For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Mojo function

cp_async_bulk_commit_group

def cp_async_bulk_commit_group()

Commits all prior initiated but uncommitted cp.async.bulk instructions into a cp.async.bulk-group.

This function commits all previously initiated but uncommitted cp.async.bulk instructions into a cp.async.bulk-group. The cp.async.bulk instructions are used for asynchronous bulk memory transfers on NVIDIA GPUs.

The function creates a synchronization point for bulk memory transfers, allowing better control over memory movement and synchronization between different stages of computation.

Note: This functionality is only available on NVIDIA GPUs. Attempting to use this function on non-NVIDIA GPUs will result in a compile time error.