*   Added int16x8 support for the built-in op `exp`
    *   Added int16x8 support for the built-in op `mirror_pad`
    *   Added int16x8 support for the built-in ops `space_to_batch_nd` and `batch_to_space_nd`
    *   Added 16-bit int type support for built-in op `less`, `greater_than`, `equal`

  let summary = [{
Gradient op for `MirrorPad` op. This op folds a mirror-padded tensor.
  }];

  let description = [{
This operation folds the padded areas of `input` by `MirrorPad` according to the
`paddings` you specify. `paddings` must be the same as `paddings` argument
given to the corresponding `MirrorPad` op.

The folded size of each dimension D of the output is: