Effective and Efficient Microprocessor Design Space Exploration Using Unlabeled Design Configurations
Qi Guo, Tianshi Chen, Yunji Chen, Zhi-Hua Zhou and Weiwu Hu
During the design of a microprocessor, Design Space Exploration (DSE) is a critical step which determines the appropriate design configuration 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 configurations. For supervised learning, however, considerable simulation costs are required for attaining the labeled design configurations. Given limited resources, it is difficult to achieve high accuracy. In this paper, inspired by recent advances in semi-supervised learning, we propose the C\textsc{omt} approach which can exploit unlabeled design configurations to improve the models. In addition to an improved predictive accuracy, C\textsc{omt} is able to guide the design of microprocessors, owing to the comprehensible model trees employed in C\textsc{omt}. Empirical study demonstrates that C\textsc{omt} significantly outperforms the state-of-the-art DSE technique through reducing mean squared error by 30\% to even 84\%, and thus, promising architectures can be attained more efficiently.