.TH MPI_Win_create 3 "11/12/2019" " " "MPI"

.SH NAME

MPI_Win_create \-  Create an MPI Window object for one-sided communication 

.SH SYNOPSIS

.nf

int MPI_Win_create(void *base, MPI_Aint size, int disp_unit, MPI_Info info,

MPI_Comm comm, MPI_Win * win)

.fi

This is a collective call executed by all processes in the group of comm. It

returns a window object that can be used by these processes to perform RMA

operations. Each process specifies a window of existing memory that it exposes

to RMA accesses by the processes in the group of comm. The window consists of

size bytes, starting at address base. In C, base is the starting address of a

memory region. In Fortran, one can pass the first element of a memory region or

a whole array, which must be 'simply contiguous' (for 'simply contiguous', see

also MPI 3.0, Section 17.1.12 on page 626). A process may elect to expose no

memory by specifying size = 0.

.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 (nonnegative 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 

- communicator (handle)

.PD 1

.SH OUTPUT PARAMETERS

.PD 0

.TP

.B win 

- window object returned by the call (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

.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

guarentee 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_INFO 

- Invalid Info 

.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

.PD 0

.TP

.B MPI_ERR_SIZE 

- 

.PD 1

.SH SEE ALSO

MPI_Win_allocate MPI_Win_allocate_shared MPI_Win_create_dynamic MPI_Win_free

.br