7.12.2. Nonblocking Broadcast
Up: Nonblocking Collective Operations
Next: Example using MPI_IBCAST
Previous: Nonblocking Barrier Synchronization
| MPI_IBCAST(buffer, count, datatype, root, comm, request) |
| INOUT buffer | starting address of buffer (choice) |
| IN count | number of entries in buffer (nonnegative integer) |
| IN datatype | datatype of buffer (handle) |
| IN root | rank of broadcast root (integer) |
| IN comm | communicator (handle) |
| OUT request | communication request (handle) |
C binding
int MPI_Ibcast(void *buffer, int count, MPI_Datatype datatype, int root, MPI_Comm comm, MPI_Request *request)
int MPI_Ibcast_c(void *buffer, MPI_Count count, MPI_Datatype datatype, int root, MPI_Comm comm, MPI_Request *request)
Fortran 2008 binding
MPI_Ibcast(buffer, count, datatype, root, comm, request, ierror)
TYPE(*), DIMENSION(..), ASYNCHRONOUS :: buffer
INTEGER, INTENT(IN) :: count, root
TYPE(MPI_Datatype), INTENT(IN) :: datatype
TYPE(MPI_Comm), INTENT(IN) :: comm
TYPE(MPI_Request), INTENT(OUT) :: request
INTEGER, OPTIONAL, INTENT(OUT) :: ierror
MPI_Ibcast(buffer, count, datatype, root, comm, request, ierror) !(_c)
TYPE(*), DIMENSION(..), ASYNCHRONOUS :: buffer
INTEGER(KIND=MPI_COUNT_KIND), INTENT(IN) :: count
TYPE(MPI_Datatype), INTENT(IN) :: datatype
INTEGER, INTENT(IN) :: root
TYPE(MPI_Comm), INTENT(IN) :: comm
TYPE(MPI_Request), INTENT(OUT) :: request
INTEGER, OPTIONAL, INTENT(OUT) :: ierror
Fortran binding
MPI_IBCAST(BUFFER, COUNT, DATATYPE, ROOT, COMM, REQUEST, IERROR)
<type> BUFFER(*)
INTEGER COUNT, DATATYPE, ROOT, COMM, REQUEST, IERROR
This call starts a nonblocking variant of MPI_BCAST (see
Section Broadcast).
Up: Nonblocking Collective Operations
Next: Example using MPI_IBCAST
Previous: Nonblocking Barrier Synchronization
7.12.2.1. Example using MPI_IBCAST
Up: Nonblocking Broadcast
Next: Nonblocking Gather
Previous: Nonblocking Broadcast
The example in this section uses an intra-communicator.
Example
Start a broadcast of 100 ints from MPI process 0 to every MPI process in the
group, perform some computation on independent data, and then complete
the outstanding broadcast operation.
MPI_Comm comm;
int array1[100], array2[100];
int root=0;
MPI_Request req;
...
MPI_Ibcast(array1, 100, MPI_INT, root, comm, &req);
compute(array2, 100);
MPI_Wait(&req, MPI_STATUS_IGNORE);
Up: Nonblocking Broadcast
Next: Nonblocking Gather
Previous: Nonblocking Broadcast
Return to MPI-5.0 Standard Index
Return to MPI Forum Home Page
(Unofficial) MPI-5.0 of June 9, 2025
HTML Generated on March 2, 2025