%result = tf_executor.graph {

// CHECK: tf_executor.Merge{{.*}}(tensor<*xf32>, tensor<4xf32>) -> (tensor<4xf32>, tensor<i32>, !tf_executor.control)
    %value, %idx, %ctlMerge = tf_executor.Merge %arg0, %arg1  : (tensor<*xf32>, tensor<4xf32>) -> (tensor<4xf32>, tensor<i32>, !tf_executor.control)
    tf_executor.fetch %value : tensor<4xf32>
  }

  // CHECK: %[[DIV:.*]] = tfl.div
  %3 = "tfl.div"(%2, %1) {fused_activation_function = "NONE"} : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32> loc("div")
  // CHECK: %[[EXP:.*]] = "tfl.exp"
  %4 = "tfl.exp"(%3) : (tensor<4xf32>) -> tensor<4xf32> loc("exp")
  // tfl.neg should not be pruned
  // CHECK: %[[NEG:.*]] = "tfl.neg"
  %5 = "tfl.neg"(%4) : (tensor<4xf32>) -> tensor<4xf32> loc("neg")

    "tf.Yield"(%2) : (tensor<i1>) -> ()
  }, {
  ^body(%barg0: tensor<*xf32>):
    %2 = "tf.SomeOp"(%barg0) : (tensor<*xf32>) -> tensor<*xf32>
    "tf.Yield"(%2) : (tensor<*xf32>) -> ()
  }) {is_stateless = false, shape_invariant} : (tensor<4xf32>) -> (tensor<*xf32>)

  func.return %0, %1 : tensor<*xf32>, tensor<*xf32>
}

// Test that both passes drop the shape_invariant attribute from
// While/WhileRegion ops within a cluster.

  // CHECK-NEXT: }

  %0 = "tfl.pseudo_const" () {value = dense<1.0> : tensor<4xf32>} : () -> tensor<4xf32> loc("Const")
  %1 = "tfl.squared_difference"(%arg0, %0) {fused_activation_function = "NONE"} : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32> loc("squared_difference")
  %2 = "tfl.mul"(%arg0, %1) {fused_activation_function = "NONE"} : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32> loc("mul")

  %0 = "tfl.pseudo_const" () {value = dense<0.0> : tensor<4xf32>} : () -> tensor<4xf32> loc("Const")
  %1 = "tfl.svdf"(%arg0, %arg1, %arg2, %arg3, %0) {fused_activation_function = "RELU", rank = 2 : i32} : (tensor<4xf32>, tensor<4xf32>, tensor<4xf32>, tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>
  func.return %1 : tensor<4xf32>

  %0 = "tf.Einsum"(%arg0, %arg1) {T = "tfdtype$DT_FLOAT", equation = "ijk,j->i"}: (tensor<4x5x6xf32>, tensor<5xf32>) -> tensor<4xf32>
  func.return %0 : tensor<4xf32>
// CHECK-LABEL: einsum_no_match
// CHECK: %[[v0:.*]] = "tf.Einsum"(%arg0, %arg1) <{equation = "ijk,j->i"}> {T = "tfdtype$DT_FLOAT"} : (tensor<4x5x6xf32>, tensor<5xf32>) -> tensor<4xf32>
// CHECK: return %[[v0]]
}

  %0 = "tfl.pseudo_const" () {value = dense<1.0> : tensor<4xf32>} : () -> tensor<4xf32> loc("Const")
  %1 = "tfl.mul"(%arg0, %0) {fused_activation_function = "NONE"} : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32> loc("mul")
  // tf.MyCustomOp is the result of conversion to a Custom op
  %2 = "tf.MyCustomOp"(%1, %0) {fused_activation_function = "RELU", int_attr = 2 : i32}  : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32> loc("MyCustomOp")

  // CHECK: %{{.*}} = "tfl.reshape"(%{{.*}}, %[[cst]]) : (tensor<4xf32>, tensor<2xi32>) -> tensor<2x2xf32>
  %cst = arith.constant dense<[2, 2]> : tensor<2xi32>
  %0 = "tfl.pseudo_const" () {value = dense<1.0> : tensor<4xf32>} : () -> tensor<4xf32> loc("Const")
  %1 = "tfl.reshape" (%0, %cst) : (tensor<4xf32>, tensor<2xi32>) -> tensor<2x2xf32> loc("reshape")
  func.return %1 : tensor<2x2xf32>

  %1 = "tfl.dequantize"(%arg0) : (tensor<4x!quant.uniform<u8:f32, 1.0>>) -> tensor<4xf32>
  %2 = "tfl.dequantize"(%arg1) : (tensor<4x!quant.uniform<u8:f32, 1.0>>) -> tensor<4xf32>
  %3 = "tfl.pow"(%1, %2) : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>
  %4 = "tfl.quantize"(%3) {qtype = tensor<4x!quant.uniform<u8:f32, 1.0>>} : (tensor<4xf32>) -> tensor<4x!quant.uniform<u8:f32, 1.0>>

  func.return %4 : tensor<4x!quant.uniform<u8:f32, 1.0>>

}

// CHECK-LABEL: func @testPow
// CHECK-SAME:(%[[ARG_0:.*]]: tensor<4xf32>, %[[ARG_1:.*]]: tensor<4xf32>) -> (tensor<4xf32>, tensor<4xf32>, tensor<4xf32>)
func.func @testPow(%arg0: tensor<4xf32>, %arg1: tensor<4xf32>) -> (tensor<4xf32>, tensor<4xf32>, tensor<4xf32>) {

  %cst_zero = arith.constant dense<0.0> : tensor<f32>
  %cst_one = arith.constant dense<1.0> : tensor<f32>