%0 = "tfl.lstm"(%arg0, %arg1, %arg2, %arg3, %arg4, %arg5, %arg6, %arg7, %arg8, %arg9, %arg10, %arg11, %arg12, %arg13, %arg14, %arg15, %arg16, %arg17, %arg18, %arg19, %arg20, %arg21, %arg22, %arg23) ({}) {cell_clip = 1.000000e+00 : f32, fused_activation_function = "NONE", kernel_type = #tfl<lstm_kernel_type_attr BASIC>} : (tensor<?xf32>,...

    // Reshape kernel to add a new spatial dimension.
    auto kernel_type = mlir::cast<ShapedType>(conv_op.getRhs().getType());
    SmallVector<int64_t, 4> kernel_2d_shape;
    for (int64_t dim : kernel_type.getShape()) {
      kernel_2d_shape.push_back(dim);
    }
    kernel_2d_shape.push_back(1);
    auto kernel_2d_type =
        RankedTensorType::get(kernel_2d_shape, kernel_type.getElementType());
    auto kernel_2d_op =

// CHECK-SAME:      <{cell_clip = 1.000000e+01 : f32, fused_activation_function = "TANH", kernel_type = #tfl<lstm_kernel_type_attr FULL>, proj_clip = 0.000000e+00 : f32}> ({

    ConfinedAttr<
      DefaultValuedOptionalAttr<TFL_LSTMKernelTypeAttr, "mlir::TFL::LSTMKernelType::BASIC">,
      [TFL_LSTMKernelTypeEqualsTo<"mlir::TFL::LSTMKernelType::BASIC">]>:$kernel_type
  );

  let hasOptions = 1;

  let results = (outs TFL_2DTensorOf<[F32, QUI8]>:$activ_output,
                      TFL_2DTensorOf<[F32, QUI16]>:$state_output,