Failure coverage of functional test methods: a comparative experimental evaluation

An effort has been made to evaluate the fault coverage of functional test methods. A study comparing a structural (manufacturing) test and three functional test methods, a tailored test, a systematic pseudo-exhaustive test, and a random test, is presented. The experiments were performed on defective microprocessors (6800 and 68000). Working with a nonbiased sample of circuits was a major concern; thus, randomly distributed defects were created on a set of good circuits by cutting either Al or poly-Si tracks using microcutter machine equipment. The results concerning defect coverage and Boolean defect coverage are largely better than those given by H.P. Klug (1988). The results indicate that the functional methods evaluated are very thorough. Random test seems to achieve an impressive fault coverage.<>