if (!paddings_op) return failure();

  auto paddings_value = paddings_op.getValue().dyn_cast<DenseElementsAttr>();
  if (!paddings_value ||
      paddings_value.getNumElements() != permutation.size() * 2)
    return failure();

  SmallVector<int32_t, 8> shuffled_paddings(paddings_value.getNumElements());
  for (const auto &index_pair :
       llvm::enumerate(paddings_value.getValues<APInt>())) {

    padding_value                 ; otherwise.
```
where `y = max(-k[1], 0)`, `x = max(k[1], 0)`.

Otherwise, the output tensor has rank `r` with dimensions
`[I, J, ..., L, num_diags, max_diag_len]` with values:

```
diagonal[i, j, ..., l, m, n]
  = input[i, j, ..., l, n+y, n+x] ; if 0 <= n+y < M and 0 <= n+x < N,
    padding_value                 ; otherwise.
```

    // values will be undefined. So we mask them later. Set up the boolean
    // expression that tells us which entries, in the output shape, are out of
    // bounds and thus become the padding_value.
    Value x_in_bounds = rewriter.create<AndOp>(
        loc,
        rewriter.create<TF::GreaterEqualOp>(loc, b_false.getType(), n_plus_x,
                                            b_zero),

  let arguments = (ins
     TFL_TensorOf<[I8, I16, I32, I64, UI8, UI16, UI32, UI64, F32, F64]>:$input,
     TFL_TensorOf<[I32]>:$dilations,
     TFL_0DTensorOf<[I8, I16, I32, I64, UI8, UI16, UI32, UI64, F32, F64]>:$padding_value
  );

  let results = (outs TFL_TensorOf<[I8, I16, I32, I64, UI8, UI16, UI32, UI64, F32, F64]>:$output);
}

def TFL_AddOp : TFL_Op<"add", [