Wrongly returns nan for vectorized complex numbers division on PPC/ZArch

[Flamefire]

🐛 Describe the bug

Copied from #92043 which still applies for vectorized PPC and likely to ZArch while it was fixed for x86 by #93277

Pytorch wrongly returns nan for complex numbers division where the results are still within the range of the datatype.
For example: (0.0 + 0.0j) / (1e-36 + 0.0j) in complex64. In this case, both operands and the results (which is 0) are within the defined range of complex64. However, it returns (nan + nanj).

Here's the reproducing code:

a = torch.tensor([0.0 + 0.0j]*8)
b = torch.tensor([1e-36 + 0.0j]*8)
print(a / b)  # it's (nan + nanj),...

Or just run test_complex_div_underflow_overflow.

The reason is that abs_2_ already overflows in the tested range (e.g. finfo.min / 2 in test_complex_div_underflow_overflow) and the elwise_mult(vr) does too.

Versions

PyTorch 2.1.0