Pretty much this. They cannot promote it for you since the behavior is very different. They must honour 24-bit integer precision.
Yes they mentionned it on some twitter account, but then does GCN store 24 bits depth value as 32 bits if a 24 bits depth texture is requested ?
Since there is no performance bandwidth advantage since 24 bits needs to be stored in a 32 bits location and 8 bits are wasted the driver might as well promote d24x8 to d32 + r8 ?
No, they store it as 24-bit fixed point with 8 bits unused. It only uses 32 bits if you request a floating point depth buffer, and they can't promote from fixed point -> floating point since the distribution of precision is different.
As for the bandwidth, this is why AMD recommends that if you never use the stencil, don't ask for a depth buffer with stencil capabilities.