int main() {
InitializeMatrix(A);
InitializeMatrix(B);
MultiplyMatricesParallel();
PrintMatrix(A);
PrintMatrix(B);
PrintMatrix(C);
Verify();
return 0;
}
void LUmatrixSeparation(mtxMatrix ilu, int *uptr, mtxMatrix &L, mtxMatrix &U)
{
int countL, countU;
int i, j, s, f, k;
double *val;
int *col;
countU = 0;
for(i = 0; i < ilu.N; i++)
{
countU += (ilu.RowIndex[i+1] - uptr[i]);
}
countL = ilu.NZ + ilu.N - countU;
InitializeMatrix(ilu.N, countL, L);
InitializeMatrix(ilu.N, countU, U);
k = 0;
val = L.Value; col = L.Col;
L.RowIndex[0] = k;
for(i = 0; i < ilu.N; i++)
{
s = ilu.RowIndex[i];
f = uptr[i];
for(j = s; j < f; j++)
{
val[k] = ilu.Value[j];
col[k] = ilu.Col[j];
k++;
}
val[k] = 1.0; col[k] = i;
k++;
L.RowIndex[i + 1] = k;
}
k = 0;
val = U.Value;
col = U.Col;
U.RowIndex[0] = k;
for(i = 0; i < ilu.N; i++)
{
s = uptr[i];
f = ilu.RowIndex[i + 1];
for(j = s; j < f; j++)
{
val[k] = ilu.Value[j];
col[k] = ilu.Col[j];
k++;
}
U.RowIndex[i + 1] = k;
}
}
//----------------------------------------------------------------------------
// Main function
int main(int argc, char* argv[])
{
int i,j;
double **Result_Seq;
int no_thrd;
if(argc != 3)
{
fprintf(stderr, "missing arguments\n", argv[0]);
exit(1);
}
//N =3;
//no_thrd = 2;
N = atoi(argv[1]);
no_thrd = atoi(argv[2]);
InitializeMatrix();
Result_Seq = MatMul();
// row and column initialization
row =0;
col=0;
MatMul_thrd(no_thrd);
if(Check_result(Result_Seq))
printf("\n----------------Results are same for both versions-------------------\n\n");
else
printf("\n-----#####----Error: Both result are not same-------####---------\n\n");
return 0;
}
int main(int argc, char **argv)
{
int iterations = 0;
double startTime = 0;
double endTime = 0;
double totalTime = 0;
int processorsAvailable;
// Generate the matrix.
InitializeMatrix();
// Initialize MPI API.
MPI_Init(&argc, &argv);
MPI_Comm_rank(MPI_COMM_WORLD, &processorRank);
MPI_Comm_size(MPI_COMM_WORLD, &processorsAvailable);
// Ask for number of processors to be used. Loop if input is invalid.
int processorsUsed = 1;
while (processorsUsed != 1 && processorsUsed != 2 && processorsUsed != 4)
{
fflush(stdin);
printf("How many processors should be used in the cluster? [1, 2, 4]: ");
scanf("%d", &processorsUsed);
}
//==================================================//
// V V V MASTERS CODE BLOCK V V V //
//==================================================//
if(processorRank == 0)
{
if(DEBUG)
{
printf("%d processors will be used.\n", processorsUsed);
printf("\n>> Running LaPlace approximation...\n\n");
}
// Start the timer.
startTime = MPI_Wtime();
// 1 processor used, the master does all the work (SEQUENTIAL).
if(processorsUsed == 1)
{
// Start the timer.
startTime = MPI_Wtime();
iterations = SequentialApproximation();
// If we reached to many iterations, quit.
if(iterations > 100000)
{
return 0;
}
}
// 2 processors used, the master and one worker.
else if(processorsUsed == 2)
{
iterations = MasterBlockedApproximation(2);
}
// 4 processors used, the master and all three workers.
else if(processorsUsed == 4)
{
iterations = MasterBlockedApproximation(4);
}
// Stop the timer.
endTime = MPI_Wtime();
printf("[SUCCESS] LaPlace approximation finished.\n");
if(DEBUG)
{
printf("\n>> Printing matrix... \n\n");
PrintMatrix();
}
// Output time taken.
totalTime = (endTime - startTime);
printf("Execution time on %2d nodes: %f\n", processorsUsed, totalTime);
}
//==================================================//
// ^ ^ ^ MASTERS CODE BLOCK ^ ^ ^ //
//==================================================//
//==================================================//
// V V V WORKER CODE BLOCK V V V //
//==================================================//
else if(processorRank < processorsUsed)
{
// 2 processors used, the master and one worker.
if(processorsUsed == 2)
{
// Worker 2 part.
if(processorRank == 1)
{
WorkerBlockedApproximation();
}
}
// 4 processors used, the master and all three workers.
else if(processorsUsed == 4)
{
// Worker 2 part.
if(processorRank == 1)
{
WorkerBlockedApproximation();
}
// Worker 3 part.
else if(processorRank == 2)
{
WorkerBlockedApproximation();
}
// Worker 4 part.
else if(processorRank == 3)
{
WorkerBlockedApproximation();
}
}
}
//==================================================//
// ^ ^ ^ WORKER CODE BLOCK ^ ^ ^ //
//==================================================//
// Finalize the MPI API, and then quit.
MPI_Finalize();
return 0;
}
int main(int argc, char *argv[]) {
FILE *input_file, *output_file, *time_file;
if (argc < 4) {
fprintf(stderr, "Invalid input parameters\n");
fprintf(stderr, "Usage: %s inputfile outputfile timefile \n", argv[0]);
exit(1);
}
else {
input_file = fopen(argv[1], "r");
output_file = fopen(argv[2], "w");
time_file = fopen(argv[3], "w");
if (!input_file || !output_file || !time_file)
exit(1);
}
MM_typecode matcode;
if (mm_read_banner(input_file, &matcode) != 0) {
printf("Could not process Matrix Market banner.\n");
exit(1);
}
if (!mm_is_matrix(matcode) || !mm_is_real(matcode) || !mm_is_coordinate(matcode)) {
printf("Sorry, this application does not support ");
printf("Market Market type: [%s]\n", mm_typecode_to_str(matcode));
exit(1);
}
mtxMatrix inputMatrix, fullMatrix, LMatrix, UMatrix, UMatrixTranspose, MMatrix;
ReadMatrix(inputMatrix, input_file);
Timer timer;
getRowIndex(&inputMatrix, inputMatrix.RowIndex);
inputMatrix.RowIndex[inputMatrix.N] = inputMatrix.NZ;
int diagNum = 0;
for (int i = 0; i < inputMatrix.N; i++) {
for (int j = inputMatrix.RowIndex[i]; j < inputMatrix.RowIndex[i + 1]; j++) {
if (i == inputMatrix.Col[j]) diagNum++;
}
}
if (mm_is_symmetric(matcode)) {
InitializeMatrix(inputMatrix.N, 2 * inputMatrix.NZ - diagNum, fullMatrix);
TriangleToFull(&inputMatrix, &fullMatrix);
FreeMatrix(inputMatrix);
}
else {
fullMatrix = inputMatrix;
}
int *diag = new int[fullMatrix.N];
for (int i = 0; i < fullMatrix.N; i++) {
for (int j = fullMatrix.RowIndex[i]; j < fullMatrix.RowIndex[i + 1]; j++) {
if (i == fullMatrix.Col[j]) diag[i] = j;
}
}
// for (int i = 0; i < fullMatrix.N + 1; i++) {
// printf("RowIndex[%i] = %i\n", i, fullMatrix.RowIndex[i]);
// }
//
//
// for (int i = 0; i < fullMatrix.N; i++) {
// printf("input[%i]= %lf\n", i, fullMatrix.Value[inputMatrix.RowIndex[i]]);
// }
//
// for (int i = 0; i < fullMatrix.N; i++) {
// printf("diag[%i]= %d\n", i, diag[i]);
// }
timer.start();
ilu0(fullMatrix, fullMatrix.Value, diag);
LUmatrixSeparation(fullMatrix, diag, LMatrix, UMatrix);
Transpose(UMatrix, UMatrixTranspose);
Multiplicate(LMatrix, UMatrixTranspose, MMatrix);
timer.stop();
std::ofstream timeLog;
timeLog.open(argv[3]);
timeLog << timer.getElapsed();
WriteFullMatrix(MMatrix, output_file, matcode);
FreeMatrix(fullMatrix);
return 0;
}
