Abstract Integrated circuit (IC) delayering workflows are highly reliant on operator experience to determine processing end points. The current method of end point detection during IC delayering uses qualitative correlations between the thickness and color of dielectric films observed via optical microscopy. The goal of this work is to quantify this relationship using computer vision. As explained in the paper, the authors trained a convolutional neural network to estimate the thickness of dielectric films based on images and measurements recorded during processing. The trained vision model explained 39% of the variance in dielectric film thickness with a mean absolute error of approximately 47 nm. The paper describes the entire workflow, including verification testing, and addresses the primary sources of error.

Abstract Backside silicon removal provides an avenue for a number of modern non-destructive and circuit edit techniques. Visible light microscopy, electron beam microscopy, and focused ion beam circuit edit benefit from a removal of back side silicon from the integrated circuit being examined. Backside milling provides a potential path for rapid sample preparation when thinned or ultrathinned samples are required. However, backside milling is an inherently destructive process and can damage the device function, rendering it no longer useful for further nondestructive analysis. Recent methods of backside milling do not guarantee device functionality at a detected end point without a priori knowledge. This work presents a methodology for functional end point detection during backside milling of integrated circuit packaging. This is achieved by monitoring second order effects in response to applied device strain, which guide the milling procedure, avoiding destructive force as the backside material is removed. Experimental data suggest a correlation between device power consumption waveforms and second order effects which inform an in situ functional end point. Keywords: functional end point, side-channel analysis, backside thinning, milling, machine learning, second order effects