%cst = "tf.Const"() {value = dense<0.000000e+00> : tensor<10xf32>} : () -> tensor<10xf32>
    %cst_0 = "tf.Const"() {value = dense<[-1, 10]> : tensor<2xi32>} : () -> tensor<2xi32>
    %1 = "tf.MatMul"(%arg0, %arg1) {
      transpose_a = false, transpose_b = false
    } : (tensor<1x10xf32>, tensor<10x10xf32>) -> tensor<1x10xf32>  loc(fused["MatMul:", "test_opt_out"])

      %arg0 = "tf.Const"() {value = dense<-3.0> : tensor<5x7xf32>} : () -> tensor<5x7xf32>
      %arg1 = "tf.Const"() {value = dense<-3.0> : tensor<11x7xf32>} : () -> tensor<11x7xf32>

      %1 = "tf.MatMul"(%arg0, %arg1) {transpose_a = false, transpose_b = true} : (tensor<5x7xf32>, tensor<11x7xf32>) -> tensor<5x11xf32>

      func.return %1 : tensor<5x11xf32>
    }
  })";
  TF_ASSERT_OK_AND_ASSIGN(

func.func @dot_general_with_bias_same_shape_fn(%arg0: tensor<1x2xf32>) -> tensor<1x3xf32> {
  %0 = stablehlo.constant dense<2.000000e+00> : tensor<2x3xf32>
  %1 = stablehlo.constant dense<2.000000e+00> : tensor<1x3xf32>
  %2 = stablehlo.dot_general %arg0, %0, contracting_dims = [1] x [0], precision = [DEFAULT, DEFAULT] : (tensor<1x2xf32>, tensor<2x3xf32>) -> tensor<1x3xf32>

  %8 = "tfl.concatenation"(%2, %0) {axis = -1 : i32, fused_activation_function = "NONE"} : (tensor<1x1xf32>, tensor<1x1xf32>) -> tensor<1x2xf32>
  %9 = "quantfork.stats"(%8) {layerStats = dense<[-0.488159984, 0.189515018]> : tensor<2xf32>} : (tensor<1x2xf32>) -> tensor<1x2xf32>
  %10 = "tfl.concatenation"(%9, %7) {axis = -1 : i32, fused_activation_function = "NONE"} : (tensor<1x2xf32>, tensor<1x2xf32>) -> tensor<1x4xf32>

  %0:3 = "tf.Split"(%arg0, %arg1) : (tensor<i32>, tensor<1x4x3x3xf32>) -> (tensor<1x4x3xf32>, tensor<1x4x3xf32>, tensor<1x4x3xf32>)
  func.return %0#0 : tensor<1x4x3xf32>

  // CHECK-LABEL: split
  // CHECK: "tfl.split"(%arg0, %arg1) <{num_splits = 3 : i32}> : (tensor<i32>, tensor<1x4x3x3xf32>) -> (tensor<1x4x3xf32>, tensor<1x4x3xf32>, tensor<1x4x3xf32>)
}

}

// CHECK-LABEL: QuantizeConcat
func.func @QuantizeConcat(tensor<1x2xf32>, tensor<1x2xf32>) -> tensor<2x2x!quant.uniform<u8:f32, 1.000000e-01:128>> {
^bb0(%arg0: tensor<1x2xf32>, %arg1: tensor<1x2xf32>):
  %0 = "tfl.concatenation"(%arg0, %arg1) {axis = 0 : i32, fused_activation_function = "NONE"} : (tensor<1x2xf32>, tensor<1x2xf32>) -> tensor<2x2xf32>

  %1 = "tf.ReadVariableOp"(%0) {device = "/CPU:0"} : (tensor<!tf_type.resource<tensor<1x1xf32>>>) -> tensor<1x1xf32>
  %2:2 = "tf.Split"(%cst, %arg0) {device = "/CPU:0"} : (tensor<i32>,  tensor<1x4xf32>) -> (tensor<1x2xf32>, tensor<1x2xf32>)
  %3:2 = "tf.Split"(%cst, %2#0) {device = "/CPU:0"} : (tensor<i32>,  tensor<1x2xf32>) -> (tensor<1x1xf32>, tensor<1x1xf32>)

  constexpr absl::string_view kProgram = R"mlir(
func.func @main(
    %arg0: tensor<10x10xf32>, %scale: tensor<10xf32>, %zp: tensor<10xi32>
  ) -> tensor<10x10xi8> {
  %0 = "tf.UniformQuantize"(%arg0, %scale, %zp) {
    quantization_axis = 1 : i64,
    quantization_min_val = -128 : i64,
    quantization_max_val = 127 : i64
  } : (tensor<10x10xf32>, tensor<10xf32>, tensor<10xi32>) -> tensor<10x10x!tf_type.qint8>

    %10 = "tf.Cast"(%9) {Truncate = false, device = ""} : (tensor<1x3xi32>) -> tensor<1x3xf32>
    %11 = "tf.Mul"(%10, %cst) {device = ""} : (tensor<1x3xf32>, tensor<f32>) -> tensor<1x3xf32>
    %12 = "tf.Relu"(%11) {device = ""} : (tensor<1x3xf32>) -> tensor<1x3xf32>
    return %12 : tensor<1x3xf32>
  }
// CHECK-LABEL: func @matmul_with_relu

  %5 = "quantfork.stats"(%4) {layerStats = dense<[-56.2916565, 122.922478]> : tensor<2xf32>} : (tensor<1x4xf32>) -> tensor<1x4xf32>
  %6 = "tfl.svdf"(%0, %1, %2, %3, %5) {fused_activation_function = "RELU", rank = 1 : i32} : (tensor<1x3xf32>, tensor<2x3xf32>, tensor<2x1xf32>, tensor<2xf32>, tensor<1x4xf32>) -> tensor<1x2xf32>