Rolf Schlagenhaft

DFT Architecture for Automotive Microprocessors using On-Chip Scan Compression supporting Dual Vendor ATPG

The implementation and validation of a common DFT architecture for a new product family of PowerPC based microprocessors for various automotive applications supporting highest quality levels and low-cost test is a big challenge. When this new architecture has to satisfy the requirements of two semiconductor companies using two different CAD flows based on different ATPG tools coming with incompatible on-chip scan compression solutions, the task becomes even more complex. This paper describes the result of this major effort and shows the problems encountered along the way.

Diagnostic Mechanism and Robustness of Safety Relevant Automotive Deep Convolutional Networks

Convolution Neural Networks today provide the best results for many image detection and image recognition problems. The computational complexity and the amount of parameters learned has increased, yet there is little to no research on the topic of functional safety for systems incorporating CNNs. The analysis on false detections due to random hardware faults concentrates on human made adversarial examples obtained by adding unrealistic noise sources over carefully selected images. Redundant execution of these networks is prohibitive in application domains where power and price constraints dominate, pushing for alternate approaches. In this paper we investigate functional safety aspects for a road labeling application, a common task in the advance driver assistance systems. We introduce computationally light safety checks that reduce the error space significantly, train a CNN on the Cityscape dataset that reaches 93% mean IU (intersection over union) and use Monte Carlo simulations to assess the impact of single event upset random hardware faults. The results show that the networks based on convolution and ReLU (rectified linear unit) have some intrinsic robustness and that together with additional constraints strong function safety claims can be made. We compare also the diagnostic coverage between floating point and fixed point implementation of CNNs and summarize key safety features needed to achieve a high diagnostic coverage.