void mrotate( mat* ma, const triple* v, f32 a ){
f32 c = vcos( a );
f32 s = vsin( a );
f32 t = 1 - c;
static mat m;
m.m[ 0 ][ 0 ] = t * v->x * v->x + c;
m.m[ 0 ][ 1 ] = t * v->x * v->y + s * v->z;
m.m[ 0 ][ 2 ] = t * v->x * v->z - s * v->y;
m.m[ 0 ][ 3 ] = 0;
m.m[ 1 ][ 0 ] = t * v->x * v->y - s * v->z;
m.m[ 1 ][ 1 ] = t * v->y * v->y + c;
m.m[ 1 ][ 2 ] = t * v->y * v->z + s * v->x;
m.m[ 1 ][ 3 ] = 0;
m.m[ 2 ][ 0 ] = t * v->x * v->z + s * v->y;
m.m[ 2 ][ 1 ] = t * v->y * v->z - s * v->x;
m.m[ 2 ][ 2 ] = t * v->z * v->z + c;
m.m[ 2 ][ 3 ] = 0;
m.m[ 3 ][ 0 ] = 0;
m.m[ 3 ][ 1 ] = 0;
m.m[ 3 ][ 2 ] = 0;
m.m[ 3 ][ 3 ] = 1;
mmult( ma, &m );
}
int main(int argc, char * argv[])
{
float *host_A, *host_B, *host_C;
float *dev_A, *dev_B, *dev_C;
int n, i;
if (argc == 1) n = 1024;
else n = atoi(argv[1]);
host_A = (float*)malloc( n*sizeof(float) );
host_B = (float*)malloc( n*sizeof(float) );
host_C = (float*)malloc( n*sizeof(float) );
for(i = 0; i < n; ++i ) {
host_A[i] = (float) i;
host_B[i] = (float) i;
}
for (i=0; i< n; i++)
vcos(i, host_A, host_B, host_C);
// print the result
for (int i = 0; i<10; i++){
printf("%f ",host_C[i]);
}
free(host_A);
free(host_B);
free(host_C);
return( 0 );
}
void shr_vmath_fwrap_vcos_(double *X, double *Y, int *n)
{
vcos(X, Y, *n, 1, 1);
}
