// CHECK: %[[MUL:.*]] = tfl.mul %arg0, %[[BROADCAST_TO]] {fused_activation_function = "NONE"} : tensor<8x7x6x5x4x3x2x1xf32>
  // CHECK: return %[[MUL]] : tensor<8x7x6x5x4x3x2x1xf32>
}

func.func @mul_with_high_dims_dynamic_shape_both_sides(%arg0: tensor<8x7x6x5x?x3x2x1xf32>, %arg1: tensor<?x3x2x1xf32>) -> tensor<8x7x6x5x?x3x2x1xf32> {

  %0 = "tfl.add"(%arg0, %arg1) {fused_activation_function = "RELU6",  per_device_costs = {CPU = 5.0 : f32, GPU = 1.0 : f32}, tac.device = "GPU"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
  %1 = "tfl.mul"(%0, %arg2) {fused_activation_function = "RELU6", per_device_costs = {CPU = 5.0 : f32, GPU = 1.0 : f32}, tac.device = "GPU"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>

  // CHECK: tfl.mul %arg0, %arg1 {fused_activation_function = "RELU6"}
  %0 = tfl.mul %arg0, %arg1 {fused_activation_function = "RELU6"} : tensor<? x i16>
  func.return %0#0 : tensor<? x i16>
}

// CHECK-LABEL: testMulComplex
func.func @testMulComplex(tensor<? x complex<f32>>, tensor<? x complex<f32>>) -> tensor<? x complex<f32>> {
^bb0(%arg0: tensor<? x complex<f32>>, %arg1: tensor<? x complex<f32>>):

// CHECK{LITERAL}: %cst_1 = arith.constant dense<[[[[1.000000e+00], [2.000000e+00]], [[2.000000e+00], [4.000000e+00]]]]> : tensor<1x2x2x1xf32>
// CHECK: %3 = tfl.mul %2, %cst_1 {fused_activation_function = "NONE"} : tensor<1x2x2x1xf32>
// CHECK: %cst_2 = arith.constant dense<[0, 3, 1, 2]> : tensor<4xi32>

		return errInvalidOID
	}

	if first.Cmp(big.NewInt(2)) > 0 || (first.Cmp(big.NewInt(2)) < 0 && second.Cmp(big.NewInt(40)) >= 0) {
		return errInvalidOID
	}

	firstComponent := first.Mul(first, big.NewInt(40))
	firstComponent.Add(firstComponent, second)

	der := appendBase128BigInt(make([]byte, 0, 32), firstComponent)

	for nextComponentExists {
		var strNum string

	}

	// ±0 - y
	// x - ±Inf
	return z.Neg(y)
}

// Mul sets z to the rounded product x*y and returns z.
// Precision, rounding, and accuracy reporting are as for [Float.Add].
// Mul panics with [ErrNaN] if one operand is zero and the other
// operand an infinity. The value of z is undefined in that case.
func (z *Float) Mul(x, y *Float) *Float {
	if debugFloat {
		x.validate()
		y.validate()
	}

		default:
			return ast.NewIdent(t.Name())
		}
	case *types.Pointer:
		x := TypeExpr(f, pkg, t.Elem())
		if x == nil {
			return nil
		}
		return &ast.UnaryExpr{
			Op: token.MUL,
			X:  x,
		}
	case *types.Array:
		elt := TypeExpr(f, pkg, t.Elem())
		if elt == nil {
			return nil
		}
		return &ast.ArrayType{
			Len: &ast.BasicLit{
				Kind:  token.INT,

(Mod32u x y) && buildcfg.GOPPC64 <= 8 => (SUB x (MULLW y (DIVWU x y)))

// (x + y) / 2 with x>=y => (x - y) / 2 + y
(Avg64u <t> x y) => (ADD (SRDconst <t> (SUB <t> x y) [1]) y)

(Mul64 ...) => (MULLD ...)
(Mul(32|16|8) ...) => (MULLW ...)
(Select0 (Mul64uhilo x y)) => (MULHDU x y)
(Select1 (Mul64uhilo x y)) => (MULLD x y)

(Div64 [false] x y) => (DIVD x y)
(Div64u ...) => (DIVDU ...)
(Div32 [false] x y) => (DIVW x y)

			loopHead := s.f.NewBlock(ssa.BlockPlain)
			loopBody := s.f.NewBlock(ssa.BlockPlain)

			// Pick right size ops.
			var mul, and, add, zext ssa.Op
			if s.config.PtrSize == 4 {
				mul = ssa.OpMul32
				and = ssa.OpAnd32
				add = ssa.OpAdd32
				zext = ssa.OpCopy
			} else {
				mul = ssa.OpMul64
				and = ssa.OpAnd64
				add = ssa.OpAdd64
				zext = ssa.OpZeroExt32to64
			}

        %add_out, %add_control = tf_executor.island wraps "tf.Add"(%arg2, %arg3) : (tensor<f32>, tensor<f32>) -> tensor<f32>
        %mul_out, %mul_control = tf_executor.island wraps "tf.Mul"(%arg2, %arg3) : (tensor<f32>, tensor<f32>) -> tensor<f32>
        %barrier = tf_executor.island(%assign_0_control, %assign_1_control, %add_control, %mul_control) wraps "tf.NoOp"() : () -> ()