func.func @depth_to_space(%arg0: tensor<1x1x1x4xf32>) -> tensor<1x2x2x1xf32> {
  %0 = "tf.DepthToSpace"(%arg0) {block_size = 2: i64,  data_format = "NHWC"}: (tensor<1x1x1x4xf32>) -> tensor<1x2x2x1xf32>
  func.return %0 : tensor<1x2x2x1xf32>
// CHECK: %[[CUSTOM_0:.*]] = "tfl.custom"(%arg0) <{custom_code = "FlexDepthToSpace", custom_option = #tfl<const_bytes : "{{.*}}">}> : (tensor<1x1x1x4xf32>) -> tensor<1x2x2x1xf32>

  %prelu = "tfl.prelu"(%arg0, %cst) : (tensor<1x10x10x3xf32>, tensor<1x1x3xf32>) -> tensor<1x10x10x3xf32>
  func.return %prelu : tensor<1x10x10x3xf32>

// CHECK: %[[cst:.*]] = arith.constant dense<[{{\[}}[1.66394591, 3.61694336, 2.0382936]]]> : tensor<1x1x3xf32>

// CHECK-NOT: "tfl.batch_matmul"
func.func @BatchmatmulToReduceSumF32(%arg0: tensor<1x16384x257xf32>) -> (tensor<1x1x257xf32>) {
  %0 = arith.constant dense<1.0> : tensor<1x1x16384xf32>
  %1 = "tfl.batch_matmul"(%0, %arg0) {adj_x = false, adj_y = false} : (tensor<1x1x16384xf32>, tensor<1x16384x257xf32>) -> tensor<1x1x257xf32>
  func.return %1 : tensor<1x1x257xf32>

// CHECK:  return
}

func.func @reverse_v2(%arg0: tensor<1x2x3x4xf32>, %arg1: tensor<1xi32>) -> tensor<1x2x3x4xf32> {
  %0 = "tf.ReverseV2"(%arg0, %arg1) : (tensor<1x2x3x4xf32>, tensor<1xi32>) -> tensor<1x2x3x4xf32>
  func.return %0 : tensor<1x2x3x4xf32>

// CHECK-LABEL:reverse_v2
// CHECK:  "tfl.reverse_v2"(%arg0, %arg1) : (tensor<1x2x3x4xf32>, tensor<1xi32>) -> tensor<1x2x3x4xf32>
// CHECK:  return
}

    precision_config = #vhlo.array_v1<[#vhlo<precision_v1 DEFAULT>, #vhlo<precision_v1 DEFAULT>]>}> : (tensor<1x1x167xf32>, tensor<167x64xf32>) -> tensor<1x1x64xf32>
  return %0 : tensor<1x1x64xf32>
}

//CHECK:func.func private @dot_general(%arg0: tensor<1x1x167xf32>, %arg1: tensor<167x64xf32>) -> tensor<1x1x64xf32> {
//CHECK-NEXT: %0 = "vhlo.dot_general_v1"(%arg0, %arg1) <{
//CHECK-SAME:    lhs_batching_dimensions = #vhlo.tensor_v1<dense<0> : tensor<1xi64>>,

// CHECK:           %[[VAL_8:.*]] = "tf.Select"(%[[VAL_2]], %[[VAL_3]], %[[VAL_7]]) : (tensor<1x2x3x4xi1>, tensor<1x2x3x4xf32>, tensor<1x2x3x4xf32>) -> tensor<1x2x3x4xf32>
// CHECK:           return %[[VAL_8]] : tensor<1x2x3x4xf32>
// CHECK:         }
func.func @sign(%arg0: tensor<1x2x3x4xf32>, %arg1: tensor<1x2x3x4xf32>) -> tensor<1x2x3x4xf32> {

  %0 = "tf.BatchMatMulV2"(%lhs, %rhs) : (tensor<4x5x1x?x3xf32>, tensor<1x1x3x5xf32>) -> tensor<4x5x1x?x5xf32>
  func.return %0 : tensor<4x5x1x?x5xf32>
}

// -----

func.func @testBatchMatMulV2InvalidPartiallyKnownMatmulDim(%lhs: tensor<4x5x1x?x3xf32>, %rhs: tensor<1x1x3x5xf32>) -> (tensor<4x5x1x?x3xf32>) {

// -----

// CHECK-LABEL: func @sign
// CHECK-SAME: [[ARG:%arg.*]]: tensor<1x2x3x4xf32>
func.func @sign(%arg0: tensor<1x2x3x4xf32>) -> tensor<1x2x3x4xf32> {
  // CHECK: [[SIGN:%.*]] = mhlo.sign [[ARG]]
  // CHECK: return [[SIGN]] : tensor<1x2x3x4xf32>
  %0 = "tf.Sign"(%arg0) : (tensor<1x2x3x4xf32>) -> (tensor<1x2x3x4xf32>)
  func.return %0 : tensor<1x2x3x4xf32>
}

// -----

// CHECK-LABEL: func @sign_dynamic