Skip to main content

Module synchronization

Module synchronization 

Source

Modules§

sync_async_proxy_shared
sync_cube
sync_plane
sync_storage
workgroup_uniform_load
Module containing the expand function for workgroup_uniform_load().
workgroup_uniform_load_atomic
Module containing the expand function for workgroup_uniform_load_atomic().

Functions§

sync_async_proxy_shared
sync_async_proxy_shared is a synchronization fence for the experimental SM 9.0+ copy functions, applying bidirectionally between the async proxy (i.e. TMA) and shared memory. Should be used after initializing the barriers, and before the copy operation. PTX: fence.proxy.async.shared::cta Experimental and subject to change.
sync_cube
Coordinates the following among all invocations in the current cube:
sync_plane
Synchronizes units within their plane (e.g., warp or SIMD group).
sync_storage
[sync_cube] over storage memory (input args) rather than shared memory, and the one synchronization that reaches past the cube.
workgroup_uniform_load
Barrier, then load reference with the result marked workgroup-uniform — mirrors WGSL’s workgroupUniformLoad. Lets a workgroup-shared value gate control flow that contains barriers. Non-WGSL backends lower it to [sync_cube] plus a plain load.
workgroup_uniform_load_atomic
Atomic counterpart of [workgroup_uniform_load]: barrier + atomic load, returning the underlying numeric (WGSL’s atomic workgroupUniformLoad overload).