-
Run testcases with mvapich2
-
Complete the graphs in paper
-
-
Test the scalability of parconnect
-
Bigger test range in ap, ap_lb
-
Slower than intel mpi
-
More unstable than intel mpi
-
There are 3 graphs in paper
-
Computation and communication with iteration
-
The tuple count with each iteration
-
The benchmark
-
Write script to estimate execution time
-
Rerun the entire workflow
-
Support other ap