Automated silicon debug data analysis techniques for a hardware data acquisition environment

Abstract

Silicon debug poses a unique challenge to the engineer because of the limited access to internal signals of the chip. Embedded hardware such as trace buffers helps overcome this challenge by acquiring data in real time. However, trace buffers only provide access to a limited subset of pre-selected signals. In order to effectively debug, it is essential to configure the trace-buffer to trace the relevant signals selected from the pre-defined set. This can be a labor-intensive and time-consuming process. This paper introduces a set of techniques to automate the configuring process for trace buffer-based hardware. First, the proposed approach utilizes UNSAT cores to identify signals that can provide valuable information for localizing the error. Next, it finds alternatives for signals not part of the traceable set so that it can imply the corresponding values. Integrating the proposed techniques with a debugging methodology, experiments show that the methodology can reduce 30% of potential suspects with as low as 8% of registers traced, demonstrating the effectiveness of the proposed procedures.