Send and Receive MPI Send and Receive Sending

Send and Receive

MPI Send and Receive • Sending and receiving are two foundational concepts of MPI • Almost every single function in MPI can be implemented with basic send and receive calls

Overview of Sending and Receiving • MPI’s send and receive calls operate in the following manner - Process 0 tries to send a message to process 1 - Process 0 packages the data into a buffer - Route the message to the right location -The location is defined by the process’s rank - Process 1 needs to acknowledge to want to receive 0’s data - Once process 1 acknowledges this, the data has been transmitted - Process 0 may go back to work

Overview of Sending and Receiving • If Process 0 has to send different types of messages to processor 1 - MPI allows senders and receivers to specify message IDs with the message (tags) - Process 1 can request a message with a certain tag number - Messages with different tag numbers will be buffered until Processor is ready to receive them

Overview of Sending and Receiving • Prototypes for MPI sending and receiving functions MPI_Send(void* data, int count, MPI_Datatype datatype, int destination, int tag, MPI_Comm communicator) MPI_Recv(void* data, int count, MPI_Datatype datatype, int source, int tag, MPI_Comm communicator, MPI_Status* status)

Overview of Sending and Receiving • The first argument is the data buffer • The second and third arguments describe the count and type of elements that reside in the buffer • MPI_Send sends the exact count of elements • MPI_Recv will receive at most the count of elements • The fourth and fifth arguments specify the rank of the sending/receiving process and the tag of the message • The sixth argument specifies the communicator • The last argument (for MPI_Recv only) provides information about the received message

MPI Data Types

Example 1 // Find out rank, size int world_rank; MPI_Comm_rank(MPI_COMM_WORLD, &world_rank); int world_size; MPI_Comm_size(MPI_COMM_WORLD, &world_size); int number; if (world_rank == 0) { number = -1; MPI_Send(&number, 1, MPI_INT, 1, 0, MPI_COMM_WORLD); } else if (world_rank == 1) { MPI_Recv(&number, 1, MPI_INT, 0, 0, MPI_COMM_WORLD, MPI_STATUS_IGNORE); printf("Process 1 received number %d from process 0n", number); }

Example 2 int token; if (world_rank != 0) { MPI_Recv(&token, 1, MPI_INT, world_rank - 1, 0, MPI_COMM_WORLD, MPI_STATUS_IGNORE); printf("Process %d received token %d from process %dn", world_rank, token, world_rank - 1); } else { // Set the token's value if you are process 0 token = -1; } MPI_Send(&token, 1, MPI_INT, (world_rank + 1) % world_size, 0, MPI_COMM_WORLD); // Now process 0 can receive from the last process. if (world_rank == 0) { MPI_Recv(&token, 1, MPI_INT, world_size - 1, 0, MPI_COMM_WORLD, MPI_STATUS_IGNORE); printf("Process %d received token %d from process %dn", world_rank, token, world_size - 1); }

Example 2 • Initialize a value from process 0, and the value is passed around every single process • Terminates when process zero receives the value from the last process • Extra care is taken to assure that it doesn’t deadlock • Process 0 makes sure that it has completed its first send before it tries to receive the value from the last process • All of the other processes simply call MPI_Recv (receiving from their neighboring lower process) and then MPI_Send (sending the value to their neighboring higher process) to pass the value along the ring

Example 2 Process 1 received token -1 from process 0 Process 2 received token -1 from process 1 Process 3 received token -1 from process 2 Process 4 received token -1 from process 3 Process 0 received token -1 from process 4