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

Mojo function

shmem_barrier_all

shmem_barrier_all()

Registers the arrival of a PE at a barrier and blocks the PE until all other PEs arrive at the barrier and all local updates and remote memory updates on the default context are completed.

The shmem_barrier_all routine is a mechanism for synchronizing all PEs in the world team at once. This routine blocks the calling PE until all PEs have called shmem_barrier_all. In a multithreaded OpenSHMEM program, only the calling thread is blocked, however, it may not be called concurrently by multiple threads in the same PE. Prior to synchronizing with other PEs, shmem_barrier_all ensures completion of all previously issued memory stores and remote memory updates issued on the default context via OpenSHMEM AMOs and RMA routine calls such as shmem_int_add, shmem_put32, shmem_put_nbi, and shmem_get_nbi.