IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /docs/manual/basics.md). For the complete Mojo documentation index, see llms.txt.
Skip to main content
Version: Nightly
For the complete Mojo documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /docs/manual/basics.md).

wait_on_dependent_grids

wait_on_dependent_grids()

Waits for all dependent grids launched by this grid to complete execution.

This function blocks the calling grid until all dependent grids that were launched by this grid have completed their execution. It provides a synchronization point between parent and child grids in a multi-grid dependency chain.

Note:

  • Only supported on NVIDIA SM90+ (Hopper architecture and newer) GPUs.
  • Must be called by all threads in a thread block to avoid undefined behavior.
  • Can be used to ensure dependent grid work is complete before proceeding with subsequent operations in the parent grid.