// CHECK:           %[[SUB:.*]] = "tf.Sub"(%[[CST]], %[[SCATTER]]) : (tensor<i32>, tensor<1x24xi32>) -> tensor<1x24xi32>
// CHECK:           %[[MUL:.*]] = "tf.Mul"(%[[SUB]], %[[CAST0]]) : (tensor<1x24xi32>, tensor<1x24xi32>) -> tensor<1x24xi32>

  %group_assignment = "tf.Const"() { value = dense<[[0, 1]]> : tensor<1x2xi32> } : () -> tensor<1x2xi32>
  %instance_key = "tf.Const"() { value = dense<3> : tensor<i32> } : () -> tensor<i32>
  %group_size, %group_key = "tf.CollectiveAssignGroupV2"(%group_assignment, %rank, %key_base) {} : (tensor<1x2xi32>, tensor<i32>, tensor<i32>) -> (tensor<i32>, tensor<i32>)
  // CHECK-NOT: "tf.CollectiveAssignGroupV2"

  func.return %0 : tensor<1x4x2xi32>
}

// -----

func.func @packNegInputAxis2(%arg0: tensor<1x4xi32>, %arg1: tensor<1x4xi32>) -> tensor<1x2x4xi32> {
  // CHECK: "tfl.pack"(%arg0, %arg1) <{axis = -2 : i32, values_count = 2 : i32}>
  %0 = "tfl.pack"(%arg0, %arg1) {axis = -2 : i32, values_count = 2 : i32} : (tensor<1x4xi32>, tensor<1x4xi32>) -> tensor<1x2x4xi32>

        }) : () -> tensor<f32>
        "tf_device.cluster"() ({
          %group = "tf.Const"() <{value = dense<[[0, 1]]> : tensor<1x2xi32>}> : () -> tensor<1x2xi32>
          %arg1_reduced = "tf.XlaAllReduce"(%arg1_id, %group) <{mode = "CrossReplica", reduce_op = "Add"}> : (tensor<f32>, tensor<1x2xi32>) -> tensor<f32>
          "tf.OpA"(%arg1_reduced) : (tensor<f32>) -> ()
          tf_device.return
        }) : () -> ()

  %s0 = "tf.Const"() {value = dense<[4, 1]> : tensor<2xi32>} : () -> tensor<2xi32>
  %s1 = "tf.Const"() {value = dense<[4, 4]> : tensor<2xi32>} : () -> tensor<2xi32>
  // expected-error @+1 {{failed to verify that result 0 is 1-D}}
  %r0, %r1 = "tf.BroadcastGradientArgs"(%s0, %s1) : (tensor<2xi32>, tensor<2xi32>) -> (tensor<2x2xi32>, tensor<0xi32>)
  func.return %r0, %r1 : tensor<2x2xi32>, tensor<0xi32>
}

// -----

  // CHECK-NEXT: "tf.AssignVariableOp"(%[[BUFFER]], %[[UPDATE]]) : (tensor<!tf_type.resource<tensor<10x2xi32>>>, tensor<10x2xi32>) -> ()
  // CHECK-NEXT: %[[CONST1:.*]] = "tf.Const"() <{value = dense<1> : tensor<1xi32>}> : () -> tensor<1xi32>

  %shape1 = arith.constant dense<[64]> : tensor<1xi32>
  %0 = "tfl.reshape"(%arg0, %shape0) : (tensor<4x4x4xf32>, tensor<2xi32>) -> tensor<16x4xf32>
  %1 = "tfl.reshape"(%0, %shape1) : (tensor<16x4xf32>, tensor<1xi32>) -> tensor<64xf32>
  %2 = "tfl.reshape"(%0, %shape1) : (tensor<16x4xf32>, tensor<1xi32>) -> tensor<64xf32>
  %3 = arith.addf %1, %2 : tensor<64xf32>
  func.return %3 : tensor<64xf32>

    %cst = "tf.Const"() {value = dense<0> : tensor<1x2xi32>} : () -> tensor<1x2xi32>
    %cst_0 = "tf.Const"() {value = dense<1> : tensor<1xi32>} : () -> tensor<1xi32>
    %cst_1 = "tf.Const"() {value = dense<2> : tensor<1xi32>} : () -> tensor<1xi32>
    %cst_2 = "tf.Const"() {value = dense<3> : tensor<1xi32>} : () -> tensor<1xi32>
    %cst_3 = "tf.Const"() {value = dense<4> : tensor<1xi32>} : () -> tensor<1xi32>

func.func @pack(%arg0: tensor<2xi32>, %arg1: tensor<2xi32>) -> tensor<2x2xi32> {
  // CHECK: mhlo.reshape {{.*}} : (tensor<2xi32>) -> tensor<1x2xi32>
  // CHECK: mhlo.reshape {{.*}} : (tensor<2xi32>) -> tensor<1x2xi32>
  // CHECK: "mhlo.concatenate"({{.*}}) <{dimension = 0 : i64}> : (tensor<1x2xi32>, tensor<1x2xi32>) -> tensor<2x2xi32>

  %0 = "tf.Pack"(%arg0, %arg1) : (tensor<2xi32>, tensor<2xi32>) -> tensor<2x2xi32>

  %2 = "tf.AddN"(%arg0, %1, %1) : (tensor<2xi32>, tensor<2xi32>, tensor<2xi32>) -> tensor<2xi32>
  %3 = "tf.AddN"(%1, %arg0, %1) : (tensor<2xi32>, tensor<2xi32> , tensor<2xi32>) -> tensor<2xi32>
  %4 = "tf.AddN"(%1, %1) : (tensor<2xi32>, tensor<2xi32>) -> tensor<2xi32>
  %5 = "tf.AddN"(%arg0, %1, %0) : (tensor<2xi32>, tensor<2xi32>, tensor<2xi32>) -> tensor<2xi32>
  func.return %2, %3, %4, %5: tensor<2xi32>, tensor<2xi32>, tensor<2xi32>, tensor<2xi32>
}