|
|
@@ -38,31 +38,31 @@ initializes a token on node 0, and the token is passed from node to node,
|
|
|
incremented by one on each step. The code is not using StarPU yet.
|
|
|
|
|
|
\code{.c}
|
|
|
- for (loop = 0; loop < nloops; loop++)
|
|
|
- {
|
|
|
- int tag = loop*size + rank;
|
|
|
+for (loop = 0; loop < nloops; loop++)
|
|
|
+{
|
|
|
+ int tag = loop*size + rank;
|
|
|
|
|
|
- if (loop == 0 && rank == 0)
|
|
|
- {
|
|
|
- token = 0;
|
|
|
- fprintf(stdout, "Start with token value %d\n", token);
|
|
|
- }
|
|
|
- else
|
|
|
- {
|
|
|
- MPI_Recv(&token, 1, MPI_INT, (rank+size-1)%size, tag, MPI_COMM_WORLD);
|
|
|
- }
|
|
|
+ if (loop == 0 && rank == 0)
|
|
|
+ {
|
|
|
+ token = 0;
|
|
|
+ fprintf(stdout, "Start with token value %d\n", token);
|
|
|
+ }
|
|
|
+ else
|
|
|
+ {
|
|
|
+ MPI_Recv(&token, 1, MPI_INT, (rank+size-1)%size, tag, MPI_COMM_WORLD);
|
|
|
+ }
|
|
|
|
|
|
- token++;
|
|
|
+ token++;
|
|
|
|
|
|
- if (loop == last_loop && rank == last_rank)
|
|
|
- {
|
|
|
- fprintf(stdout, "Finished: token value %d\n", token);
|
|
|
- }
|
|
|
- else
|
|
|
- {
|
|
|
- MPI_Send(&token, 1, MPI_INT, (rank+1)%size, tag+1, MPI_COMM_WORLD);
|
|
|
- }
|
|
|
+ if (loop == last_loop && rank == last_rank)
|
|
|
+ {
|
|
|
+ fprintf(stdout, "Finished: token value %d\n", token);
|
|
|
}
|
|
|
+ else
|
|
|
+ {
|
|
|
+ MPI_Send(&token, 1, MPI_INT, (rank+1)%size, tag+1, MPI_COMM_WORLD);
|
|
|
+ }
|
|
|
+}
|
|
|
\endcode
|
|
|
|
|
|
\section NotUsingMPISupport About not using the MPI support
|
|
|
@@ -73,39 +73,39 @@ execution to StarPU. This is possible by just using starpu_data_acquire(), for
|
|
|
instance:
|
|
|
|
|
|
\code{.c}
|
|
|
- for (loop = 0; loop < nloops; loop++)
|
|
|
- {
|
|
|
- int tag = loop*size + rank;
|
|
|
+for (loop = 0; loop < nloops; loop++)
|
|
|
+{
|
|
|
+ int tag = loop*size + rank;
|
|
|
|
|
|
- /* Acquire the data to be able to write to it */
|
|
|
- starpu_data_acquire(token_handle, STARPU_W);
|
|
|
- if (loop == 0 && rank == 0)
|
|
|
- {
|
|
|
- token = 0;
|
|
|
- fprintf(stdout, "Start with token value %d\n", token);
|
|
|
- }
|
|
|
- else
|
|
|
- {
|
|
|
- MPI_Recv(&token, 1, MPI_INT, (rank+size-1)%size, tag, MPI_COMM_WORLD);
|
|
|
- }
|
|
|
+ /* Acquire the data to be able to write to it */
|
|
|
+ starpu_data_acquire(token_handle, STARPU_W);
|
|
|
+ if (loop == 0 && rank == 0)
|
|
|
+ {
|
|
|
+ token = 0;
|
|
|
+ fprintf(stdout, "Start with token value %d\n", token);
|
|
|
+ }
|
|
|
+ else
|
|
|
+ {
|
|
|
+ MPI_Recv(&token, 1, MPI_INT, (rank+size-1)%size, tag, MPI_COMM_WORLD);
|
|
|
+ }
|
|
|
starpu_data_release(token_handle);
|
|
|
|
|
|
- /* Task delegation to StarPU to increment the token. The execution might
|
|
|
- * be performed on a CPU, a GPU, etc. */
|
|
|
- increment_token();
|
|
|
+ /* Task delegation to StarPU to increment the token. The execution might
|
|
|
+ * be performed on a CPU, a GPU, etc. */
|
|
|
+ increment_token();
|
|
|
|
|
|
- /* Acquire the update data to be able to read from it */
|
|
|
- starpu_data_acquire(token_handle, STARPU_R);
|
|
|
- if (loop == last_loop && rank == last_rank)
|
|
|
- {
|
|
|
- fprintf(stdout, "Finished: token value %d\n", token);
|
|
|
- }
|
|
|
- else
|
|
|
- {
|
|
|
- MPI_Send(&token, 1, MPI_INT, (rank+1)%size, tag+1, MPI_COMM_WORLD);
|
|
|
- }
|
|
|
- starpu_data_release(token_handle);
|
|
|
+ /* Acquire the update data to be able to read from it */
|
|
|
+ starpu_data_acquire(token_handle, STARPU_R);
|
|
|
+ if (loop == last_loop && rank == last_rank)
|
|
|
+ {
|
|
|
+ fprintf(stdout, "Finished: token value %d\n", token);
|
|
|
}
|
|
|
+ else
|
|
|
+ {
|
|
|
+ MPI_Send(&token, 1, MPI_INT, (rank+1)%size, tag+1, MPI_COMM_WORLD);
|
|
|
+ }
|
|
|
+ starpu_data_release(token_handle);
|
|
|
+}
|
|
|
\endcode
|
|
|
|
|
|
In that case, <c>libstarpumpi</c> is not needed. One can also use <c>MPI_Isend()</c> and
|
|
|
@@ -167,8 +167,7 @@ int main(int argc, char **argv)
|
|
|
}
|
|
|
else
|
|
|
{
|
|
|
- starpu_mpi_irecv_detached(token_handle, (rank+size-1)%size, tag,
|
|
|
- MPI_COMM_WORLD, NULL, NULL);
|
|
|
+ starpu_mpi_irecv_detached(token_handle, (rank+size-1)%size, tag, MPI_COMM_WORLD, NULL, NULL);
|
|
|
}
|
|
|
|
|
|
increment_token();
|
|
|
@@ -181,8 +180,7 @@ int main(int argc, char **argv)
|
|
|
}
|
|
|
else
|
|
|
{
|
|
|
- starpu_mpi_isend_detached(token_handle, (rank+1)%size, tag+1,
|
|
|
- MPI_COMM_WORLD, NULL, NULL);
|
|
|
+ starpu_mpi_isend_detached(token_handle, (rank+1)%size, tag+1, MPI_COMM_WORLD, NULL, NULL);
|
|
|
}
|
|
|
}
|
|
|
|
|
|
@@ -316,14 +314,12 @@ static int complex_pack_data(starpu_data_handle_t handle, unsigned node, void **
|
|
|
{
|
|
|
STARPU_ASSERT(starpu_data_test_if_allocated_on_node(handle, node));
|
|
|
|
|
|
- struct starpu_complex_interface *complex_interface =
|
|
|
- (struct starpu_complex_interface *) starpu_data_get_interface_on_node(handle, node);
|
|
|
+ struct starpu_complex_interface *complex_interface = (struct starpu_complex_interface *) starpu_data_get_interface_on_node(handle, node);
|
|
|
|
|
|
*count = complex_get_size(handle);
|
|
|
starpu_malloc_flags(ptr, *count, 0);
|
|
|
memcpy(*ptr, complex_interface->real, complex_interface->nx*sizeof(double));
|
|
|
- memcpy(*ptr+complex_interface->nx*sizeof(double), complex_interface->imaginary,
|
|
|
- complex_interface->nx*sizeof(double));
|
|
|
+ memcpy(*ptr+complex_interface->nx*sizeof(double), complex_interface->imaginary, complex_interface->nx*sizeof(double));
|
|
|
|
|
|
return 0;
|
|
|
}
|
|
|
@@ -332,12 +328,10 @@ static int complex_unpack_data(starpu_data_handle_t handle, unsigned node, void
|
|
|
{
|
|
|
STARPU_ASSERT(starpu_data_test_if_allocated_on_node(handle, node));
|
|
|
|
|
|
- struct starpu_complex_interface *complex_interface =
|
|
|
- (struct starpu_complex_interface *) starpu_data_get_interface_on_node(handle, node);
|
|
|
+ struct starpu_complex_interface *complex_interface = (struct starpu_complex_interface *) starpu_data_get_interface_on_node(handle, node);
|
|
|
|
|
|
memcpy(complex_interface->real, ptr, complex_interface->nx*sizeof(double));
|
|
|
- memcpy(complex_interface->imaginary, ptr+complex_interface->nx*sizeof(double),
|
|
|
- complex_interface->nx*sizeof(double));
|
|
|
+ memcpy(complex_interface->imaginary, ptr+complex_interface->nx*sizeof(double), complex_interface->nx*sizeof(double));
|
|
|
|
|
|
return 0;
|
|
|
}
|
|
|
@@ -369,8 +363,7 @@ void starpu_complex_interface_datatype_allocate(starpu_data_handle_t handle, MPI
|
|
|
MPI_Aint displacements[2];
|
|
|
MPI_Datatype types[2] = {MPI_DOUBLE, MPI_DOUBLE};
|
|
|
|
|
|
- struct starpu_complex_interface *complex_interface =
|
|
|
- (struct starpu_complex_interface *) starpu_data_get_interface_on_node(handle, STARPU_MAIN_RAM);
|
|
|
+ struct starpu_complex_interface *complex_interface = (struct starpu_complex_interface *) starpu_data_get_interface_on_node(handle, STARPU_MAIN_RAM);
|
|
|
|
|
|
MPI_Address(complex_interface, displacements);
|
|
|
MPI_Address(&complex_interface->imaginary, displacements+1);
|
|
|
@@ -461,13 +454,11 @@ data which will be needed by the tasks that we will execute.
|
|
|
int mpi_rank = my_distrib(x, y, size);
|
|
|
if (mpi_rank == my_rank)
|
|
|
/* Owning data */
|
|
|
- starpu_variable_data_register(&data_handles[x][y], STARPU_MAIN_RAM,
|
|
|
- (uintptr_t)&(matrix[x][y]), sizeof(unsigned));
|
|
|
+ starpu_variable_data_register(&data_handles[x][y], STARPU_MAIN_RAM, (uintptr_t)&(matrix[x][y]), sizeof(unsigned));
|
|
|
else if (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))
|
|
|
/* I don't own this index, but will need it for my computations */
|
|
|
- starpu_variable_data_register(&data_handles[x][y], -1,
|
|
|
- (uintptr_t)NULL, sizeof(unsigned));
|
|
|
+ starpu_variable_data_register(&data_handles[x][y], -1, (uintptr_t)NULL, sizeof(unsigned));
|
|
|
else
|
|
|
/* I know it's useless to allocate anything for this */
|
|
|
data_handles[x][y] = NULL;
|
|
|
@@ -600,7 +591,8 @@ can just pass NULL to starpu_mpi_task_insert():
|
|
|
|
|
|
\code{.c}
|
|
|
starpu_data_handle_t data0 = NULL;
|
|
|
-if (rank == 0) {
|
|
|
+if (rank == 0)
|
|
|
+{
|
|
|
starpu_variable_data_register(&data0, STARPU_MAIN_RAM, (uintptr_t) &val0, sizeof(val0));
|
|
|
starpu_mpi_data_register(data0, 0, rank);
|
|
|
}
|
|
|
@@ -615,12 +607,15 @@ data1 to node 0, which owns data and thus will need the value of data1 to execut
|
|
|
|
|
|
\code{.c}
|
|
|
starpu_data_handle_t data0 = NULL, data1, data;
|
|
|
-if (rank == 0) {
|
|
|
+if (rank == 0)
|
|
|
+{
|
|
|
starpu_variable_data_register(&data0, STARPU_MAIN_RAM, (uintptr_t) &val0, sizeof(val0));
|
|
|
starpu_mpi_data_register(data0, -1, rank);
|
|
|
starpu_variable_data_register(&data1, -1, 0, sizeof(val1));
|
|
|
starpu_variable_data_register(&data, STARPU_MAIN_RAM, (uintptr_t) &val, sizeof(val));
|
|
|
-} else if (rank == 1) {
|
|
|
+}
|
|
|
+else if (rank == 1)
|
|
|
+{
|
|
|
starpu_variable_data_register(&data1, STARPU_MAIN_RAM, (uintptr_t) &val1, sizeof(val1));
|
|
|
starpu_variable_data_register(&data, -1, 0, sizeof(val));
|
|
|
}
|
|
|
@@ -641,10 +636,13 @@ starpu_variable_data_register(&pernode, -1, 0, sizeof(val));
|
|
|
starpu_mpi_data_register(pernode, -1, STARPU_MPI_PER_NODE);
|
|
|
|
|
|
/* Normal data: one on node0, one on node1 */
|
|
|
-if (rank == 0) {
|
|
|
+if (rank == 0)
|
|
|
+{
|
|
|
starpu_variable_data_register(&data0, STARPU_MAIN_RAM, (uintptr_t) &val0, sizeof(val0));
|
|
|
starpu_variable_data_register(&data1, -1, 0, sizeof(val1));
|
|
|
-} else if (rank == 1) {
|
|
|
+}
|
|
|
+else if (rank == 1)
|
|
|
+{
|
|
|
starpu_variable_data_register(&data0, -1, 0, sizeof(val1));
|
|
|
starpu_variable_data_register(&data1, STARPU_MAIN_RAM, (uintptr_t) &val1, sizeof(val1));
|
|
|
}
|
|
|
@@ -744,8 +742,7 @@ migrate the data, and register the new location.
|
|
|
|| 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)))
|
|
|
/* Register newly-needed data */
|
|
|
- starpu_variable_data_register(&data_handles[x][y], -1,
|
|
|
- (uintptr_t)NULL, sizeof(unsigned));
|
|
|
+ starpu_variable_data_register(&data_handles[x][y], -1, (uintptr_t)NULL, sizeof(unsigned));
|
|
|
if (data_handles[x][y])
|
|
|
{
|
|
|
/* Migrate the data */
|
|
|
@@ -808,14 +805,12 @@ for(x = 0; x < nblocks ; x++)
|
|
|
int mpi_rank = my_distrib(x, nodes);
|
|
|
if (rank == root)
|
|
|
{
|
|
|
- starpu_vector_data_register(&data_handles[x], STARPU_MAIN_RAM, (uintptr_t)vector[x],
|
|
|
- blocks_size, sizeof(float));
|
|
|
+ starpu_vector_data_register(&data_handles[x], STARPU_MAIN_RAM, (uintptr_t)vector[x], blocks_size, sizeof(float));
|
|
|
}
|
|
|
else if ((mpi_rank == rank) || ((rank == mpi_rank+1 || rank == mpi_rank-1)))
|
|
|
{
|
|
|
/* I own this index, or i will need it for my computations */
|
|
|
- starpu_vector_data_register(&data_handles[x], -1, (uintptr_t)NULL,
|
|
|
- block_size, sizeof(float));
|
|
|
+ starpu_vector_data_register(&data_handles[x], -1, (uintptr_t)NULL, block_size, sizeof(float));
|
|
|
}
|
|
|
else
|
|
|
{
|
Nathalie Furmento