In the physical synthesis of integrated circuits the legalization step may move all circuit cells to fix overlaps and misalignments. While doing so, it should cause the smallest perturbation possible to the solution found by previous optimization steps to preserve placement quality. Legalization techniques must handle circuits with millions of cells within acceptable runtimes, besides facing other issues such as mixed-cell-height and fence regions. In this work we propose a k-d tree data structure to partition the circuit, thus removing data dependency. Then, legalization is sped up through both input size reduction and parallel execution. As a use case we employed a modified version of the classic legalization algorithm Abacus. Our solution achieved a maximum speedup of 35 times over a sequential version of Abacus for the circuits of the ICCAD2015 CAD contest. It also provided up to 10% reduction on the average cell displacement.

Machine learning has been used to improve the predictability of different physical design problems, such as timing, clock tree synthesis and routing, but not for legalization. Predicting the outcome of legalization can be helpful to guide incremental placement and circuit partitioning, speeding up those algorithms. In this work we extract histograms of features and snapshots of the circuit from several regions in a way that the model can be trained independently from region size. Then, we evaluate how traditional and convolutional deep learning models use this set of features to predict the quality of a legalization algorithm without having to executing it. When evaluating the models with holdout cross validation, the best model achieves an accuracy of 80% and an F-score of at least 0.7. Finally, we used the best model to prune partitions with large displacement in a circuit partitioning strategy. Experimental results in circuits (with up to millions of cells) showed that the pruning strategy improved the maximum displacement of the legalized solution by 5% to 94%. In addition, using the machine learning model avoided from 22% to 99% of the calls to the legalization algorithm, which speeds up the pruning process by up to 3×.

Machine learning models have been used to improve the quality of different physical design steps, such as timing analysis, clock tree synthesis and routing. However, so far very few works have addressed the problem of algorithm selection during physical design, which can drastically reduce the computational effort of some steps. This work proposes a legalization algorithm selection framework using deep convolutional neural networks. To extract features, we used snapshots of circuit placements and used transfer learning to train the models using pre-trained weights of the Squeezenet architecture. By doing so we can greatly reduce the training time and required data even though the pre-trained weights come from a different problem. We performed extensive experimental analysis of machine learning models, providing details on how we chose the parameters of our model, such as convolutional neural network architecture, learning rate and number of epochs. We evaluated the proposed framework by training a model to select between different legalization algorithms according to cell displacement and wirelength variation. The trained models achieved an average F-score of 0.98 when predicting cell displacement and 0.83 when predicting wirelength variation. When integrated into the physical design flow, the cell displacement model achieved the best results on 15 out of 16 designs, while the wirelength variation model achieved that for 10 out of 16 designs, being better than any individual legalization algorithm. Finally, using the proposed machine learning model for algorithm selection resulted in a speedup of up to 10x compared to running all the algorithms separately.