Thread-block cluster
A thread-block cluster is an optional CUDA cooperation scope introduced with Hopper. Supported launches group blocks that can coordinate and access one another’s shared memory within the cluster.
How it works
Cluster scheduling provides stronger placement and progress guarantees than unrelated blocks in a grid. Distributed shared memory still needs lifetime and synchronization discipline: a remote block’s shared memory cannot be accessed after that block has exited.
Work through an example
An algorithm with a histogram too large for one block’s shared memory may divide it across cooperating blocks, then combine contributions under cluster synchronization.
Where the term can mislead
Cluster size and launch support depend on the device and configuration. Query the supported limits and use cluster-aware occupancy calculations.
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.