Write a program to measure the time it takes to send 1, 2, 4, ..., 1M C
doubles from one processor to another using MPI_Ssend and MPI_Recv.  Use the
same techniques as in the memcpy assignment to average out variations and
overhead in MPI_Wtime.  In this version, use an MPI_COMM_WORLD that has more
than 2 processes (the more the better).  Have each process send and receive
with the process <CODE>size/2</CODE> away, where there are <CODE>size</CODE>
processes in MPI_COMM_WORLD.
<P>
Print the size, time, and rate in MB/sec for each test.
<P>
Make sure that both sender and reciever are ready when you begin the test.
The sample solution uses MPI_Sendrecv, as well
as MPI_Barrier to ensure that the various pairs start nearly together, but
other choices are possible. 
