Rank 6 choosing device 2 out of 4
Rank 5 choosing device 1 out of 4
Rank 7 choosing device 3 out of 4
Rank 4 choosing device 0 out of 4
Rank 0 choosing device 0 out of 4
Standard lattice layout:
 4 dimensions
 Node remapping: TRIVIAL (no effort made to reorder)

 Sites on node: 32 x 16 x 16 x 16
 Processor layout: 1 x 2 x 2 x 2
Rank 2 choosing device 2 out of 4
Rank 1 choosing device 1 out of 4
Rank 3 choosing device 3 out of 4
Matrix * Matrix: 0.932617ms 
Vector * Matrix: 0.378418 ms 
Vector square sum: 0.546875 ms 
Dirac 4 dirs: 3.80859ms 
Dirac: 4.45312ms 
CG: 8.04688ms / iteration
 COMMS from node 0: 1028 done, 9712(90.4283%) optimized away
