}

// Ensure OCONVNOP is zero cost.
func Conv(v uint64) uint64 { // ERROR "can inline Conv"
	return conv2(conv2(conv2(v))) // ERROR "inlining call to (conv1|conv2)"
}
func conv2(v uint64) uint64 { // ERROR "can inline conv2"
	return conv1(conv1(conv1(conv1(v)))) // ERROR "inlining call to conv1"
}
func conv1(v uint64) uint64 { // ERROR "can inline conv1"

}

// Ensure OCONVNOP is zero cost.
func Conv(v uint64) uint64 { // ERROR "can inline Conv"
	return conv2(conv2(conv2(v))) // ERROR "inlining call to (conv1|conv2)"
}
func conv2(v uint64) uint64 { // ERROR "can inline conv2"
	return conv1(conv1(conv1(conv1(v)))) // ERROR "inlining call to conv1"
}
func conv1(v uint64) uint64 { // ERROR "can inline conv1"

  %5 = "tf.Conv2D"(%4, %arg3)
        {
          data_format = "NCHW",
          dilations = [1, 1, 1, 1],
          explicit_paddings = [],
          padding = "VALID",
          strides = [1, 1, 2, 2]
        } : (tensor<?x3x230x230xf32>, tensor<7x7x3x64xf32>) -> tensor<?x64x112x112xf32>

  // CHECK: %[[CONV0:[0-9]*]] = "tf.Conv2D"
  // CHECK-SAME: %[[PAD]]

  %conv2 = "tfl.conv_2d"(%4, %5, %cst) {dilation_h_factor = 1 : i32, dilation_w_factor = 1 : i32, fused_activation_function = "NONE", padding = "SAME", stride_h = 2 : i32, stride_w = 2 : i32} : (tensor<1x112x112x32xf32>, tensor<32x3x3x3xf32>, tensor<32xf32>) -> tensor<1x56x56x32xf32>

  %b2 = arith.constant dense<[1.0e-2, 2.1473647e1, -2.1473647e2]> : tensor<3xf32>
  %conv = "tfl.conv_2d"(%0, %w, %b) {
    dilation_h_factor = 1 : i32, dilation_w_factor = 1 : i32, fused_activation_function = "RELU",
    padding = "SAME", stride_h = 1 : i32, stride_w = 1 : i32
  } : (tensor<1x5x5x2xf32>, tensor<3x1x1x2xf32>, tensor<3xf32>) -> tensor<1x5x5x3xf32>
  %conv2 = "tfl.conv_2d"(%0, %w, %b2) {

  // CHECK-NEXT: [[CONV:%.*]] = "tf.Conv2D"([[INPUT]], [[FILTER]]) <{dilations = [1, 2, 2, 1], padding = "SAME", strides = [1, 1, 1, 1]}> : (tensor<1x128x128x3xf32>, tensor<5x5x3x8xf32>) -> tensor<1x128x128x8xf32>
  // CHECK-NEXT: [[RESULT:%.*]] = "tf.BiasAdd"([[CONV]], [[BIAS]]) : (tensor<1x128x128x8xf32>, tensor<8xf32>) -> tensor<1x128x128x8xf32>

// CHECK-DAG: %[[cst:.*]] = "tf.Const{{.*}} dense<8.000000e+00> : tensor<3x3x3x16xf32>
// CHECK-DAG: %[[cst_0:.*]] = "tf.Const{{.*}} dense<1.200000e+01> : tensor<16xf32>
// CHECK-NEXT: %[[conv:.*]] = "tf.Conv2D"(%arg0, %[[cst]])
// CHECK-NEXT: %[[bias:.*]] = "tf.AddV2"(%[[conv]], %[[cst_0]])
// CHECK-NEXT: return %[[bias]] : tensor<256x8x7x16xf32>
}

// CHECK-LABEL: convaddv2mul

// CHECK: %[[cast:.*]] = "tf.Cast"(%[[cst]]) <{Truncate = false}> : (tensor<2x3x3x2xbf16>) -> tensor<2x3x3x2xf32>
// CHECK: %[[conv:.*]] = "tf.Conv2D"(%arg0, %[[cast]])
// CHECK: %[[identity:.*]] = "tf.IdentityN"(%[[conv]]) {device = ""} : (tensor<1x3x2x2xf32>) -> tensor<1x3x2x2xf32>
// CHECK: return %[[identity]] : tensor<1x3x2x2xf32>

// CHECK: %[[DEQUANTIZE:.*]] = "quantfork.dcast"(%[[QUANTIZE]])
// CHECK: %[[CONV:.*]] = "tf.Conv2D"(%arg0, %[[DEQUANTIZE]])
// CHECK: return %[[CONV]]
}

// CHECK-LABEL: perChannelFakeQuantWithConv2D
func.func @perChannelFakeQuantWithConv2D(tensor<256x32x32x3xf32>) -> (tensor<256x8x7x16xf32>) {
^bb0(%arg: tensor<256x32x32x3xf32>) :

// CHECK: %[[CONV2D:.*]] = "tf.Conv2D"(%arg0, %[[CONST]]) <{data_format = "NHWC", dilations = [1, 1, 2, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 2, 1], use_cudnn_on_gpu = true}> : (tensor<1x3x4x3xf32>, tensor<2x3x3x2xf32>) -> tensor<1x3x2x2xf32>