212. Communication Calls


Up: Contents Next: Put Previous: Window Attributes

MPI supports three RMA communication calls: MPI_PUT transfers data from the caller memory (origin) to the target memory; MPI_GET transfers data from the target memory to the caller memory; and MPI_ACCUMULATE updates locations in the target memory, e.g. by adding to these locations values sent from the caller memory. These operations are nonblocking: the call initiates the transfer, but the transfer may continue after the call returns. The transfer is completed, both at the origin and at the target, when a subsequent synchronization call is issued by the caller on the involved window object. These synchronization calls are described in Section Synchronization Calls , page Synchronization Calls .

The local communication buffer of an RMA call should not be updated, and the local communication buffer of a get call should not be accessed after the RMA call, until the subsequent synchronization call completes.


Rationale.

The rule above is more lenient than for message-passing, where we do not allow two concurrent sends, with overlapping send buffers. Here, we allow two concurrent puts with overlapping send buffers. The reasons for this relaxation are

    1. Users do not like that restriction, which is not very natural (it prohibits concurrent reads).
    2. Weakening the rule does not prevent efficient implementation, as far as we know.


    3. Weakening the rule is important for performance of RMA: we want to associate one synchronization call with as many RMA operations is possible. If puts from overlapping buffers cannot be concurrent, then we need to needlessly add synchronization points in the code.

( End of rationale.)
It is erroneous to have concurrent conflicting accesses to the same memory location in a window; if a location is updated by a put or accumulate operation, then this location cannot be accessed by a load or another RMA operation until the updating operation has completed at the target. There is one exception to this rule; namely, the same location can be updated by several concurrent accumulate calls, the outcome being as if these updates occurred in some order. In addition, a window cannot concurrently be updated by a put or accumulate operation and by a local store operation. This, even if these two updates access different locations in the window. The last restriction enables more efficient implementations of RMA operations on many systems. These restrictions are described in more detail in Section Semantics and Correctness , page Semantics and Correctness .

The calls use general datatype arguments to specify communication buffers at the origin and at the target. Thus, a transfer operation may also gather data at the source and scatter it at the destination. However, all arguments specifying both communication buffers are provided by the caller.

For all three calls, the target process may be identical with the origin process; i.e., a process may use an RMA operation to move data in its memory.


Rationale.

The choice of supporting ``self-communication'' is the same as for message-passing. It simplifies some coding, and is very useful with accumulate operations, to allow atomic updates of local variables. ( End of rationale.)
MPI_PROC_NULL is a valid target rank in the MPI RMA calls MPI_ACCUMULATE, MPI_GET, and MPI_PUT. The effect is the same as for MPI_PROC_NULL in MPI point-to-point communication. After any RMA operation with rank MPI_PROC_NULL, it is still necessary to finish the RMA epoch with the synchronization method that started the epoch.


Up: Contents Next: Put Previous: Window Attributes

Return to MPI-2.1 Standard Index
Return to MPI Forum Home Page
MPI-2.0 of July 1, 2008
HTML Generated on July 6, 2008