void
sor (float **current_ptr, float **next_ptr)
{
int i, j, my_start, my_end, my_num_rows;
float *U_Curr_Above = (float *) shmalloc ((sizeof (float)) * ((int) floor (WIDTH / H))); /* 1d array holding values from bottom row of PE above */
float *U_Curr_Below = (float *) shmalloc ((sizeof (float)) * ((int) floor (WIDTH / H))); /* 1d array holding values from top row of PE below */
float *U_Send_Buffer = (float *) shmalloc ((sizeof (float)) * ((int) floor (WIDTH / H))); /* 1d array holding values that are currently being sent */
//float U_Curr_Above[(int)floor(WIDTH/H)]; /* 1d array holding values from bottom row of PE above */
//float U_Curr_Below[(int)floor(WIDTH/H)]; /* 1d array holding values from top row of PE below */
//float U_Send_Buffer[(int)floor(WIDTH/H)]; /* 1d array holding values that are currently being sent */
float W = 1.5;
//MPI_Request request;
//MPI_Status status;
//MPI_Comm_size(MPI_COMM_WORLD,&p);
//MPI_Comm_rank(MPI_COMM_WORLD,&my_rank);
my_start = get_start (my_rank);
my_end = get_end (my_rank);
my_num_rows = get_num_rows (my_rank);
/*
* Communicating ghost rows - only bother if p > 1
*/
if (p > 1)
{
/* send/receive bottom rows */
if (my_rank < (p - 1))
{
/* populate send buffer with bottow row */
for (i = 0; i < (int) floor (WIDTH / H); i++)
{
U_Send_Buffer[i] = current_ptr[my_num_rows - 1][i];
}
/* non blocking send */
//MPI_Isend(U_Send_Buffer,(int)floor(WIDTH/H),MPI_FLOAT,my_rank+1,0,MPI_COMM_WORLD,&request);
shmem_float_put (U_Curr_Above, U_Send_Buffer,
(int) floor (WIDTH / H), my_rank + 1);
}
//if (my_rank > ROOT) {
/* blocking receive */
//MPI_Recv(U_Curr_Above,(int)floor(WIDTH/H),MPI_FLOAT,my_rank-1,0,MPI_COMM_WORLD,&status);
//}
//MPI_Barrier(MPI_COMM_WORLD);
shmem_barrier_all ();
/* send/receive top rows */
if (my_rank > ROOT)
{
/* populate send buffer with top row */
for (i = 0; i < (int) floor (WIDTH / H); i++)
{
U_Send_Buffer[i] = current_ptr[0][i];
}
/* non blocking send */
//MPI_Isend(U_Send_Buffer,(int)floor(WIDTH/H),MPI_FLOAT,my_rank-1,0,MPI_COMM_WORLD,&request);
shmem_float_put (U_Curr_Below, U_Send_Buffer,
(int) floor (WIDTH / H), my_rank - 1);
}
//if (my_rank < (p-1)) {
/* blocking receive */
//MPI_Recv(U_Curr_Below,(int)floor(WIDTH/H),MPI_FLOAT,my_rank+1,0,MPI_COMM_WORLD,&status);
//}
//MPI_Barrier(MPI_COMM_WORLD);
shmem_barrier_all ();
}
/* solve next reds (i+j odd) */
for (j = my_start; j <= my_end; j++)
{
for (i = 0; i < (int) floor (WIDTH / H); i++)
{
if ((i + j) % 2 != 0)
{
next_ptr[j - my_start][i] =
get_val_par (U_Curr_Above, current_ptr, U_Curr_Below, my_rank,
i, j) + (W / 4) * (get_val_par (U_Curr_Above,
current_ptr,
U_Curr_Below,
my_rank, i - 1,
j) +
get_val_par (U_Curr_Above,
current_ptr,
U_Curr_Below,
my_rank, i + 1,
j) +
get_val_par (U_Curr_Above,
current_ptr,
U_Curr_Below,
my_rank, i,
j - 1) +
get_val_par (U_Curr_Above,
current_ptr,
U_Curr_Below,
my_rank, i,
j + 1) -
4 *
(get_val_par
(U_Curr_Above, current_ptr,
U_Curr_Below, my_rank, i,
j)) - (pow (H, 2) * f (i,
j)));
enforce_bc_par (next_ptr, my_rank, i, j);
}
}
}
/* solve next blacks (i+j) even .... using next reds */
for (j = my_start; j <= my_end; j++)
{
for (i = 0; i < (int) floor (WIDTH / H); i++)
{
if ((i + j) % 2 == 0)
{
next_ptr[j - my_start][i] =
get_val_par (U_Curr_Above, current_ptr, U_Curr_Below, my_rank,
i, j) + (W / 4) * (get_val_par (U_Curr_Above,
next_ptr,
U_Curr_Below,
my_rank, i - 1,
j) +
get_val_par (U_Curr_Above,
next_ptr,
U_Curr_Below,
my_rank, i + 1,
j) +
get_val_par (U_Curr_Above,
next_ptr,
U_Curr_Below,
my_rank, i,
j - 1) +
get_val_par (U_Curr_Above,
next_ptr,
U_Curr_Below,
my_rank, i,
j + 1) -
4 *
(get_val_par
(U_Curr_Above, next_ptr,
U_Curr_Below, my_rank, i,
j)) - (pow (H, 2) * f (i,
j)));
enforce_bc_par (next_ptr, my_rank, i, j);
}
}
}
shfree(U_Send_Buffer);
shfree(U_Curr_Below);
shfree(U_Curr_Above);
}
void jacobi (float ** current_ptr,float ** next_ptr) {
int i,j,p,my_rank,my_start,my_end,my_num_rows;
float U_Curr_Above[(int)floor(WIDTH/H)]; /* 1d array holding values from bottom row of PE above */
float U_Curr_Below[(int)floor(WIDTH/H)]; /* 1d array holding values from top row of PE below */
float U_Send_Buffer[(int)floor(WIDTH/H)]; /* 1d array holding values that are currently being sent */
MPI_Request request;
MPI_Status status;
MPI_Comm_size(MPI_COMM_WORLD,&p);
MPI_Comm_rank(MPI_COMM_WORLD,&my_rank);
my_start = get_start(my_rank);
my_end = get_end(my_rank);
my_num_rows = get_num_rows(my_rank);
/*
* Communicating ghost rows - only bother if p > 1
*/
if (p > 1) {
/* send/receive bottom rows */
if (my_rank < (p-1)) {
/* populate send buffer with bottow row */
for (i=0;i<(int)floor(WIDTH/H);i++) {
U_Send_Buffer[i] = current_ptr[my_num_rows-1][i];
}
/* non blocking send */
MPI_Isend(U_Send_Buffer,(int)floor(WIDTH/H),MPI_FLOAT,my_rank+1,0,MPI_COMM_WORLD,&request);
}
if (my_rank > ROOT) {
/* blocking receive */
MPI_Recv(U_Curr_Above,(int)floor(WIDTH/H),MPI_FLOAT,my_rank-1,0,MPI_COMM_WORLD,&status);
}
MPI_Barrier(MPI_COMM_WORLD);
/* send/receive top rows */
if (my_rank > ROOT) {
/* populate send buffer with top row */
for (i=0;i<(int)floor(WIDTH/H);i++) {
U_Send_Buffer[i] = current_ptr[0][i];
}
/* non blocking send */
MPI_Isend(U_Send_Buffer,(int)floor(WIDTH/H),MPI_FLOAT,my_rank-1,0,MPI_COMM_WORLD,&request);
}
if (my_rank < (p-1)) {
/* blocking receive */
MPI_Recv(U_Curr_Below,(int)floor(WIDTH/H),MPI_FLOAT,my_rank+1,0,MPI_COMM_WORLD,&status);
}
MPI_Barrier(MPI_COMM_WORLD);
}
/* Jacobi method using global addressing */
for (j=my_start;j<=my_end;j++) {
for (i=0;i<(int)floor(WIDTH/H);i++) {
next_ptr[j-my_start][i] = .25*(get_val_par(U_Curr_Above,current_ptr,U_Curr_Below,my_rank,i-1,j)
+ get_val_par(U_Curr_Above,current_ptr,U_Curr_Below,my_rank,i+1,j)
+ get_val_par(U_Curr_Above,current_ptr,U_Curr_Below,my_rank,i,j-1)
+ get_val_par(U_Curr_Above,current_ptr,U_Curr_Below,my_rank,i,j+1)
- (pow(H,2)*f(i,j)));
enforce_bc_par(next_ptr,my_rank,i,j);
}
}
}