Openmp-嵌套用于循环

如何安全地线程化下面的嵌套for循环，以便在具有8个线程的核心上并行运行程序，并且仍然以正确的顺序输出数据。我曾尝试使用#pragma omp for命令，但这会给我一条错误消息：工作共享区域可能未紧密嵌套在工作共享、关键或显式任务区域内。

注意：这段代码是为了介绍并行编程，所以为了优化，它写得很差

#pragma omp parallel private(t, i, j) shared(nx, ny, nt)
{
// main loop
for (int t = 0; t < nt; t++)
{
cout << "n" << t;
cout.flush();
// first block 
for (int i = 0; i < nx; i++)
{
for(int j=0; j < ny ;j++)
{
if (i> 0 && i < nx - 1 && j >0 && j < ny - 1) 
{
vr[i][j] = (vi[i+1][j]+vi[i-1][j]+vi[i][j-1]+vi[i][j+1]) / 4.;
} 
else if (i == 0 && i < nx - 1 && j > 0 && j < ny - 1) 
{
vr[i][j] = (vi[i+1][j]+10.+vi[i][j-1]+vi[i][j+1]) / 4.;
} 
else if (i > 0 && i == nx - 1 && j > 0 && j < ny - 1) 
{
vr[i][j] = (5.+vi[i-1][j]+vi[i][j-1]+vi[i][j+1]) / 4.;
} 
else if (i > 0 && i < nx - 1 && j == 0 && j < ny - 1) 
{
vr[i][j] = (vi[i+1][j]+vi[i-1][j]+15.45+vi[i][j+1]) / 4.;
} 
else if (i > 0 && i < nx - 1 && j > 0 && j == ny - 1) 
{
vr[i][j] = (vi[i+1][j]+vi[i-1][j]+vi[i][j-1]-6.7) / 4.;
}
}
}
// second block
for (int i = 0; i < nx; i++) 
{
for (int j = 0; j < ny; j++)
{
if (fabs(fabs(vr[i][j]) - fabs(vi[i][j])) < 1e-2) 
{
fout << "n" << t << " " << i << " " << j << " "
<< fabs(vi[i][j]) << " " << fabs(vr[i][j]);
}
}
#pragma omp for schedule(static,100)
// third block
for (int i = 0; i < nx; i++) 
{
for (int j = 0; j < ny; j++) 
{
vi[i][j] = vi[i][j] / 2. + vr[i][j] / 2.;
}
}
}
}