[mvapich-discuss] The cost of MPI_Fence()?

[Tan Guangming]

I'm implementing an algorithm using MVAPICH2 0.9.2 on Infiniband. The program 
is executed as follows:
for (i = 0; i < loops; i++) {
	MPI_Fence;
	for (dest = 0; dest < p; dest++)
		if (id != dest)
			MPI_Put; 
	computation;
	MPI_Fence;
}
The time measurement shows that the most of communication time(98%) is 
consumed by the synchronization MPI_Fence. Each message size is larger than 
100KB. 
How to optimizing the cost of synchronization?