Back to Bits: Extending Shannon's communication performance framework to computing
Max Hawkins, Richard Vuduc

TL;DR
This paper extends Shannon's information theory to define a new, more comprehensive performance metric for computing systems, capturing the meaningful information processed beyond traditional measures like flops.
Contribution
It introduces a novel information-theoretic framework for evaluating computing performance, applicable across diverse and emerging computing paradigms.
Findings
Defines computing as information transformation via mutual information
Provides a unified, implementation-agnostic performance measure
Applicable to analog, quantum, and reversible computing
Abstract
This work proposes a novel computing performance unit grounded in information theory. Modern computing systems are increasingly diverse, supporting low-precision formats, hardware specialization, and emerging paradigms such as analog, quantum, and reversible logic. Traditional metrics like floating-point operations (flops) no longer accurately capture this complexity. We frame computing as the transformation of information through a channel and define performance in terms of the mutual information between a system's inputs and outputs. This approach measures not just the quantity of data processed, but the amount of meaningful information encoded, manipulated, and retained through computation. Our framework provides a principled, implementation-agnostic foundation for evaluating performance.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
