|
| procedure, pass(this) | init (this, send_pe, recv_pe) |
| | Initialise crystal router based communication method See gs_comm.f90 for details.
|
| |
| procedure, pass(this) | free (this) |
| | Deallocate crystal router based communication method.
|
| |
| procedure, pass(this) | nbsend (this, u, n, tag, deps, strm) |
| | See gs_comm.f90 for more details on these routines.
|
| |
| procedure, pass(this) | nbrecv (this, tag) |
| | Post the receives of the first routing stage.
|
| |
| procedure, pass(this) | nbwait (this, u, n, op, strm) |
| | Drive the remaining routing stages and reduce what is delivered into the shared vector.
|
| |
| procedure, pass(this) | init_vec (this) |
| | Allocate the fused vector working and send buffers, sized for GS_VEC_NC components. Deferred to the first fused exchange, see gs_comm_t. The routing plan is shared with the scalar exchange and is not rebuilt here, so this stays rank local.
|
| |
| procedure, pass(this) | nbsend_vec (this, u, n, nc, tag, deps, strm) |
| | Pack the shared vector and post the send of the first routing stage, fused nc-component.
|
| |
| procedure, pass(this) | nbrecv_vec (this, tag, nc) |
| | Post the receives of the first routing stage, fused nc-component.
|
| |
| procedure, pass(this) | nbwait_vec (this, u, n, nc, op, strm) |
| | Drive the remaining routing stages and reduce what is delivered into the shared vector, fused nc-component.
|
| |
| procedure(gs_comm_init), deferred, pass | init gs_comm_init |
| |
| procedure(gs_comm_free), deferred, pass | free gs_comm_free |
| |
| procedure(gs_nbsend), deferred, pass | nbsend gs_nbsend |
| |
| procedure(gs_nbrecv), deferred, pass | nbrecv gs_nbrecv |
| |
| procedure(gs_nbwait), deferred, pass | nbwait gs_nbwait |
| |
| procedure, pass(this) | init_dofs (this) |
| |
| procedure, pass(this) | free_dofs (this) |
| |
| procedure, pass(this) | init_order (this, send_pe, recv_pe) |
| | Obtains which ranks to send and receive data from.
|
| |
| procedure, pass(this) | free_order (this) |
| |
| procedure, pass(this) | take_schedule (this, src) |
| | Take over the gather-scatter schedule (dof lists and peer order) of src, avoiding a second (expensive) pass over the connectivity. The data is moved rather than copied, so src is left without a schedule and must not be used for communication afterwards (it can still be freed). No communication resources are set up here; complete the handover with init_schedule once src has been freed, so that the two backends never hold their resources at the same time.
|
| |
| procedure, pass(this) | init_schedule (this) |
| | Set up this communication method for the schedule taken over by take_schedule. Collective, as init is.
|
| |
| procedure, pass(this) | init_vec (this) |
| | Fused vector halo exchange. Default implementations abort; backends that set vec_supported = .true. override them.
|
| |
| procedure, pass(this) | nbsend_vec (this, u, n, nc, tag, deps, strm) |
| | Default fused vector send. Abort unless a backend overrides it.
|
| |
| procedure, pass(this) | nbrecv_vec (this, tag, nc) |
| | Default fused vector receive. Abort unless a backend overrides it.
|
| |
| procedure, pass(this) | nbwait_vec (this, u, n, nc, op, strm) |
| | Default fused vector wait/reduce. Abort unless a backend overrides it.
|
| |
|
| type(gs_crystal_plan_t) | plan |
| | The routing plan, worked out once from the schedule.
|
| |
| real(kind=rp), dimension(:), allocatable | buf |
| | Working buffer, two columns of plannwrk laid end to end. Column q starts at (q-1)*plannwrk.
|
| |
| real(kind=rp), dimension(:), allocatable | sbuf |
| | Send buffer, plannsmax words.
|
| |
| real(kind=rp), dimension(:), allocatable | buf_v |
| | Fused vector working and send buffers, the same layout scaled by GS_VEC_NC components. Positions are interleaved: position p holds its nc components at nc*(p-1) + 1 .. nc*p.
|
| |
| real(kind=rp), dimension(:), allocatable | sbuf_v |
| |
| type(mpi_request), dimension(1) | sreq |
| | Requests of the stage in flight, at most one send and two receives.
|
| |
| type(mpi_request), dimension(2) | rreq |
| |
| integer | nsreq = 0 |
| |
| integer | nrreq = 0 |
| |
| integer | tag = 0 |
| | Tag of the operation in flight, taken from nbrecv since the later stages are driven from nbwait, which is not given one.
|
| |
| type(stack_i4_t), dimension(:), allocatable | send_dof |
| | A list of stacks of dof indices local to this process to send to rank_i.
|
| |
| type(stack_i4_t), dimension(:), allocatable | recv_dof |
| | recv_dof(rank_i) is a stack of dof indices local to this process to receive from rank_i. size(recv_dof) == pe_size
|
| |
| integer, dimension(:), allocatable | send_pe |
| | Array of ranks that this process should send to.
|
| |
| integer, dimension(:), allocatable | recv_pe |
| | array of ranks that this process will receive messages from
|
| |
| logical | vec_supported = .false. |
| | Whether this backend implements the fused vector (multi-component) halo exchange (nbsend_vec/nbrecv_vec/nbwait_vec). When .false., the gs_op_r3 caller falls back to nc independent scalar exchanges.
|
| |
| logical | vec_ready = .false. |
| | Whether the buffers the fused vector exchange needs are in place. They are sized GS_VEC_NC times the halo, quadrupling what the backend holds, and only gs_op_r3 ever touches them, so a backend that can allocate them on its own defers that to the first fused exchange (see init_vec) rather than paying for it in every run. A backend whose vector buffers are part of an allocation the whole run has to agree on – symmetric memory, coarrays, registered memory, an RMA window – cannot defer, since a rank with no shared dofs never reaches the first fused exchange; those allocate in init and set this there.
|
| |
Definition at line 65 of file gs_crystal.f90.