129 |
|
|
130 |
C-- Always cumulate tile local-sum in the same order by applying MPI allreduce |
C-- Always cumulate tile local-sum in the same order by applying MPI allreduce |
131 |
C to array of tiles ; can get slower with large number of tiles (big set-up) |
C to array of tiles ; can get slower with large number of tiles (big set-up) |
132 |
#undef GLOBAL_SUM_ORDER_TILES |
#define GLOBAL_SUM_ORDER_TILES |
133 |
|
|
134 |
C-- Alternative way of doing global sum without MPI allreduce call |
C-- Alternative way of doing global sum without MPI allreduce call |
135 |
C but instead, explicit MPI send & recv calls. Expected to be slower. |
C but instead, explicit MPI send & recv calls. Expected to be slower. |