Update README.md

README.md

@@ -29,10 +29,10 @@ The resulting executable `rankdlb` can be run using mpirun.  It takes three argu
 
 To run the kernel execute
 ```
-mpirun -np <num processes> rankdlb <cycles> <items_per_rank_initial> <max_items_per_rank>
+mpirun -np <num processes> ./rankdlb <cycles> <items_per_rank_initial> <max_items_per_rank>
 ```
 
-For example: mpirun -np 16 1000 100000 150000
+For example: mpirun -np 16 ./rankdlb 1000 100000 150000
 
 The kernel continuously reports the rate at which it processes work items. A higher value indicates better load balance. It can be seen that the rate drops while rank 0 creates new work items. The rate increaes again when load balcing was performed.