%0 = "tf.Conv2D"(%arg0, %arg1) {padding = "SAME", strides = [1, 1, 1, 1]} : (tensor<*xf32>, tensor<*xf32>) -> tensor<?x?x?x?xf32>
  func.return %0 : tensor<?x?x?x?xf32>
}

// -----

// CHECK-LABEL: func @testValidConv3D
func.func @testValidConv3D(%arg0: tensor<256x32x32x32x3xf32>, %arg1: tensor<3x3x3x3x16xf32>) -> tensor<256x32x32x32x16xf32> {

    %5 = "tf.Pad"(%arg0, %3) : (tensor<2x224x224x3xf32>, tensor<4x2xi32>) -> tensor<2x230x230x3xf32>
    // CHECK: "tf.Conv2D"
    // CHECK-SAME: strides = [1, 1, 1, 1]
    // CHECK-SAME: (tensor<2x115x115x12xf32>, tensor<4x4x12x64xf32>) -> tensor<2x112x112x64xf32>

  %0 = "tf.Conv2D"(%output, %cst) <{data_format = "NHWC", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 2, 2, 1], use_cudnn_on_gpu = true}> {attr_map = "0:strides,1:use_cudnn_on_gpu,2:padding,3:explicit_paddings,4:dilations", device...

  %6 = "tfl.var_handle"() {container = "", shared_name = "conv_variable/state"} : () -> tensor<!tf_type.resource>
  %7 = "tfl.read_variable"(%6) : (tensor<!tf_type.resource>) -> tensor<1x3x1x1xf32>

  key: "MobilenetV1/MobilenetV1/Conv2d_0/BatchNorm/FusedBatchNorm@"
  value {
    file_line_cols {
      file_index: 5
      line: 362
    }
  }
}
traces {
  key: "MobilenetV1/MobilenetV1/Conv2d_0/Conv2D@"
  value {
    file_line_cols {
      file_index: 2
      line: 27
    }
  }
}
traces {
  key: "input@"
  value {
    file_line_cols {
      file_index: 40
      line: 690

    %3 = "tf.Cast"(%2) {Truncate = false} : (tensor<960x960x3x512xi8>) -> tensor<960x960x3x512xi32>
    %4 = "tf.Sub"(%3, %arg5) : (tensor<960x960x3x512xi32>, tensor<512xi32>) -> tensor<960x960x3x512xi32>
    %5 = "tf.Conv2D"(%1, %4) {dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 2, 1], use_cudnn_on_gpu = true} : (tensor<1x2240x2240x3xi32>, tensor<960x960x3x512xi32>) -> tensor<1x2240x1120x512xi32>

  %dq_bias = "quantfork.dcast"(%q_bias) : (tensor<2x!quant.uniform<i32:f32, 0.044022349891595126>>) -> tensor<2xf32>

    %9 = "tf.Cast"(%6) {Truncate = false, device = ""} : (tensor<1x3x4x3x3xi32>) -> tensor<1x3x4x3x3xf32>
    %10 = "tf.Cast"(%8) {Truncate = false, device = ""} : (tensor<2x3x3x3x2xi32>) -> tensor<2x3x3x3x2xf32>
    %11 = "tf.Conv3D"(%9, %10) {device = "", dilations = [1, 1, 1, 1, 1], padding = "SAME", strides = [1, 1, 2, 1, 1]} : (tensor<1x3x4x3x3xf32>, tensor<2x3x3x3x2xf32>) -> tensor<1x3x2x3x2xf32>

	{"runtime.stringtoslicerune", 1},
	{"runtime.slicecopy", 1},
	{"runtime.decoderune", 1},
	{"runtime.countrunes", 1},
	{"runtime.convT", 1},
	{"runtime.convTnoptr", 1},
	{"runtime.convT16", 1},
	{"runtime.convT32", 1},
	{"runtime.convT64", 1},
	{"runtime.convTstring", 1},
	{"runtime.convTslice", 1},
	{"runtime.assertE2I", 1},
	{"runtime.assertE2I2", 1},
	{"runtime.panicdottypeE", 1},
	{"runtime.panicdottypeI", 1},

#include "tensorflow/core/lib/core/status_test_util.h"
#include "tensorflow/core/lib/random/random.h"

namespace tensorflow {
namespace {

using ops::AvgPool;
using ops::AvgPool3D;
using ops::BiasAdd;
using ops::Conv2D;
using ops::Conv2DBackpropInput;
using ops::DepthwiseConv2dNative;
using ops::Elu;
using ops::FractionalAvgPool;
using ops::FractionalMaxPool;
using ops::FusedBatchNormV3;
using ops::L2Loss;
using ops::LogSoftmax;