Why is my parallel std::for_each only using 1 thread?

I'm trying to parallelize this C++ code (computing a continuous Fourier transform of points, modeled as Dirac impulses), and this code compiles and works correctly, but it only uses 1 thread. Is there something else I need to do to get multiple threads working? This is on a Mac with 4 cores (8 threads), compiled with GCC 10.

vector<double> GetFourierImage(const Point pts[],
                               const int num_samples,
                               const int res,
                               const double freq_step) {
  vector<double> fourier_img(res*res, 0.0);
  double half_res = 0.5 * res;

  vector<int> rows(res);
  std::iota(rows.begin(), rows.end(), 0);
  std::for_each(  // Why doesn't this parallelize?
      std::execution::par_unseq,
      rows.begin(), rows.end(),
      [&](int i) {
    double y = freq_step * (i - half_res);
    for (int j = 0; j < res; j++) {
      double x = freq_step * (j - half_res);

      double fx = 0.0, fy = 0.0;
      for (int pt_idx = 0; pt_idx < num_samples; pt_idx++) {
        double dot = (x * pts[pt_idx].x) + (y * pts[pt_idx].y);
        double exp = -2.0 * M_PI * dot;
        fx += cos(exp);
        fy += sin(exp);
      }
      fourier_img[i*res + j] = sqrt((fx*fx + fy*fy) / num_samples);
    }
  });

  return fourier_img;
}