func.func @main(tensor<40x37xf32>, tensor<40x37xf32>) -> tensor<40x40xf32> {
^bb0(%arg0: tensor<40x37xf32>, %arg1: tensor<40x37xf32>):
  %cst = arith.constant dense<1.0> : tensor<40xf32>
  %0:2 = "tfl.fully_connected"(%arg0, %arg1, %cst) {fused_activation_function = "NONE", keep_num_dims = false, weights_format = "DEFAULT"} : (tensor<40x37xf32>, tensor<40x37xf32>, tensor<40xf32>) -> (tensor<40x40xf32>, tensor<40x40xf32>)

// CHECK: %[[CST:.*]] = "tfl.no_value"() <{value}> : () -> none

  %cst = "tf.Const"() {device = "/job:localhost/replica:0/task:0/device:CPU:0", value = dense<3> : tensor<i32>} : () -> tensor<i32>
  %0 = "tf.Less"(%arg0, %cst) {device = "/job:localhost/replica:0/task:0/device:CPU:0"} : (tensor<i32>, tensor<i32>) -> tensor<i1>
  %1 = "tf.Less"(%arg1, %cst) {device = "/job:localhost/replica:0/task:0/device:CPU:0"} : (tensor<i32>, tensor<i32>) -> tensor<i1>

// CHECK-NEXT: "func.return"([[res]]) : (tensor<*xf32>) -> ()


// -----

// CHECK-LABEL: standalone_same_scale_test
func.func @standalone_same_scale_test(%arg0: tensor<*xf32>) -> tensor<*xf32> {
  %cst = arith.constant dense<[-1, 144]> : tensor<2xi32>
  %0 = "quantfork.qcast"(%arg0) : (tensor<*xf32>) -> tensor<*x!quant.uniform<i8:f32, 5.000000e-02:-10>>

  %cst = "tfl.no_value"() {value = unit} : () -> none

// CHECK-NOT: tf.ReadVariableOp
  %0 = "tf.ReadVariableOp"(%arg0) : (tensor<*x!tf_type.resource<tensor<1xf32>>>) -> tensor<1xf32>
  %cst = "tf.Const"() <{value = dense<0.000000e+00> : tensor<f32>}> : () -> tensor<f32>
  %cst_0 = "tf.Const"() <{value = dense<1> : tensor<1xi64>}> : () -> tensor<1xi64>
  %fill = "tf.Fill"(%cst_0, %cst) : (tensor<1xi64>, tensor<f32>) -> tensor<1xf32>
  tf_device.replicate([%0, %fill] as %arg_r0: tensor<1xf32>) {n = 2 : i32} {

// the quantization parameters as a TypeAttr and "tfl.dequantize" op used to
// convert the output type to the next op. Here are the transformations:
//
// input   min cst       max cst          input   min cst       max cst
//  \       |             |                \       |             |
//   \  (tf.Identity) (tf.Identity)   =>    \  (tf.Identity) (tf.Identity)
//    \     |             |                  \     |             |

func.func @commute_transpose_reduce_window(
      %input: tensor<1x114x114x64xf32>,
      %cst: tensor<f32>) -> tensor<1x64x56x56xf32> {
  %tpos = stablehlo.transpose %input, dims = [0, 3, 1, 2]
      : (tensor<1x114x114x64xf32>) -> tensor<1x64x114x114xf32>
  %ret = "stablehlo.reduce_window"(%tpos, %cst)
      <{window_dimensions = array<i64: 1, 1, 3, 3>, window_strides = array<i64: 1, 1, 2, 2>}> ({

				timeout *= 2
				retry = true
				cst.close()
			}
			return true
		}

		if _, err := cst.c.Get(cst.ts.URL); err != nil {
			if tooShort(err) {
				continue
			}
			t.Fatalf("got error: %s", err)
		}

		time.Sleep(10 * timeout)
		if _, err := cst.c.Get(cst.ts.URL); err != nil {
			if tooShort(err) {
				continue
			}

    %cst = "tf.Const"() <{value = dense<[0, 1]> : tensor<2xi32>}> {device = ""} : () -> tensor<2xi32>
    %cst_0 = "tf.Const"() <{value = dense<1.000000e+01> : tensor<f32>}> {device = ""} : () -> tensor<f32>
    %0 = "tf.Sum"(%arg0, %cst) <{keep_dims = false}> {device = ""} : (tensor<1x4xf32>, tensor<2xi32>) -> tensor<f32>