VMOV	V8.D[0], R4
	VMOV	V8.D[1], R5
	CBZ	R4, not_equal
	CBZ	R5, not_equal
	BNE	chunk64_loop
	AND	$0x3f, R2, R2
	CBZ	R2, equal
chunk16:
	// work with 16-byte chunks
	BIC	$0xf, R2, R3
	CBZ	R3, tail
	ADD	R3, R0, R6	// end of chunks
chunk16_loop:
	LDP.P	16(R0), (R4, R5)
	LDP.P	16(R1), (R7, R9)
	EOR	R4, R7
	CBNZ	R7, not_equal
	EOR	R5, R9
	CBNZ	R9, not_equal
	CMP	R0, R6
	BNE	chunk16_loop
	AND	$0xf, R2, R2

  // CHECK-NEXT:   %[[ADD:.*]] = "tf.Add"(%[[ARG1]], %[[ARG3]]) : (tensor<f32>, tensor<f32>) -> tensor<f32>
  // CHECK-NEXT:   %[[NOT_EQUAL:.*]] = "tf.NotEqual"(%[[IDEN]], %[[ADD]]) : (tensor<f32>, tensor<f32>) -> tensor<i1>
  // CHECK-NEXT:   %[[CONDITION:.*]] = tensor.extract %[[NOT_EQUAL]][] : tensor<i1>
  // CHECK-NEXT:   scf.condition(%[[CONDITION]]) %[[ARG3]], %[[ARG4]] : tensor<f32>, tensor<*xf32>
  // CHECK-NEXT: } do {

        <!--</module>-->

        <!-- Coding -->
        <module name="CovariantEquals"/>

  GREATER_EQUAL = 62,
  LESS_EQUAL = 63,
  SELECT = 64,
  SLICE = 65,
  SIN = 66,
  TRANSPOSE_CONV = 67,
  SPARSE_TO_DENSE = 68,
  TILE = 69,
  EXPAND_DIMS = 70,
  EQUAL = 71,
  NOT_EQUAL = 72,
  LOG = 73,
  SUM = 74,
  SQRT = 75,
  RSQRT = 76,
  SHAPE = 77,
  POW = 78,
  ARG_MIN = 79,
  FAKE_QUANT = 80,
  REDUCE_PROD = 81,
  REDUCE_MAX = 82,
  PACK = 83,

  GREATER_EQUAL = 62,
  LESS_EQUAL = 63,
  SELECT = 64,
  SLICE = 65,
  SIN = 66,
  TRANSPOSE_CONV = 67,
  SPARSE_TO_DENSE = 68,
  TILE = 69,
  EXPAND_DIMS = 70,
  EQUAL = 71,
  NOT_EQUAL = 72,
  LOG = 73,
  SUM = 74,
  SQRT = 75,
  RSQRT = 76,
  SHAPE = 77,
  POW = 78,
  ARG_MIN = 79,
  FAKE_QUANT = 80,
  REDUCE_PROD = 81,
  REDUCE_MAX = 82,
  PACK = 83,

// CHECK:  tfl.floor_div %arg0, %arg1 : tensor<8x16xi16>
// CHECK:  return
}

func.func @not_equal(%arg0: tensor<8x16xf32>, %arg1: tensor<8x16xf32>) -> tensor<8x16xi1> {
  %0 = "tf.NotEqual"(%arg0, %arg1) : (tensor<8x16xf32>, tensor<8x16xf32>) -> tensor<8x16xi1>
  func.return %0 : tensor<8x16xi1>

// CHECK-LABEL: not_equal
// CHECK:  tfl.not_equal(%arg0, %arg1) : (tensor<8x16xf32>, tensor<8x16xf32>) -> tensor<8x16xi1>
// CHECK:  return
}

  GREATER_EQUAL = 62,
  LESS_EQUAL = 63,
  SELECT = 64,
  SLICE = 65,
  SIN = 66,
  TRANSPOSE_CONV = 67,
  SPARSE_TO_DENSE = 68,
  TILE = 69,
  EXPAND_DIMS = 70,
  EQUAL = 71,
  NOT_EQUAL = 72,
  LOG = 73,
  SUM = 74,
  SQRT = 75,
  RSQRT = 76,
  SHAPE = 77,
  POW = 78,
  ARG_MIN = 79,
  FAKE_QUANT = 80,
  REDUCE_PROD = 81,
  REDUCE_MAX = 82,
  PACK = 83,

  );
}

def TFL_NotEqualOp : TFL_Op<"not_equal", [
    TFL_OperandsHaveSameShapesOrBroadcastableShape<[0, 1], 4>,
    ComparisonOpSameElementTypeConstraint,
    ResultsBroadcastableShape,
    Commutative,
    Pure]> {
  let summary = "Not_equal operator";

  let description = [{
    Element-wise not_equal operation.
  }];

  let arguments = (

```python
    # Apply function (increments x_i) on elements for which a certain condition
    # apply (x_i != -1 in this example).
    x=tf.constant([0.1, -1., 5.2, 4.3, -1., 7.4])
    condition_mask=tf.not_equal(x,tf.constant(-1.))
    partitioned_data = tf.dynamic_partition(
        x, tf.cast(condition_mask, tf.int32) , 2)
    partitioned_data[1] = partitioned_data[1] + 1.0
    condition_indices = tf.dynamic_partition(

        `tf.floor`, `tf.greater`, `tf.greater_equal`, `tf.less`,
        `tf.less_equal`, `tf.log`, `tf.logp1`, `tf.logical_and`,
        `tf.logical_not`, `tf.logical_or`, `tf.maximum`, `tf.minimum`,
        `tf.not_equal`, `tf.sin`, `tf.sinh`, `tf.tan`
    *   Deprecate `tf.data.Dataset.shard`.
    *   Deprecate `saved_model.loader.load` which is replaced by
        `saved_model.load` and `saved_model.main_op`, which will be replaced by