a modular circuit design includes a mapping from global clock domains to global voltage domains. A processor assigns, to a first instance of a clocked primitive component, a global voltage domain based on which global clock domain clocks the first instance, automatically adds, to the modular circuit design, first power supply rails to power the first instance, and connects the first power supply rails from the first instance to a first power supply for a first global voltage domain. The processor assigns, to a second instance of the clocked primitive component, a second global voltage domain based on which global clock domain clocks the second instance, automatically adds second power supply rails to power the second instance, and connects the second power supply rails to a second power supply for a second global voltage domain. The processor may perform further processing on the updated modular circuit design.

A machine learning (ML) system is trained to predict the number of design rules violations of a circuit design that includes a multitude of Gcells. To achieve this, a netlist associated with the circuit design is placed by a place and route tool. A first list of features associated with the placed netlist is delivered to the ML system. A global route of the circuit design is performed by a global router. Next, a second list of features is delivered from the global router to the ML system. Thereafter, a detailed route of the circuit design is performed by a detailed router. A label associated with each Gcell in the circuit design is delivered to the ML system from the detailed route. The ML system is trained using the first and second list of features and the labels.

A machine learning (ML) system is trained to predict the number of design rules violations of a circuit design that includes a multitude of Gcells. To achieve this, a netlist associated with the circuit design is placed by a place and route tool. A first list of features associated with the placed netlist is delivered to the ML system. A global route of the circuit design is performed by a global router. Next, a second list of features is delivered from the global router to the ML system. Thereafter, a detailed route of the circuit design is performed by a detailed router. A label associated with each Gcell in the circuit design is delivered to the ML system from the detailed route. The ML system is trained using the first and second list of features and the labels.

A method for automatically creating a global routing solution for an integrated circuit. The method includes generating n original population of GR solutions. In one or more subsequent phases the method generates succeeding populations of GR solutions. The generation of each succeeding population includes determining a plurality of base GR solutions from the current population of GR solutions, determining a plurality of DRC hotspot areas within the plurality of base GR solutions, determining a plurality of patching GR solutions from which patches may be extracted, and hybridizing patching of GR solutions into base GR solutions.

A method for automatically creating a global routing solution for an integrated circuit. The method includes generating n original population of GR solutions. In one or more subsequent phases the method generates succeeding populations of GR solutions. The generation of each succeeding population includes determining a plurality of base GR solutions from the current population of GR solutions, determining a plurality of DRC hotspot areas within the plurality of base GR solutions, determining a plurality of patching GR solutions from which patches may be extracted, and hybridizing patching of GR solutions into base GR solutions.

Methods, systems, and devices are disclosed for automatically generating physical layouts of integrated circuits. A circuit is partitioned into one or more cells based on a circuit description. The method further checks availability of a layout of a cell for all the cells generated during the partition step. If a layout of a cell is not available, the method generates a layout of the cell by an automatic tool, and packages the generated layout in a form of a standard cell compatible with a standard cell placement and routing tool. Afterwards, the generated layout may be exported to the standard cell placement and routing tool. Finally, the standard cell placement and routing tool may merge individual layouts of the one or more cells of the circuit to generate a layout for the circuit.

Test line structures are provided. A test line structure includes a semiconductor substrate, a plurality of diagnosis units and a plurality of first micro pad units. The diagnosis units are formed over the semiconductor substrate. Each of the diagnosis units includes a first interconnect structure having a first routing pattern. The first interconnect structures of the diagnosis units are connected in series to form a first test chain through the first micro pad units, and each of the first micro pad units is configured to connect the first interconnect structures of two adjacent diagnosis units in the first test chain. The first routing patterns of the first interconnect structures in the diagnosis units are different.

Test line structures are provided. A test line structure includes a semiconductor substrate, a plurality of diagnosis units and a plurality of first micro pad units. The diagnosis units are formed over the semiconductor substrate. Each of the diagnosis units includes a first interconnect structure having a first routing pattern. The first interconnect structures of the diagnosis units are connected in series to form a first test chain through the first micro pad units, and each of the first micro pad units is configured to connect the first interconnect structures of two adjacent diagnosis units in the first test chain. The first routing patterns of the first interconnect structures in the diagnosis units are different.

On-the-fly multi-bit flip-flop (MBFF) generation is provided by selecting at least two flip-flop blocks from a plurality of candidate flip-flop blocks; identifying a control block from a plurality of candidate control blocks, the control block being identified based on operational specifications of the selected flip-flop blocks; and generating a multi-bit flip-flop instance based on the selected flip-flop blocks and the identified control block.

On-the-fly multi-bit flip-flop (MBFF) generation is provided by selecting at least two flip-flop blocks from a plurality of candidate flip-flop blocks; identifying a control block from a plurality of candidate control blocks, the control block being identified based on operational specifications of the selected flip-flop blocks; and generating a multi-bit flip-flop instance based on the selected flip-flop blocks and the identified control block.