// CHECK-DAG: %[[input_23:.*]] = "tfl.dequantize"({{.*}}) : (tensor<2x!quant.uniform<i16<-32767:32767>:f32, 2.736719606284107E-5>>) -> tensor<2xf32>

// CHECK: %[[lstm:.*]] = "tfl.unidirectional_sequence_lstm"(%[[input_0]], %[[input_1]], %[[input_2]], %[[input_3]], %[[input_4]], %[[input_5]], %[[input_6]], %[[input_7]], %[[input_8]],

    p.device = &dummy_device;
    p.step_id = 43;

    Tensor t(tensorflow::uint8(123));

    gtl::InlinedVector<TensorValue, 4> inputs;
    // Simulate 2 inputs
    inputs.emplace_back(&t);
    inputs.emplace_back();
    p.inputs = inputs;

    Status status;
    std::unique_ptr<OpKernel> kernel =
        GetFakeKernel(device_name, op_name, node_name, &status);
    TF_EXPECT_OK(status);

  EXPECT_THAT(input2->type, Eq(TensorType_INT8));

  // Check if the quantization params of the minimum/maximum inputs match
  // after requantization
  EXPECT_THAT(input1->quantization->scale, Eq(input2->quantization->scale));
  EXPECT_THAT(input1->quantization->zero_point,
              Eq(input2->quantization->zero_point));

  // Check the input quantization params match the output ones.

  TFE_DeleteTensorHandle(ret);

  // Clone an op with inputs and no device set.
  TFE_TensorHandle* input1 = TestMatrixTensorHandle(ctx);
  TFE_TensorHandle* input2 = TestMatrixTensorHandle(ctx);
  TFE_Op* original_identity = TFE_NewOp(ctx, "IdentityN", status);
  CHECK_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);
  TFE_TensorHandle* inputs[] = {input1, input2};
  TFE_OpAddInputList(original_identity, inputs, 2, status);

  // The first one will the function's output
  std::vector<TF_Output> outputs;

  // Add while loop to func_graph_
  {
    // The inputs to the while loop
    std::vector<TF_Output> inputs = {{feed1, 0}, {feed2, 0}};
    std::unique_ptr<TF_WhileParams> params(new TF_WhileParams(
        TF_NewWhile(func_graph_, &inputs[0], inputs.size(), s_)));

sign.input 9d61b19deffd5a60ba84:d75a980182b10ab7d54b::e5564300c360ac729086: 4ccd089b28ff96da9db6:3d4017c3e843895a92b7:72:92a009a9f0d4cab8720e: c5aa8df43f9f837bedb7:fc51cd8e6218a1a38da4:af82:6291d657deec24024827: 0d4a05b07352a5436e18:e61a185bcef2613a6c7c:cbc77b:d9868d52c2bebce5f3fa: 6df9340c138cc188b5fe:c0dac102c4533186e25d:5f4c8989:124f6fc6b0d100842769: b780381a65edf8b78f69:e253af0766804b869bb1:18b6bec097:b2fc46ad47af464478c1: 78ae9effe6f245e924a7:fbcfbfa40505d7f2be44:89010d855972:6ed629fc1d9ce9e14687:...

	return results
}

// hasThreshold returns true if the threshold is in the input list
func hasThreshold(inputs []evictionapi.Threshold, item evictionapi.Threshold) bool {
	for _, input := range inputs {
		if input.GracePeriod == item.GracePeriod && input.Operator == item.Operator && input.Signal == item.Signal && compareThresholdValue(input.Value, item.Value) {
			return true
		}
	}
	return false
}

		fp31        = regInfo{inputs: []regMask{fp, fp, fp}, outputs: fponly}
		fp21clobber = regInfo{inputs: []regMask{fp, fp}, outputs: fponly}
		fpgp        = regInfo{inputs: fponly, outputs: gponly}
		gpfp        = regInfo{inputs: gponly, outputs: fponly}
		fp11        = regInfo{inputs: fponly, outputs: fponly}
		fp1flags    = regInfo{inputs: []regMask{fp}}

[[sec:task_inputs_outputs]]
== Task inputs and outputs

In the most common case, a task takes some inputs and generates some outputs.
We can consider the process of Java compilation as an example of a task.
The Java source files act as inputs of the task, while the generated class files, i.e. the result of the compilation, are the outputs of the task.

.Example task inputs and outputs
image::taskInputsOutputs.png[]

		gp21           = regInfo{inputs: []regMask{gpg, gpg}, outputs: []regMask{gp}}
		gp21nog        = regInfo{inputs: []regMask{gp, gp}, outputs: []regMask{gp}}
		gp21flags      = regInfo{inputs: []regMask{gp, gp}, outputs: []regMask{gp, 0}}
		gp2flags       = regInfo{inputs: []regMask{gpg, gpg}}
		gp2flags1      = regInfo{inputs: []regMask{gp, gp}, outputs: []regMask{gp}}