|
|
@@ -320,6 +320,39 @@ application can prune the task for loops according to the data distribution,
|
|
|
so as to only submit tasks on nodes which have to care about them (either to
|
|
|
execute them, or to send the required data).
|
|
|
|
|
|
+A way to do some of this quite easily can be to just add an <c>if</c> like this:
|
|
|
+
|
|
|
+\code{.c}
|
|
|
+ for(loop=0 ; loop<niter; loop++)
|
|
|
+ for (x = 1; x < X-1; x++)
|
|
|
+ for (y = 1; y < Y-1; y++)
|
|
|
+ if (my_distrib(x,y,size) == my_rank
|
|
|
+ || my_distrib(x-1,y,size) == my_rank
|
|
|
+ || my_distrib(x+1,y,size) == my_rank
|
|
|
+ || my_distrib(x,y-1,size) == my_rank
|
|
|
+ || my_distrib(x,y+1,size) == my_rank)
|
|
|
+ starpu_mpi_insert_task(MPI_COMM_WORLD, &stencil5_cl,
|
|
|
+ STARPU_RW, data_handles[x][y],
|
|
|
+ STARPU_R, data_handles[x-1][y],
|
|
|
+ STARPU_R, data_handles[x+1][y],
|
|
|
+ STARPU_R, data_handles[x][y-1],
|
|
|
+ STARPU_R, data_handles[x][y+1],
|
|
|
+ 0);
|
|
|
+ starpu_task_wait_for_all();
|
|
|
+\endcode
|
|
|
+
|
|
|
+This permits to drop the cost of function call argument passing and parsing.
|
|
|
+
|
|
|
+If the <c>my_distrib</c> function can be inlined by the compiler, the latter can
|
|
|
+improve the test.
|
|
|
+
|
|
|
+If the <c>size</c> can be made a compile-time constant, the compiler can
|
|
|
+considerably improve the test further.
|
|
|
+
|
|
|
+If the distribution function is not too complex and the compiler is very good,
|
|
|
+the latter can even optimize the <c>for</c> loops, thus dramatically reducing
|
|
|
+the cost of task submission.
|
|
|
+
|
|
|
A function starpu_mpi_task_build() is also provided with the aim to
|
|
|
only construct the task structure. All MPI nodes need to call the
|
|
|
function, only the node which is to execute the task will return a
|
