MPI_Iallgather function

Article
09/14/2018

Gathers data from all members of a group and sends the data to all members of the group in a non-blocking way.

Syntax

int MPIAPI MPI_Iallgather(
  _In_opt_  const void         *sendbuf,
  _In_             int         sendcount,
  _In_            MPI_Datatype sendtype,
  _Out_opt_       void         *recvbuf,
  _In_            int          recvcount,
  _In_            MPI_Datatype recvtype,
  _In_            MPI_Comm     comm,
  _Out_           MPI_Request  *request
);

Parameters

sendbuf [in, optional]
The pointer to the data to be sent to all processes in the group. The number and data type of the elements in the buffer are specified in the sendcount and sendtype parameters. Each element in the buffer corresponds to a process in the group.

If the comm parameter references an intracommunicator, you can specify an in-place option by specifying MPI_IN_PLACE in all processes. The sendcount and sendtype parameters are ignored. Each process enters data in the corresponding receive buffer element. The nth process sends data to the nth element of the receive buffer.
sendcount [in]
The number of elements in the buffer that is specified in the sendbuf parameter. If sendcount is zero, the data part of the message is empty.
sendtype [in]
The MPI data type of the elements in the send buffer.
recvbuf [out, optional]
The pointer to a buffer that contains the data that is received from each process. The number and data type of the elements in the buffer are specified in the recvcount and recvtype parameters.
recvcount [in]
The number of elements in the receive buffer. If the count is zero, the data part of the message is empty.
recvtype [in]
The MPI data type of the elements in the receive buffer.
comm [in]
The MPI_Comm communicator handle.
request [out]
The MPI_Request handle representing the communication operation.

Return value

Returns MPI_SUCCESS on success. Otherwise, the return value is an error code.

In Fortran, the return value is stored in the IERROR parameter.

Fortran

    MPI_IALLGATHER(SENDBUF, SENDCOUNT, SENDTYPE, RECVBUF, RECVCOUNT, RECVTYPE, COMM, REQUEST, IERROR)
        <type> SENDBUF(*), RECVBUF(*)
        INTEGER SENDCOUNT, SENDTYPE, RECVCOUNT, RECVTYPE, COMM, REQUEST, IERROR

Remarks

A non-blocking call initiates a collective reduction operation which must be completed in a separate completion call. Once initiated, the operation may progress independently of any computation or other communication at participating processes. In this manner, non-blocking reduction operations can mitigate possible synchronizing eﬀects of reduction operations by running them in the “background.”

All completion calls (e.g., MPI_Wait) are supported for non-blocking reduction operations.

Requirements

Product	Microsoft MPI v7
Header	Mpi.h; Mpif.h
Library	Msmpi.lib
DLL	Msmpi.dll

Share via