Thread
A CUDA thread is one logical execution of a kernel, with its own index, register values and control-flow state.
How it works
Threads use their indices to divide the output work. Within a warp, one issued instruction acts on the currently participating lanes. A lane number identifies a thread position inside that warp; it is not a permanent physical core assignment.
Work through an example
In a one-dimensional launch, thread 7 of block 3 with 256 threads per block has global index 3 × 256 + 7 = 775. It can compute output element 775 if that index is valid.
Where the term can mislead
Independent thread scheduling does not remove the need for explicit synchronization when threads communicate through memory.
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.