matmul.arg0(1, 0) = 4;
    matmul.arg0(1, 1) = 5;
    matmul.arg0(1, 2) = 6;

    matmul.arg1(0, 0) = 7;
    matmul.arg1(0, 1) = 8;
    matmul.arg1(1, 0) = 9;
    matmul.arg1(1, 1) = 10;
    matmul.arg1(2, 0) = 11;
    matmul.arg1(2, 1) = 12;

    EXPECT_TRUE(matmul.Run());
    EXPECT_EQ(matmul.error_msg(), "");
    const float results[4] = {58, 64, 139, 154};
    for (int i = 0; i < 4; ++i) {

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

   (IsInt8ElementType $weight),
   (IsConstTensor $weight),
   (IsInt32ElementType $matmul),
   (HasStaticShapeConstraint $weight)],
  [], (addBenefit 10)>;

// Convert Matmul with hybrid inputs (f32 activation/int8 weight) to XlaDotV2
def ConvertTFMatMulToXLADotV2OpWeightOnly : Pat<
  (TF_MatMulOp:$matmul
    $input,
    (TF_MulOp (TF_CastOp (TF_IdentityOp $weight), $truncate1), $scale),

  input: "sequential/quant_dense/MatMul/kquant/FakeQuantWithMinMaxVars/ReadVariableOp"
  input: "sequential/quant_dense/MatMul/kquant/FakeQuantWithMinMaxVars/ReadVariableOp_1"
  attr {
    key: "narrow_range"
    value {
      b: false
    }
  }
  attr {
    key: "num_bits"
    value {
      i: 8
    }
  }
}
node {
  name: "sequential/quant_dense/MatMul/kquant/IdentityN"

    TFE_OpAddInput(matmul, h0_task0, status);
    ASSERT_EQ(TF_GetCode(status), TF_OK) << TF_Message(status);
    TFE_OpAddInput(matmul, has_packed_input ? packed_handle : h1_task2, status);
    ASSERT_EQ(TF_GetCode(status), TF_OK) << TF_Message(status);
  } else {
    // Handles are on task0 (local), and task2, but op is on task1.
    matmul = MatMulOp(ctx, h0_task0, h1_task2);
  }
  if (remote) {

                                   "gradients/MatMul", false, true);
    TF_Operation* matmul2 = MatMul(expected_graph_, s_, const0, const3,
                                   "gradients/MatMul_1", true, false);
    expected_grad_outputs[0] = {matmul1, 0};
    expected_grad_outputs[1] = {matmul2, 0};
  }

  TF_Tensor* FloatTensor2x2(const float* values) {

# CHECK-DAG: %[[MUL1:.*]] = "tf.MatMul"(%[[ARG0]], %[[ARG1]])
# CHECK-DAG: %[[MUL2:.*]] = "tf.MatMul"(%[[ARG1]], %[[ARG0]])
# CHECK:  %[[IDENTITY:.*]]:2 = "tf.IdentityN"(%[[MUL1]], %[[MUL2]])
# CHECK: return %[[IDENTITY]]#1, %[[IDENTITY]]#0


def Test():

  x = tf.constant(1.0, shape=(5, 3))
  y = tf.constant(1.0, shape=(3, 5))

  s = tf.matmul(x, y)
  t = tf.matmul(y, x)
  [t, s] = array_ops.identity_n([t, s])

  std::unique_ptr<TFE_Op, decltype(&TFE_DeleteOp)> matmul(
      MatMulOp(context, hcpu, hdevice), TFE_DeleteOp);
  TFE_OpSetDevice(matmul.get(), name, status.get());
  ASSERT_TRUE(TF_GetCode(status.get()) == TF_OK) << TF_Message(status.get());
  TFE_TensorHandle* retval;
  int num_retvals = 1;
  TFE_Execute(matmul.get(), &retval, &num_retvals, status.get());

  op: "Identity"
  input: "Placeholder_1"
  attr {
    key: "T"
    value {
      type: DT_BOOL
    }
  }
}
node {
  name: "cond/MatMul"
  op: "MatMul"
  input: "cond/MatMul/Switch:1"
  input: "cond/MatMul/Switch_1:1"
  attr {
    key: "T"
    value {
      type: DT_FLOAT
    }
  }
  attr {
    key: "transpose_a"
    value {
      b: false
    }

# RUN: tf_tfl_translate -unfold_batchmatmul=false -tf-input-arrays=Placeholder,Placeholder_1 -tf-input-shapes=2,5,3:3,7 -tf-input-data-types=DT_FLOAT,DT_FLOAT -tf-output-arrays=MatMul -output-mlir %s -o - 2>&1 | FileCheck %s

node {
  name: "Placeholder"
  op: "Placeholder"
  attr {
    key: "dtype"
    value {
      type: DT_FLOAT
    }
  }
  attr {
    key: "shape"
    value {
      shape {
        dim {
          size: 2