Branch efficiency
Branch efficiency describes how uniformly threads take branch paths under a particular tool’s branch-counting convention. It is a control-flow statistic, not overall GPU efficiency.
How it works
The metric’s exact population and availability vary by profiler and GPU. A uniform branch can still select expensive work, and code without branches can still waste lanes through predicates or partial tiles.
Work through an example
A warp whose 32 lanes all enter a long loop can have uniform branching yet run much slower than a short divergent operation. Compare instruction work and measured time before optimizing the percentage.
Where the term can mislead
Do not assume every profiler exposes the same historical branch-efficiency metric or that 100% means all lanes always do useful work.
Connect the idea
Take it into practice
Continue with the existing concept, apply it to an interview problem, or follow a course lesson. Access requirements are shown before you open a page.
New to GPUs? Start with the free execution-model concept.
Sources and scope
Examples here are teaching calculations, not measured GPU performance. Consult the linked documentation for the exact device, instruction and tool version. Source review: 25 October 2026.