Supporting half-precision floats is annoying 5 years ago
The article makes a lot of good points. But there are some cases where f16 is very useful. In the context of deep learning it's frequently useful to move from f32 -> f16. This can allow you to double the size of your models in memory (system or GPU/TPU). Since network size is often determinant of performance, doubling the number of parameters/activations in your model can make a big difference.