A Taxonomy of Approximate Computing Techniques

Approximate computing is the idea that systems can gain performance and energy efficiency if they expend less effort on producing a “perfect” answer. Approximate computing techniques propose various ways of exposing and exploiting accuracy– efficiency trade-offs. We present a taxonomy that classifies approximate computing techniques according to their most salient features: compute vs. data, deterministic vs. nondeterministic and coarsevs. fine-grained. These axes allow us to address questions about the visibility, testability and flexibility of different techniques. We use this taxonomy to inform future research in approximate architectures, compilers and applications that will catalyze mainstream adoption of approximate computing.