SM utilization
SM utilization is an ambiguous label unless the tool and counter are named. Device activity, resident warps and execution-pipeline throughput measure different properties.
How it works
nvidia-smi GPU utilization reports kernel activity during its sampling window. Nsight metrics can instead describe SM active cycles or throughput relative to selected pipeline peaks. DCGM fields add their own definitions and collection constraints.
Work through an example
A persistent, lightly loaded kernel may keep the device active while accomplishing little useful work. Compare the activity sample with application throughput and a scoped kernel investigation.
Where the term can mislead
“The GPU is 100% utilized” cannot justify a capacity decision without the counter, sample interval and workload outcome.
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.