Obtaining and reasoning about good enough software

Software systems often exhibit a surprising flexibility in the range of execution paths they can take to produce an acceptable result. This flexibility enables new techniques that augment systems with the ability to productively tolerate a wide range of errors. We show how to exploit this flexibility to obtain transformations that improve reliability and robustness or trade off accuracy in return for increased performance or decreased power consumption. We discuss how to use empirical, probabilistic, and statistical reasoning to understand why these techniques work.