Cluster-based Localization of IR-drop in Test Application considering Parasitic Elements

Harshad Dhotre; Stephan Eggersglüß; Rolf Drechsler

In: 20th IEEE Latin American Test Symposium. IEEE Latin American Test Symposium (LATS-2019), March 11-13, Santiago, Chile, 2019.


Highly compact test patterns are vulnerable to IR-drop during testing which might lead to failures or breakdowns.An accurate analysis of all test patterns is infeasible due to theexcessive analysis run time. Previous switching activity based IR-drop prediction methods are highly approximate since less data isused to analyze the test set. In this paper, we propose a dynamicIR-drop prediction methodology, which considers resistive andcapacitive parasitic elements of the circuit together with theswitching activity. The proposed method uses machine-learningbased clustering and is more accurate than the general switchingbased method. More importantly, the methodology is fast enoughthat the complete test set can be processed to identify vulnerablepatterns prone to IR-drop failure. The experiments show theeffectiveness of the proposed approach for the approximateanalysis of the complete test set.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence