Influence of error correlations on the signature analysis aliasing

Signature analysis is often used in the test area to reduce the amount of information to check. The drawback of this compaction is its non-zero aliasing probability, i.e. the possibility to obtain a correct signature in spite of errors in the compacted words. Up to now, the studies on aliasing have focused on BIST applications and do not consider correlations between errors in two compacted words. However, online test methods also use signature analysis. The reported experiments show that, in this context and for some types of faults, the existing correlations have a noticeable impact on the aliasing probability. Further theoretical studies taking into account these correlations are therefore required to model the aliasing observed at each compaction step. It also seems that checking a signature in the middle of a linear block of instructions is better than checking it just before or after a branching instruction