“Smart ” Design Space Sampling to Predict Pareto-Optimal Solutions

Many high-level synthesis tools offer degrees of freedom in map-ping high-level specifications to Register-Transfer Level descrip-tions. These choices do not affect the functional behavior but span a design space of different cost-performance tradeoffs. In this pa-per we present a novel machine learning-based approach that ef-ficiently determines the Pareto-optimal designs while only sam-pling and synthesizing a fraction of the design space. The approach combines three key components: (1) A regression model based on Gaussian processes to predict area and throughput based on syn-thesis training data. (2) A “smart ” sampling strategy, GP-PUCB, to iteratively refine the model by carefully selecting the next design to synthesize to maximize progress. (3) A stopping criterion based on assessing the accuracy of the model without access to complete synthesis data. We demonstrate the effectiveness of our approach using IP generators for discrete Fourier transforms and sorting net-works. However, our algorithm is not specific to this application and can be applied to a wide range of Pareto front prediction prob-lems