Partial bist insertion to eliminate data correlation

Abstract

A new partial BIST insertion approach based on eliminating data correlation to improve pseudo-random testability is presented. Data correlation causes the circuit to be in a subset of the states more or less frequently, which leads to low fault coverage in pseudo-random test. One important cause of correlation is reconvergent fanout. Incorporating BIST test flip-flops into reconvergent paths will break correlation, however, breaking all reconvergent fanout is unnecessary since some reconvergent fanout results in negligible correlation. We introduce a metric to determine the degree of correlation caused by a set of reconvergent fanout paths. We use this metric to identify problematic reconvergent fanout which must be broken through partial BIST insertion. We provide an algorithm to break high correlation reconvergent paths. Our algorithm provides high fault coverage while selecting fewer BIST flip-flops than required using loop breaking techniques. Experimental results produced using our algorithm rank on average among the top 11.6% of all possible solutions with the same number of flip-flops.