Energy efficiency is a primary design goal in the embedded space. Embedded and mobile devices are typically battery operated, and hence battery lifetime is a key design goal. Along with this quest for improved energy efficiency comes the trend of ever more complex and diverse applications. Hardware customization is an effective approach for meeting application performance requirements while achieving high levels of energy efficiency. Application-specific processors achieve high performance at low energy by tailoring their designs towards a specific workload, i.e., an application or application domain of interest. A fundamental question that has remained unanswered so far though is to what extent processor customization is sensitive to the training workload's input datasets.