gs_shmem.F90 File Reference

Go to the source code of this file.

Data Types
type	gs_shmem::gs_shmem_buf_t
	Symmetric buffer for one direction of OpenSHMEM communication. More...
type	gs_shmem::gs_shmem_t
	Gather-scatter communication using OpenSHMEM one-sided puts with per-rank signaling for completion (OpenSHMEM 1.5). More...

Modules
module	gs_shmem
	Defines OpenSHMEM gather-scatter communication.

Functions/Subroutines
subroutine	gs_shmem::gs_shmem_buf_init (this, pe_order, dof_stack)
	Allocate symmetric memory and per-neighbor bookkeeping for one direction of communication.
subroutine	gs_shmem::gs_shmem_buf_free (this)
	Release symmetric memory and bookkeeping.
subroutine	gs_shmem::gs_shmem_init (this, send_pe, recv_pe)
	Initialise OpenSHMEM based communication method.
subroutine	gs_shmem::gs_shmem_free (this)
	Deallocate OpenSHMEM based communication method.
subroutine	gs_shmem::gs_shmem_nbsend (this, u, n, tag, deps, strm)
	Pack the gathered shared dofs into the symmetric send buffer and issue non-blocking puts with signaling to each neighbor's recv buffer. Before each put, wait for the receiver's ack of our previous round so we never overwrite a buffer the receiver hasn't consumed yet.
subroutine	gs_shmem::gs_shmem_nbrecv (this, tag)
	No-op: receives are completed via remote put-with-signal.
subroutine	gs_shmem::gs_shmem_nbwait (this, u, n, op, strm)
	Wait per-neighbor for the signal indicating that data has landed, apply the gather-scatter operation from the recv buffer into u, and ack the sender so they may overwrite the buffer in the next round.
subroutine	gs_shmem::gs_shmem_nbsend_vec (this, u, n, nc, tag, deps, strm)
	Fused nc-component send: pack nc contiguous component blocks per peer slab and put nc*ndofs reals with a single signal. Buffer indexing and put size scale by nc; the per-rank signalling is unchanged.
subroutine	gs_shmem::gs_shmem_nbrecv_vec (this, tag, nc)
	No-op: receives are completed via remote put-with-signal.
subroutine	gs_shmem::gs_shmem_nbwait_vec (this, u, n, nc, op, strm)
	Fused nc-component wait/reduce: per peer, wait on the data signal and reduce nc component blocks into u, then ack the sender.

Variables
logical	gs_shmem::gs_shmem_thread_multiple = .false.
	True when the OpenSHMEM library provides SHMEM_THREAD_MULTIPLE. The send path then lets each OpenMP thread run the back-pressure wait, the pack and the put for its own share of the send peers; otherwise every SHMEM call is funnelled through the master thread, mirroring how gs_mpi keys off NEKO_MPI_THREAD_PROVIDED. Queried on every gs_shmem_t init (the level is a property of the library, so all instances agree).
logical, parameter, public	gs_shmem::gs_shmem_avail = .false.
	Whether a native OpenSHMEM library was built into this Neko (–with-openshmem). Lets callers (e.g. the gs comm. autotuner) skip the backend rather than aborting in init on builds without it.