Expectation-Oriented Framework for Automating Approximate Programming

This paper describes ExpAX, a framework for automating approx-imate programming based on programmer-specified error expec-tations. Three components constitute ExpAX: (1) a programming model based on a new kind of program specification, which we re-fer to as expectations. Our programming model enables program-mers to implicitly relax the accuracy constraints without explicitly marking operations approximate; (2) a novel approximation safety analysis that automatically identifies a safe-to-approximate subset of the program operations; and (3) an optimization that automati-cally marks a subset of the safe-to-approximate operations as ap-proximate while considering the error expectation. Further, we for-mulate the process of automatically marking operations as approxi-mate as an optimization problem and provide a genetic algorithm to solve it. We evaluate ExpAX using a diverse set of applications and show that it can provide significant energy savings while improving the quality-of-result degradation. ExpAX automatically excludes the safe-to-approximate operations that if approximated lead to sig-nificant quality degradation. 1