// Tests input and output names from FlatBuffer are added to `tf.entry_function` attribute.

// CHECK-LABEL: @main
func.func @main(%arg0: tensor<4xi8>, %arg1: tensor<4xi32>) -> (tensor<4xi32>, tensor<4xi8>)
// CHECK: attributes {tf.entry_function = {inputs = "input0,input1", outputs = "output0,output1"}}
attributes {tf.entry_function = {inputs = "input0,input1", outputs = "output0,output1"}} {

    %outputs_4, %control_4 = tf_executor.island wraps "tf.Identity"(%outputs_3) {T = "tfdtype$DT_FLOAT", device = "", name = "output_0_shard_0"} : (tensor<0xf32>) -> tensor<0xf32>
    %control_5 = tf_executor.island(%control, %control_4) wraps "tf.NoOp"() : () -> ()

      type: DT_FLOAT
    }
  }
}
node {
  name: "output_0"
  op: "Identity"
  input: "conv_net_2d_1/Relu"
  attr {
    key: "T"
    value {
      type: DT_FLOAT
    }
  }
}
library {
}

# CHECK: 'main' inputs:
# CHECK-NEXT: name: 'input'
# CHECK-NEXT: 'main' outputs:

          ],
          "name": "output0",
          "quantization": {
          }
        },
        {
          "shape": [
            128,
            32,
            32,
            3
          ],
          "name": "output1",
          "quantization": {
          }
        }
      ],
      "inputs": [
        0,
        1
      ],
      "outputs": [
        2,
        3
      ],

    %outputs_0 = "tf.MatMul"(%arg0, %arg1) {device = "TPU", transpose_a = false, transpose_b = false} : (tensor<2x2xf32>, tensor<2x2xf32>) -> tensor<2x2xf32>
    // CHECK: tf.IdentityN
    %outputs_1, %outputs_2 = "tf.IdentityN"(%outputs, %outputs_0) {device = "CPU"} : (tensor<2x2xf32>, tensor<2x2xf32>) -> (tensor<2x2xf32>, tensor<2x2xf32>)
    func.return %outputs_0, %outputs_1 : tensor<2x2xf32>, tensor<2x2xf32>
}

    }
    inputs_.push_back(t->output_);
    *output = tensorflow::down_cast<TracingTensorHandle*>(outputs[0]);
    return absl::OkStatus();
  }

  Status Finalize(OutputList* outputs, AbstractFunction** f) override {
    std::vector<TF_Output> graph_outputs;
    graph_outputs.reserve(outputs->outputs.size());
    for (auto* abstract_output : outputs->outputs) {
      GraphTensor* output = dyn_cast<GraphTensor>(abstract_output);

  }

  func.func @mul1(%arg0: tensor<1xf32> {tf_saved_model.index_path = ["y"]}, %arg1: tensor<1xf32> {tf_saved_model.index_path = ["x"]}) -> (tensor<1xf32> {tf_saved_model.index_path = ["output_0"]}) attributes {tf.entry_function = {inputs = "mul1_y:0,mul1_x:0", outputs = "output:0"}, tf_saved_model.exported_names = ["mul1"]} {
    %0 = "tf.Mul"(%arg1, %arg0) : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
    func.return %0 : tensor<1xf32>
  }

zirain <******@****.***> 1703405786 +0800

zirain <******@****.***> 1703405786 +0800

Jacek Ewertowski <******@****.***> 1701261434 +0100