compute Jacobi on cpu4 |
Move Jacobi from d1 to ctl11 |
move Jacobi from ctl11 to ctl21 |
move Jacobi from ctl21 to mem1 |
move Jacobi from mem1 to ctl21 |
move Jacobi from ctl21 to network0 |
move Jacobi from network0 to ctl20 |
move Jacobi from ctl20 to mem0 |
move Jacobi from mem0 to cpu0 |
compute Jacobi on cpu0 |
move Jacobi from mem1 to ctl21 |
move Jacobi from ctl21 to network0 |
move Jacobi from network0 to ctl22 |
move Jacobi from ctl22 to mem2 |
move Jacobi from mem2 to cpu2 |
compute Jacobi on cpu2 |
move Jacobi from mem1 to ctl21 |
move Jacobi from ctl21 to network0 |
move Jacobi from network0 to ctl25 |
move Jacobi from ctl25 to mem5 |
move Jacobi from mem5 to cpu5 |
compute Jacobi on cpu5 |
Move Jacobi from d0 to ctl10 |
move Jacobi from ctl10 to ctl20 |
move Jacobi from ctl20 to mem0 |
move Jacobi from mem0 to ctl20 |
move Jacobi from ctl20 to network0 |
move Jacobi from network0 to ctl21 |
move Jacobi from ctl21 to mem1 |
move Jacobi from mem1 to cpu1 |
compute Jacobi on cpu1 |
move Jacobi from mem0 to ctl20 |
move Jacobi from ctl20 to network0 |
move Jacobi from network0 to ctl24 |
move Jacobi from ctl24 to mem4 |
move Jacobi from mem4 to cpu4 |
Also a simpler data parallel version |