An expected hypervolume improvement algorithm for architectural exploration of embedded processors
Hongwei Wang, Jinglin Shi, Ziyuan Zhu · 2016
Surrogate model based design space exploration (DSE) techniques have been widely used in finding the Pareto-optimal design points of embedded processor architectures. However, existing such methods lack of sound modeling of the uncertainty of the surrogate models, which greatly limits the searching scope. In this paper we propose an expected hypervolume improvement (EHVI) algorithm which models the uncertainty of an adaptive component selection and smoothing operator (ACOSSO) surrogate model by means of constructing a Gaussian random distribution and searches the Pareto points by taking an EHVI criterion. Experimental results prove the effectiveness of the proposed algorithm through comparing with two existing DSE algorithms.