Efficient function call tracing with link-time binary rewriting for CE devices

As the scale and complexity of software components in consumer electronics increase, the importance of performance optimization is rapidly growing. Consequently, the demand for performance optimization tools tailored for the consumer electronics environment is stronger than ever. A function call tracer is a vital tool for investigating relationships between functions, invocation counts of a function, and elapsed time in a function. Despite its importance in performance optimization, the limited capability of embedded hardware prohibits use of existing dynamic binary instrumentation tools. Moreover, the use of closed proprietary components excludes source-level analysis tools out of viable options. In this paper, LITIFUT, a function call tracer designed for consumer electronics, is proposed. This tool rewrites an executable file or a library file to inject profiling code during the linking stage. This approach achieves as little performance overhead as source-level instrumentation and as minor developer-intervention as binary-level instrumentation. The prototype implementation supports the two most popular embedded processor architectures. The evaluation with a real-world embedded software application showed that LITIFUT successfully profiles program activities with insignificant overhead.