Program debugging is a process of identifying and fixing bugs. Identifying the root causes is the hardest, thus the most expensive, component of debugging. According to a U.S. federal study, software defects costs U.S. economy an estimated $59.5 billion each year and improvements (including testing and debugging) could reduce this cost by a third, or $22.5 billion. Therefore, automated approaches that help developers quickly pinpoint the root causes of failures are of great importance. Many approaches have been proposed to facilitate fault localization. The limitations of these approaches are well-known and sometimes severe. To circumvent these shortcomings, we propose to leverage hardware performance counters to locate functional defects. The objective of this project is to empirically evaluate the accuracy and effectiveness of using hardware performance counters-based program profiling data in locating functional defects. Hardware performance counters have been traditionally leveraged to perform low-level performance analysis and tuning of software systems. In this project, we will leverage hardware performance counters in a novel way, exploiting them for functional correctness debugging by identifying pieces of program code that perform some “suspicious” activities.