Abstract: The present disclosure relates to electronic circuit design, and more specifically, to training a neural network to serve as the reward function for optimization-based approaches to PCB design automation. Embodiments may include generating, using a processor, one or more placed designs using a genetic optimization methodology including a reward function and adjusting the one or more placed designs and the reward function during the generating. Embodiments may further include routing the one or more placed designs using an auto-router to assign a routability score label and training a neural network, using the one or more placed designs and the routability score label, to extract one or more intermediate features from the one or more placed designs. Embodiments may also include predicting a routability of the PCB design based upon, at least in part, the one or more intermediate features.

Abstract: The present disclosure relates to applying genetic optimization to a routing strategy associated with an electronic design. Embodiments may include receiving pin and net information from an electronic design file and determining a minimum spanning tree for all pins associated with each net. Embodiments may include identifying pairs of connected pins and representing the pins as at least one line segment without layer information. Embodiments may include generating a crossing map based upon the line segments and assigning random layer information to each of the line segments. Embodiments may further include performing crossover and mutation operations to the line segments using hyperparameters and evaluating a fitness of the line segments. Embodiments may also include instantiating vias based upon a layer to which the line segment was assigned.

Abstract: The present disclosure relates to systems and methods for floorplanning using machine learning techniques. Embodiments may include receiving an electronic design and analyzing the electronic design using a reinforcement learning agent. Embodiments may further include recommending a first action wherein the first action includes at least one of a place agent action, a via agent action, or a route agent action. Embodiments may also include updating the electronic design based upon, at least in part, the first action to generate an updated electronic design. Embodiments may further include analyzing the updated electronic design using the reinforcement learning agent and recommending a second action wherein the second action includes at least one of a place agent action, a via agent action, or a route agent action. Embodiments may also include updating the updated electronic design based upon the second action to generate a second updated electronic design.