Commit 2c56c9e0 authored by Xavier Teruel's avatar Xavier Teruel
Browse files

Update README.md

parent 5ca4bf3b
......@@ -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.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment