layerStats = dense<[-1.28e-5, 1.27e-5]> : tensor<2xf32>
  } : (tensor<1x5x5x2xf32>) -> tensor<1x5x5x2xf32>
  %w = arith.constant dense<[[[[-1.0, 1.0]]], [[[1.0, 2.0]]], [[[-2.0, 1.0]]]]> : tensor<3x1x1x2xf32>
  %b = arith.constant dense<0.0> : tensor<3xf32>
  %b2 = arith.constant dense<[1.0e-2, 2.1473647e1, -2.1473647e2]> : tensor<3xf32>
  %conv = "tfl.conv_2d"(%0, %w, %b) {

  %0 = arith.constant dense<-1.0> : tensor<f32>
  %1 = arith.constant dense<1.0> : tensor<f32>
  %2 = arith.constant dense<1.0> : tensor<f32>
  %3 = arith.constant dense<1.0> : tensor<f32>
  %4 = arith.constant dense<4.0> : tensor<f32>
  %5 = arith.constant dense<4.0> : tensor<f32>
  %6 = arith.constant dense<2.0> : tensor<f32>

  // CHECK-DAG: [[cst0:%.*]] = arith.constant dense<1.000000e+00> : tensor<f32>

	if err != nil {
		return err
	}
	sc.Parity = s.Parity
	return nil
}

// MarshalText - marshals storage class string.
func (sc *StorageClass) MarshalText() ([]byte, error) {
	if sc.Parity != 0 {
		return []byte(fmt.Sprintf("%s:%d", schemePrefix, sc.Parity)), nil
	}
	return []byte{}, nil
}

func (sc *StorageClass) String() string {
	if sc.Parity != 0 {

  func.return %result : !tfr.tensor_list
// CHECK-DAG: %[[N_128:.*]] = arith.constant -128 : i32
// CHECK-DAG: %[[N32:.*]] = arith.constant 32 : i32
// CHECK-DAG: %[[N42:.*]] = arith.constant 42 : i32
// CHECK-DAG: %[[N52:.*]] = arith.constant 52 : i32
// CHECK-DAG: %[[N102:.*]] = arith.constant 102 : i32
// CHECK-DAG: %[[N127:.*]] = arith.constant 127 : i32
// CHECK-NEXT: %[[none_min:.*]] = "tfr.constant_tensor"(%[[N_128]])

// CHECK-LABEL: einsum_with_runtime_outputshape1
// CHECK-DAG: %[[cst:.*]] = arith.constant dense<[0, 1, 3, 2]> : tensor<4xi32>
// CHECK-DAG: %[[cst_0:.*]] = arith.constant dense<[-1, 36, 1, 32]> : tensor<4xi64>
// CHECK-DAG: %[[cst_1:.*]] = arith.constant dense<[0, 1]> : tensor<2xi32>
// CHECK-DAG: %[[cst_2:.*]] = arith.constant dense<2> : tensor<1xi32>

  %cst = arith.constant dense<0.000000e+00> : tensor<4x2xf32>
  %cst_0 = arith.constant dense<0.000000e+00> : tensor<8xf32>
  %cst_1 = arith.constant dense<[1, 0, 2]> : tensor<3xi32>
  %cst_2 = arith.constant dense<0.000000e+00> : tensor<4x4x2xf32>
  %cst_3 = arith.constant dense<4> : tensor<i32>
  %cst_4 = arith.constant dense<1.000000e+00> : tensor<f32>
  %cst_5 = arith.constant dense<1> : tensor<i32>

// CHECK-NEXT:  [[NEG_ONE:%.*]] = arith.constant dense<-1> : tensor<1xi32>
// CHECK-NEXT:  [[ZERO:%.*]] = arith.constant dense<0> : tensor<i32>
// CHECK-NEXT:  [[ONE:%.*]] = arith.constant dense<1> : tensor<1xi32>
// CHECK-NEXT:  [[ELEM_SHAPE:%.*]] = "tf.Slice"([[SHAPE]], [[ONE]], [[NEG_ONE]]) : (tensor<?xi32>, tensor<1xi32>, tensor<1xi32>) -> tensor<?xi32>
// CHECK-NEXT:  [[ZERO_1:%.*]] = arith.constant dense<0> : tensor<i32>

      CHECK-NEXT: %{{.*}} = arith.cmpi "eq", %x, %y : i64
      CHECK-NEXT: %{{.*}} = arith.cmpi "ult", %x, %y : i64
      CHECK-NEXT: %{{.*}} = arith.cmpi "ule", %x, %y : i64
      CHECK-NEXT: %{{.*}} = arith.cmpi "ugt", %x, %y : i64
      CHECK-NEXT: %{{.*}} = arith.cmpi "uge", %x, %y : i64
      CHECK-NEXT: %{{.*}} = arith.cmpi "ne", %x, %y : i64
      CHECK-NEXT: %{{.*}} = arith.addi %x, %y : i64

  func.return %3 : tensor<64xf32>

// CHECK-LABEL: func @reshape_removeAdjacentWithMultipleUse
// CHECK:  %[[CST:.*]] = arith.constant dense<64> : tensor<1xi32>
// CHECK:  %[[RESHAPE_1:.*]] = "tfl.reshape"(%arg0, %[[CST]]) : (tensor<4x4x4xf32>, tensor<1xi32>) -> tensor<64xf32>
// CHECK:  %[[RESHAPE_2:.*]]  = "tfl.reshape"(%arg0, %[[CST]]) : (tensor<4x4x4xf32>, tensor<1xi32>) -> tensor<64xf32>

    %cst_3 = arith.constant dense<1.0> : tensor<20x20xf32>
    %cst_7 = arith.constant dense<1.0> : tensor<20xf32>
    %recurrent_input = arith.constant dense<1.0> : tensor<1x20xf32>
    %recurrent_stats = "quantfork.stats"(%recurrent_input) {layerStats = dense<[-2.0, 1.0]> : tensor<2xf32>} : (tensor<1x20xf32>) -> tensor<1x20xf32>
    %cell_input = arith.constant dense<1.0> : tensor<1x20xf32>