Abstract
During the design of a microprocessor, Design Space Exploration (DSE) is a critical step which determines the appropriate design con?guration of the microprocessor. In the computer architecture community, supervised learning techniques have been applied to DSE to build models for predicting the qualities of design con?gurations. For supervised learning, however, considerable simulation costs are required for attaining the labeled design con?gurations. Given limited resources, it is dif?cult to achieve high accuracy. In this paper, inspired by recent advances in semi-supervised learning, we propose the COMT approach which can exploit unlabeled design con?gurations to improve the models. In addition to an improved predictive accuracy, COMT is able to guide the design of microprocessors, owing to the use of comprehensible model trees. Empirical study demonstrates that COMT signi?cantly outperforms state-of-theart DSE technique through reducing mean squared error by 30% to 84%, and thus, promising architectures can be attained more ef?ciently.