int main(){
//declare matrix
int mat1[3][3];
int mat2[3][3];
int mat_add[3][3]; //for addition
int mat_mul[3][3]; //for multiplication
int mat_trp[3][3]; //for transpose
printf("enter the first matrix: \n");
create(mat1);
printf("enter the second matrix: \n");
create(mat2);
printf("display matrix 1:\n");
display(mat1);
printf("display matrix 2:\n");
display(mat2);
printf("addition of mat1 and mat2: \n");
matadd(mat1,mat2,mat_add);
display(mat_add);
printf("multiplication of mat1 and mat2: \n");
matadd(mat1,mat2,mat_mul);
display(mat_mul);
printf("transpose of mat1 and mat2: \n");
transpose(mat1,mat_trp);
display(mat_trp);
return 0;
}
void pure_vel_update(void)
{
int i;
double temp[3];
matmul(3, 3, (double *)p_dcm, 3, 1, (double *)p_velo_20ms, (double *)pure_vel);
//earth rate correction
cross(omg_dub, pure_v_old, temp);
matmulint(3,1,(double *)temp, eight_delt, (double *)temp);
matsub(3,1,(double *)pure_vel, (double *)temp, (double *)pure_vel);
matadd(3,1,(double *)pure_vel, (double *)pure_ecef_gravity, (double *)pure_vel);
matadd(3,1,(double *)pure_vel, (double *)pure_v_old, (double *)pure_vel);
matadd(3,1,(double *)pure_vel, (double *)pure_v_old, (double *)pure_vav);
matmulint(3,1,(double *)pure_vav, 0.5, (double *)pure_vav);
for (i = 0; i < 3; i++)
pure_v_old[i] = pure_vel[i];
}
void mgfas(double **u, int n, int maxcyc)
{
double anorm2(double **a, int n);
void copy(double **aout, double **ain, int n);
void interp(double **uf, double **uc, int nf);
void lop(double **out, double **u, int n);
void matadd(double **a, double **b, double **c, int n);
void matsub(double **a, double **b, double **c, int n);
void relax2(double **u, double **rhs, int n);
void rstrct(double **uc, double **uf, int nc);
void slvsm2(double **u, double **rhs);
unsigned int j,jcycle,jj,jm1,jpost,jpre,nf,ng=0,ngrid,nn;
double **irho[NGMAX+1],**irhs[NGMAX+1],**itau[NGMAX+1],
**itemp[NGMAX+1],**iu[NGMAX+1];
double res,trerr;
nn=n;
while (nn >>= 1) ng++;
if (n != 1+(1L << ng)) nrerror("n-1 must be a power of 2 in mgfas.");
if (ng > NGMAX) nrerror("increase NGMAX in mglin.");
nn=n/2+1;
ngrid=ng-1;
irho[ngrid]=dmatrix(1,nn,1,nn);
rstrct(irho[ngrid],u,nn);
while (nn > 3) {
nn=nn/2+1;
irho[--ngrid]=dmatrix(1,nn,1,nn);
rstrct(irho[ngrid],irho[ngrid+1],nn);
}
nn=3;
iu[1]=dmatrix(1,nn,1,nn);
irhs[1]=dmatrix(1,nn,1,nn);
itau[1]=dmatrix(1,nn,1,nn);
itemp[1]=dmatrix(1,nn,1,nn);
slvsm2(iu[1],irho[1]);
free_dmatrix(irho[1],1,nn,1,nn);
ngrid=ng;
for (j=2;j<=ngrid;j++) {
nn=2*nn-1;
iu[j]=dmatrix(1,nn,1,nn);
irhs[j]=dmatrix(1,nn,1,nn);
itau[j]=dmatrix(1,nn,1,nn);
itemp[j]=dmatrix(1,nn,1,nn);
interp(iu[j],iu[j-1],nn);
copy(irhs[j],(j != ngrid ? irho[j] : u),nn);
for (jcycle=1;jcycle<=maxcyc;jcycle++) {
nf=nn;
for (jj=j;jj>=2;jj--) {
for (jpre=1;jpre<=NPRE;jpre++)
relax2(iu[jj],irhs[jj],nf);
lop(itemp[jj],iu[jj],nf);
nf=nf/2+1;
jm1=jj-1;
rstrct(itemp[jm1],itemp[jj],nf);
rstrct(iu[jm1],iu[jj],nf);
lop(itau[jm1],iu[jm1],nf);
matsub(itau[jm1],itemp[jm1],itau[jm1],nf);
if (jj == j)
trerr=ALPHA*anorm2(itau[jm1],nf);
rstrct(irhs[jm1],irhs[jj],nf);
matadd(irhs[jm1],itau[jm1],irhs[jm1],nf);
}
slvsm2(iu[1],irhs[1]);
nf=3;
for (jj=2;jj<=j;jj++) {
jm1=jj-1;
rstrct(itemp[jm1],iu[jj],nf);
matsub(iu[jm1],itemp[jm1],itemp[jm1],nf);
nf=2*nf-1;
interp(itau[jj],itemp[jm1],nf);
matadd(iu[jj],itau[jj],iu[jj],nf);
for (jpost=1;jpost<=NPOST;jpost++)
relax2(iu[jj],irhs[jj],nf);
}
lop(itemp[j],iu[j],nf);
matsub(itemp[j],irhs[j],itemp[j],nf);
res=anorm2(itemp[j],nf);
if (res < trerr) break;
}
}
copy(u,iu[ngrid],n);
for (nn=n,j=ng;j>=1;j--,nn=nn/2+1) {
free_dmatrix(itemp[j],1,nn,1,nn);
free_dmatrix(itau[j],1,nn,1,nn);
free_dmatrix(irhs[j],1,nn,1,nn);
free_dmatrix(iu[j],1,nn,1,nn);
if (j != ng && j != 1) free_dmatrix(irho[j],1,nn,1,nn);
}
}
void matmul_strassen(double* a, double* b, double* c, int n)
{
double* tmp1 = (double*) malloc((n*n/4)*sizeof(double));
double* tmp2 = (double*) malloc((n*n/4)*sizeof(double));
double* a11 = (double*) malloc((n*n/4)*sizeof(double));
double* a12 = (double*) malloc((n*n/4)*sizeof(double));
double* a21 = (double*) malloc((n*n/4)*sizeof(double));
double* a22 = (double*) malloc((n*n/4)*sizeof(double));
double* b11 = (double*) malloc((n*n/4)*sizeof(double));
double* b12 = (double*) malloc((n*n/4)*sizeof(double));
double* b21 = (double*) malloc((n*n/4)*sizeof(double));
double* b22 = (double*) malloc((n*n/4)*sizeof(double));
double* c11 = (double*) malloc((n*n/4)*sizeof(double));
double* c12 = (double*) malloc((n*n/4)*sizeof(double));
double* c21 = (double*) malloc((n*n/4)*sizeof(double));
double* c22 = (double*) malloc((n*n/4)*sizeof(double));
double* m1 = (double*) malloc((n*n/4)*sizeof(double));
double* m2 = (double*) malloc((n*n/4)*sizeof(double));
double* m3 = (double*) malloc((n*n/4)*sizeof(double));
double* m4 = (double*) malloc((n*n/4)*sizeof(double));
double* m5 = (double*) malloc((n*n/4)*sizeof(double));
double* m6 = (double*) malloc((n*n/4)*sizeof(double));
double* m7 = (double*) malloc((n*n/4)*sizeof(double));
int i, j, k, ii, jj, kk, N;
double tmp;
// partition A and B
N = n/2;
for (i=0; i< N; i++)
{
for (j=0; j< N; j++)
{
a11[i*N +j ] = a[i*n+j];
b11[i*N +j ] = b[i*n+j];
a12[i*N +j ] = a[i*n+j+N];
b12[i*N +j ] = b[i*n+j+N];
a21[i*N +j ] = a[(i+N)*n+j];
b21[i*N +j ] = b[(i+N)*n+j];
a22[i*N +j ] = a[(i+N)*n+j+N];
b22[i*N +j ] = b[(i+N)*n+j+N];
}
}
//print(a, n);
//print(a11, N);
//print(a12, N);
//print(a21, N);
//print(a22, N);
//form m1 = (a11 + a22)(b11 + b22)
matadd(a11, a22, tmp1, N);
matadd(b11, b22, tmp2, N);
matmul(tmp1, tmp2, m1, N);
//form m2 = (a21 + a22)b11
matadd(a21, a22, tmp1, N);
matmul(tmp1, b11, m2, N);
//form m3 = a11(b12 - b22)
matsub(b12, b22, tmp1, N);
matmul(a11, tmp1, m3, N);
//form m4 = a22(b21 - b11)
matsub(b21, b11, tmp1, N);
matmul(a22, tmp1, m4, N);
//form m5 = (a11 +a12)b22
matadd(a11, a12, tmp1, N);
matmul(tmp1, b22, m5, N);
//form m6 = (a21 -a11)(b11 + b12)
matsub(a21, a11, tmp1, N);
matadd(b11, b12, tmp2, N);
matmul(tmp1, tmp2, m6, N);
//form m7 = (a12 -a22)(b21 + b22)
matsub(a12, a22, tmp1, N);
matadd(b21, b22, tmp2, N);
matmul(tmp1, tmp2, m7, N);
//============================
//form c11 = m1 + m4 - m5 + m7
matadd(m1, m4, tmp1, N);
matsub(tmp1, m5, tmp2, N);
matadd(tmp2, m7, c11, N);
//form c12 = m3 + m5
matadd(m3, m5, c12, N);
//form c21 = m2 + m4
matadd(m2, m4, c21, N);
//fomr c22 = m1 - m2 + m3 + m6
matsub(m1, m2, tmp1, N);
matadd(tmp1, m3, tmp2, N);
matadd(tmp2, m6, c22, N);
for (i=0; i< N; i++)
{
for (j=0; j< N; j++)
{
c[i*n+j] = c11[i*N +j ];
c[i*n+j+N] = c12[i*N +j ];
c[(i+N)*n+j] = c21[i*N +j ];
c[(i+N)*n+j+N] = c22[i*N +j ];
}
}
free(tmp1);
free(tmp2);
free(a11);
free(a12);
free(a21);
free(a22);
free(b11);
free(b12);
free(b21);
free(b22);
free(c11);
free(c12);
free(c21);
free(c22);
free(m1);
free(m2);
free(m3);
free(m4);
free(m5);
free(m6);
free(m7);
}
