During the design of a microprocessor, Design Space Exploration (DSE) is a critical step whichdetermines 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 order to design an efficient architecture for Loongson (Godson) series, Phd student Guo Qi, together with assistant professor Chen Tianshi, associate professor Chen Yunji, professor Zhou Zhi-Hua, professor Hu Weiwu and professor Xu Zhiwei proposed the COMT approach which can exploit unlabeled design configurations to improve the predictive models, which is inspired by recent advances in semi-supervised learning. 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 significantly outperforms state-of-the-art DSE technique through reducing mean squared error by 30% to 84%, and thus, promising architectures can be attained more efficiently.

The work titled with “Effective and Efficient Microprocessor Design Space Exploration Using Unlabeled Design Configurations” was reported at the 22nd International Joint Conference on Artificial Intelligence (IJCAI’2011), held in Barcelona, Spain from 16th to 22nd July, 2011 by associate professor Chen Yunji. It is also the first regular IJCAI paper of ICT. The paper is delivered by International Joint Conference on Artificial Intelligence at www.ijcai.org