//              rsqrt(variance + epsilon)
// CHECK:  %[[RSQRT:.*]] = "tf.Rsqrt"(%[[ADD1]])
//              scale * rsqrt(variance + epsilon)
// CHECK:  %[[MUL1:.*]] = "tf.Mul"(%[[ARG1:.*]], %[[RSQRT]])
//              x * scale * rsqrt(variance + epsilon)
// CHECK:  %[[MUL2:.*]] = "tf.Mul"(%[[ARG0:.*]], %[[MUL1]])
//              mean * scale * rsqrt(variance + epsilon)

// TODO(karimnosseir): Add constraints that the kernel code assumes.
// constraint on axis and depth.
multiclass L2NormalizePatterns<Op FirstOp, Op SecondOp> {
  // This pattern constructs L2NormalizationOp from
  // Mul->Rsqrt->Sum->Square Or
  // Div->sqrt->Sum->Square
  def L2NormalizePattern1#FirstOp#SecondOp : Pat<
                  (FirstOp $x,
                     (SecondOp
                        (TFL_SumOp

    // CHECK-DAG: %[[ACCUM_NEW:.*]] = "tf.AddV2"(%[[ACCUM]], %[[GRAD_SQ]]) : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>
    // CHECK-DAG: %[[RSQRT_ACCUM:.*]] = "tf.Rsqrt"(%[[ACCUM_NEW]]) : (tensor<4xf32>) -> tensor<4xf32>
    // CHECK-DAG: %[[ADAGRAD_LR:.*]] = "tf.Mul"(%[[LR]], %[[RSQRT_ACCUM]]) : (tensor<f32>, tensor<4xf32>) -> tensor<4xf32>

  // Use the built-in operator.
  grad_outputs->push_back(
      internal::RsqrtGrad(scope, op.output(0), grad_inputs[0]));
  return scope.status();
}
REGISTER_GRADIENT_OP("Rsqrt", RsqrtGrad);

Status ExpGrad(const Scope& scope, const Operation& op,
               const std::vector<Output>& grad_inputs,
               std::vector<Output>* grad_outputs) {
  // dy/dx = exp(x) = y

  explicit FusedBatchNormV3Pat(::mlir::MLIRContext *context)
      : ::mlir::RewritePattern(
            "tf.FusedBatchNormV3", 1, context,
            {"tf.Add", "tf.Const", "tf.Mul", "tf.Rsqrt", "tf.Sub"}) {}

  ::mlir::LogicalResult matchAndRewrite(
      ::mlir::Operation *fused_batch_norm,
      ::mlir::PatternRewriter &rewriter) const override {

            "Floor", "IsFinite", "IsInf", "IsNan", "Inv", "Reciprocal", "Log",
            "Log1p", "Invert", "LogicalNot", "Ndtri", "Neg", "Rint", "Round",
            "Rsqrt", "Sigmoid", "Sign", "Sinh", "Softplus", "Softsign", "Sqrt",
            "Square", "Tan", "Tanh", "Real", "Imag", "Erf", "Erfc", "Erfinv",
            "Lgamma", "Digamma",
            // Binary

	MOVD $32, R17

	MOVD $p256mul<>+0x00(SB), CPOOL

	LXVD2X (R0)(x_ptr), X0
	LXVD2X (R16)(x_ptr), X1

	XXPERMDI X0, X0, $2, X0
	XXPERMDI X1, X1, $2, X1

sqrLoop:
	// Sqr uses same value for both

	VOR	X0, X0, Y0
	VOR	X1, X1, Y1

	LXVD2X (R16)(CPOOL), P1
	LXVD2X (R0)(CPOOL), P0

	CALL p256MulInternal<>(SB)

	MOVD	n+16(FP), N
	ADD	$-1, N

r&f--nx?t--nx??ublk--nx???ppol?q&0-t&baol--nx?soum--nx?veib--nx??x-&ipphl--nx?r&embh--nx?imph--nx???y-tinks--nx??r&f-atsr--nx?g-&an&ms--nx?nd--nx??e&drf--nx?ngs--nx??murs--nx?netl--nx?olmb--nx?sorr--nx??h-&a&lms--nx?yrf--nx??emjt--nx??i&-&lboh--nx?rsir--nx?y&d&ar--nx?na--nx??ksa--nx?lem--nx?r&ul--nx?yd--nx????stu??j-&drav--nx?rolf--nx?sdav--nx??kua?l-&drojf--nx?lares--nx??m-tlohr--nx?n-esans--nx?olf?p-sdnil--nx?s-ladrl--nx?tih?v-rvsyt--nx??s&a&ns?ons??i&ar?er&dron?r&os?øs???ár??la&g?h??mor!t??si...

r&f--nx?t--nx??ublk--nx???ppol?q&0-t&baol--nx?soum--nx?veib--nx??x-&ipphl--nx?r&embh--nx?imph--nx???y-tinks--nx??r&f-atsr--nx?g-&an&ms--nx?nd--nx??e&drf--nx?ngs--nx??murs--nx?netl--nx?olmb--nx?sorr--nx??h-&a&lms--nx?yrf--nx??emjt--nx??i&-&lboh--nx?rsir--nx?y&d&ar--nx?na--nx??ksa--nx?lem--nx?r&ul--nx?yd--nx????stu??j-&drav--nx?rolf--nx?sdav--nx??kua?l-&drojf--nx?lares--nx??m-tlohr--nx?n-esans--nx?olf?p-sdnil--nx?s-ladrl--nx?tih?v-rvsyt--nx??s&a&ns?ons??i&ar?er&dron?r&os?øs???ár??la&g?h??mor!t??si...