Chenglong Sun and Tian Huang, Chinese Academy of Sciences, China

Fault localization is time-consuming and difficult, which makes it the bottleneck of the debugging progress. To help facilitate this task, there exist many fault localization techniques that help narrow down the region of the suspicious code in a program. Better accuracy in fault localization is achieved from heavy computation cost. Fault localization techniques that can effectively locate faults also manifest slow response rate. In this paper, we promote the use of pre-computing to distribute the time-intensive computations to the idle period of coding phase, in order to speed up such techniques and achieve both low-cost and high accuracy. We raise the research problems of finding suitable techniques that can be pre-computed and adapt it to the pre-computing paradigm in a continuous integration environment. Further, we use an existing fault localization technique to demonstrate our research exploration, and shows visions and challenges of the related methodologies.

Software testing, fault localization, continuous integration, mutation testing