221 lines
5.2 KiB
Groff
221 lines
5.2 KiB
Groff
.TH MPI_Win_create 3 "2/3/2025" " " "MPI"
|
|
.SH NAME
|
|
MPI_Win_create \- Create an MPI Window object for one-sided communication
|
|
.SH SYNOPSIS
|
|
.nf
|
|
.fi
|
|
.nf
|
|
int MPI_Win_create(void *base, MPI_Aint size, int disp_unit, MPI_Info info,
|
|
MPI_Comm comm, MPI_Win *win)
|
|
.fi
|
|
|
|
.nf
|
|
int MPI_Win_create_c(void *base, MPI_Aint size, MPI_Aint disp_unit,
|
|
MPI_Info info, MPI_Comm comm, MPI_Win *win)
|
|
.fi
|
|
|
|
|
|
.SH INPUT PARAMETERS
|
|
.PD 0
|
|
.TP
|
|
.B base
|
|
- initial address of window (choice)
|
|
.PD 1
|
|
.PD 0
|
|
.TP
|
|
.B size
|
|
- size of window in bytes (non-negative integer)
|
|
.PD 1
|
|
.PD 0
|
|
.TP
|
|
.B disp_unit
|
|
- local unit size for displacements, in bytes (positive integer)
|
|
.PD 1
|
|
.PD 0
|
|
.TP
|
|
.B info
|
|
- info argument (handle)
|
|
.PD 1
|
|
.PD 0
|
|
.TP
|
|
.B comm
|
|
- intra-communicator (handle)
|
|
.PD 1
|
|
|
|
.SH OUTPUT PARAMETERS
|
|
.PD 0
|
|
.TP
|
|
.B win
|
|
- window object (handle)
|
|
.PD 1
|
|
|
|
.SH NOTES
|
|
|
|
The displacement unit argument is provided to facilitate address arithmetic in
|
|
RMA operations: the target displacement argument of an RMA operation is scaled
|
|
by the factor disp_unit specified by the target process, at window creation.
|
|
|
|
The info argument provides optimization hints to the runtime about the expected
|
|
usage pattern of the window. The following info keys are predefined.
|
|
|
|
.PD 0
|
|
.TP
|
|
.B no_locks
|
|
- If set to true, then the implementation may assume that passive
|
|
target synchronization (i.e.,
|
|
.I MPI_Win_lock
|
|
,
|
|
.I MPI_Win_lock_all
|
|
) will not be used on
|
|
the given window. This implies that this window is not used for 3-party
|
|
communication, and RMA can be implemented with no (less) asynchronous agent
|
|
activity at this process.
|
|
.PD 1
|
|
|
|
.PD 0
|
|
.TP
|
|
.B accumulate_ordering
|
|
- Controls the ordering of accumulate operations at the
|
|
target. The argument string should contain a comma-separated list of the
|
|
following read/write ordering rules, where e.g. "raw" means read-after-write:
|
|
"rar,raw,war,waw".
|
|
.PD 1
|
|
|
|
.PD 0
|
|
.TP
|
|
.B accumulate_ops
|
|
- If set to same_op, the implementation will assume that all
|
|
concurrent accumulate calls to the same target address will use the same
|
|
operation. If set to same_op_no_op, then the implementation will assume that
|
|
all concurrent accumulate calls to the same target address will use the same
|
|
operation or
|
|
.I MPI_NO_OP
|
|
\&.
|
|
This can eliminate the need to protect access for
|
|
certain operation types where the hardware can guarantee atomicity. The default
|
|
is same_op_no_op.
|
|
.PD 1
|
|
|
|
.PD 0
|
|
.TP
|
|
.B mpi_accumulate_granularity
|
|
- Controls the desired synchronization granularity
|
|
for accumulate ops. It sets the size of memory range in bytes for which the
|
|
MPI library should acquire a synchronization primitive to ensure the atomicity
|
|
of updates. The default is 0 which let the MPI library decides the granularity.
|
|
When the info hint is set to a positive value, the actual range of synchroniation
|
|
is round-up to the next size that fits the Datatype used in the accumulate
|
|
operation (see MPI standard 4.1). All processes in the group of a windows must
|
|
set to the same value.
|
|
.PD 1
|
|
|
|
.SH THREAD AND INTERRUPT SAFETY
|
|
|
|
This routine is thread-safe. This means that this routine may be
|
|
safely used by multiple threads without the need for any user-provided
|
|
thread locks. However, the routine is not interrupt safe. Typically,
|
|
this is due to the use of memory allocation routines such as
|
|
.I malloc
|
|
or other non-MPICH runtime routines that are themselves not interrupt-safe.
|
|
|
|
.SH NOTES FOR FORTRAN
|
|
All MPI routines in Fortran (except for
|
|
.I MPI_WTIME
|
|
and
|
|
.I MPI_WTICK
|
|
) have
|
|
an additional argument
|
|
.I ierr
|
|
at the end of the argument list.
|
|
.I ierr
|
|
is an integer and has the same meaning as the return value of the routine
|
|
in C. In Fortran, MPI routines are subroutines, and are invoked with the
|
|
.I call
|
|
statement.
|
|
|
|
All MPI objects (e.g.,
|
|
.I MPI_Datatype
|
|
,
|
|
.I MPI_Comm
|
|
) are of type
|
|
.I INTEGER
|
|
in Fortran.
|
|
|
|
.SH ERRORS
|
|
|
|
All MPI routines (except
|
|
.I MPI_Wtime
|
|
and
|
|
.I MPI_Wtick
|
|
) return an error value;
|
|
C routines as the value of the function and Fortran routines in the last
|
|
argument. Before the value is returned, the current MPI error handler is
|
|
called. By default, this error handler aborts the MPI job. The error handler
|
|
may be changed with
|
|
.I MPI_Comm_set_errhandler
|
|
(for communicators),
|
|
.I MPI_File_set_errhandler
|
|
(for files), and
|
|
.I MPI_Win_set_errhandler
|
|
(for
|
|
RMA windows). The MPI-1 routine
|
|
.I MPI_Errhandler_set
|
|
may be used but
|
|
its use is deprecated. The predefined error handler
|
|
.I MPI_ERRORS_RETURN
|
|
may be used to cause error values to be returned.
|
|
Note that MPI does
|
|
.B not
|
|
guarantee that an MPI program can continue past
|
|
an error; however, MPI implementations will attempt to continue whenever
|
|
possible.
|
|
|
|
.PD 0
|
|
.TP
|
|
.B MPI_SUCCESS
|
|
- No error; MPI routine completed successfully.
|
|
.PD 1
|
|
.PD 0
|
|
.TP
|
|
.B MPI_ERR_ARG
|
|
- Invalid argument. Some argument is invalid and is not
|
|
identified by a specific error class (e.g.,
|
|
.I MPI_ERR_RANK
|
|
).
|
|
.PD 1
|
|
.PD 0
|
|
.TP
|
|
.B MPI_ERR_COMM
|
|
- Invalid communicator. A common error is to use a null
|
|
communicator in a call (not even allowed in
|
|
.I MPI_Comm_rank
|
|
).
|
|
.PD 1
|
|
.PD 0
|
|
.TP
|
|
.B MPI_ERR_DISP
|
|
-
|
|
.PD 1
|
|
.PD 0
|
|
.TP
|
|
.B MPI_ERR_INFO
|
|
- Invalid Info
|
|
.PD 1
|
|
.PD 0
|
|
.TP
|
|
.B MPI_ERR_SIZE
|
|
-
|
|
.PD 1
|
|
.PD 0
|
|
.TP
|
|
.B MPI_ERR_OTHER
|
|
- Other error; use
|
|
.I MPI_Error_string
|
|
to get more information
|
|
about this error code.
|
|
.PD 1
|
|
|
|
.SH SEE ALSO
|
|
MPI_Win_allocate MPI_Win_allocate_shared MPI_Win_create_dynamic MPI_Win_free
|
|
.br
|