Evolutionary Generation Approach of Test Data for Multiple Paths Coverage of Message-passing Parallel Programs

Test data generation, the premise of software testing, has attracted scholars in the software engineering community in recent years. Influenced by task partitioning, process scheduling, and network delays, parallel programs are executed in a non-deterministic way, which makes test data generation of parallel programs different from that of serial programs in essence. This paper investigated the problem of generating test data for multiple paths coverage of message-passing parallel programs. A mathematical model of the above problem was built based on each given path and its equivalent ones. It was solved by using a genetic algorithm to generate all desired data in one run. The proposed method was applied to five benchmark programs, and compared with the existing methods. The experimental results show that the proposed method greatly shortens the number of iterations and time consumption without reducing the coverage rate.