Leveraging Bayesian Optimization to Speed Up Automatic Precision Tuning

Using just the right amount of numerical precision is an important aspect for guaranteeing performance and energy efficiency requirements. Word-Length Optimization (WLO) is the automatic process for tuning the precision, i.e., bit-width, of variables and operations represented using fixed-point arithmetic. However, state-of-the-art precision tuning approaches do not scale well in large applications where many variables are involved. In this paper, we propose a hybrid algorithm combining Bayesian optimization (BO) and a fast local search to speed up the WLO procedure. Through experiments, we first show some evidence on how this combination can improve exploration time. Then, we propose an algorithm to automatically determine a reasonable transition point between the two algorithms. By statistically analyzing the convergence of the probabilistic models constructed during BO, we derive a stopping condition that determines when to switch to the local search phase. Experimental results indicate that our algorithm can reduce exploration time by up to 50%-80% for large benchmarks.