Fault Coverage of a Test Set on Structure-Preserving Siblings of a Circuit-Under-Test

Abstract

Most of the Automatic Test Pattern Generation (ATPG) algorithms for digital circuits rely heavily on netlist description that comprises both network interconnect structure among logic gates and the functionality of each gate. The performance of an ATPG tool on a circuit-under-test (CUT) C is determined by the size of the test set T and its fault coverage (FC). Despite extensive research in the field of testing, the following question remains unanswered: Is the structure or the functionality of C dominant in determining FC of a test-set T for C? In this paper, we present empirical evidence in favour of the dominance of structure on FC by randomly selecting a logic gate from a synthesized netlist for C, and replacing it by a different type of gate. Our experiments provide an un-intuitive result that F C of a test-set T for C under the single stuck-at fault model remains nearly the same on other sibling circuits that have identical structure as of C but with different gate functionality, provided these have similar extent of fault redundancy. This observation supports the view that feeding structural information alone may suffice to train machine-learning models that are currently being used to expedite different problems of digital circuit testing and diagnosis.