Slow ArrayD operation

[ungsik]

I am converting the following python code into rust using ArrayD.

tmp = numpy.zeros_like(h4e)
dim = h4e.shape[0]

for i in range(dim):
    for j in range(dim):
        for k in range(dim):
            for m in range(dim):
                tmp[i, j, k, m, :, :, :, :] = (
                    (h4e[i, j, k, m, :, :, :, :] -
                     h4e[i, j, m, k, :, :, :, :] +
                     h4e[i, m, j, k, :, :, :, :] -
                     h4e[i, m, k, j, :, :, :, :] -
                     h4e[i, k, j, m, :, :, :, :] +
                     h4e[i, k, m, j, :, :, :, :]) -
                    (h4e[j, i, k, m, :, :, :, :] -
                     h4e[j, i, m, k, :, :, :, :] +
                     h4e[j, m, i, k, :, :, :, :] -
                     h4e[j, m, k, i, :, :, :, :] -
                     h4e[j, k, i, m, :, :, :, :] +
                     h4e[j, k, m, i, :, :, :, :]) -
                    (h4e[k, j, i, m, :, :, :, :] -
                     h4e[k, j, m, i, :, :, :, :] +
                     h4e[k, m, j, i, :, :, :, :] -
                     h4e[k, m, i, j, :, :, :, :] -
                     h4e[k, i, j, m, :, :, :, :] +
                     h4e[k, i, m, j, :, :, :, :]) -
                    (h4e[m, j, k, i, :, :, :, :] -
                     h4e[m, j, i, k, :, :, :, :] +
                     h4e[m, i, j, k, :, :, :, :] -
                     h4e[m, i, k, j, :, :, :, :] -
                     h4e[m, k, j, i, :, :, :, :] +
                     h4e[m, k, i, j, :, :, :, :])) / 24.0

When I tried the following code, it takes about 50 seconds when the shape is [6; 8].
Is there more performant and correct way?

let mut tmp = ArrayD::<c64>::zeros(IxDyn(&[dim; 8]));
for (i, j, k, m) in iproduct!(0..dim, 0..dim, 0..dim, 0..dim) {
    for (p, q, r, s) in iproduct!(0..dim, 0..dim, 0..dim, 0..dim) {
        tmp[&[i, j, k, m, p, q, r, s][..]] = (
            (h4e[&[i, j, k, m, p, q, r, s][..]] -
            h4e[&[i, j, m, k, p, q, r, s][..]] +
        h4e[&[i, m, j, k, p, q, r, s][..]] -
            h4e[&[i, m, k, j, p, q, r, s][..]] -
            h4e[&[i, k, j, m, p, q, r, s][..]] +
        h4e[&[i, k, m, j, p, q, r, s][..]]) -
            (h4e[&[j, i, k, m, p, q, r, s][..]] -
            h4e[&[j, i, m, k, p, q, r, s][..]] +
        h4e[&[j, m, i, k, p, q, r, s][..]] -
            h4e[&[j, m, k, i, p, q, r, s][..]] -
            h4e[&[j, k, i, m, p, q, r, s][..]] +
        h4e[&[j, k, m, i, p, q, r, s][..]]) -
            (h4e[&[k, j, i, m, p, q, r, s][..]] -
            h4e[&[k, j, m, i, p, q, r, s][..]] +
        h4e[&[k, m, j, i, p, q, r, s][..]] -
            h4e[&[k, m, i, j, p, q, r, s][..]] -
            h4e[&[k, i, j, m, p, q, r, s][..]] +
        h4e[&[k, i, m, j, p, q, r, s][..]]) -
            (h4e[&[m, j, k, i, p, q, r, s][..]] -
            h4e[&[m, j, i, k, p, q, r, s][..]] +
        h4e[&[m, i, j, k, p, q, r, s][..]] -
            h4e[&[m, i, k, j, p, q, r, s][..]] -
            h4e[&[m, k, j, i, p, q, r, s][..]] +
        h4e[&[m, k, i, j, p, q, r, s][..]])) / 24.0
    }
}