# CHECK:           %[[VAL_12:.*]] = "tfl.pack"(%[[VAL_10]], %[[VAL_11]]) <{axis = 0 : i32, values_count = 2 : i32}> : (tensor<5x7xf32>, tensor<5x7xf32>) -> tensor<2x5x7xf32>
# CHECK:           return %[[VAL_12]] : tensor<2x5x7xf32>

func.func @batchmatmulv2_basic(%arg0: tensor<1x4x2xf32>, %arg1: tensor<3x2x4xf32>) -> tensor<3x4x4xf32> {
// CHECK-LABEL:   func @batchmatmulv2_basic
// CHECK-SAME:        ([[LHS:%.*]]: tensor<1x4x2xf32>, [[RHS:%.*]]: tensor<3x2x4xf32>) -> tensor<3x4x4xf32>
// CHECK:           [[LHSSHAPE:%.*]] = shape.shape_of [[LHS]] : tensor<1x4x2xf32>
// CHECK:           [[RHSSHAPE:%.*]] = shape.shape_of [[RHS]] : tensor<3x2x4xf32>
// CHECK:           [[CM2:%.*]] = arith.constant -2 : index

  // CHECK: "tf.BatchMatMulV2"(%arg0, %arg1) <{adj_x = false, adj_y = false, grad_x = false, grad_y = false}> {device = "/job:localhost/replica:0/task:0/device:GPU:0"}
  %0 = "tf.BatchMatMul"(%arg0, %arg1) <{adj_x = false, adj_y = false}> {device = "/job:localhost/replica:0/task:0/device:GPU:0"} : (tensor<2x3x5xf32>, tensor<2x5x7xf32>) -> tensor<2x3x7xf32>
  func.return %0: tensor<2x3x7xf32>
}

  // CHECK-SAME: %[[ARG0:.*]]: tensor<3x4x5xf32>
  // CHECK-SAME: %[[ARG1:.*]]: tensor<3x5x2xf32>
  // CHECK-SAME: %[[ARG2:.*]]: tensor<2x3x2xi64>
  func.func private @composite_and_gather(%arg0: tensor<3x4x5xf32>, %arg1: tensor<3x5x2xf32>, %arg2: tensor<2x3x2xi64>) -> tensor<2x3x2x2xf32> {
    // CHECK: %[[Q1:.*]] = "quantfork.qcast"(%[[ARG0]]) {volatile} : (tensor<3x4x5xf32>) -> tensor<3x4x5x!quant.uniform<i8:f32, 5.000000e-03>>

  producer: 175
}

# CHECK: func @main(%[[VAL_0:.*]]: tensor<2x5x3xf32>, %[[VAL_1:.*]]: tensor<3x7xf32>) -> tensor<2x5x7xf32> attributes {tf.entry_function = {control_outputs = "", inputs = "Placeholder,Placeholder_1", outputs = "MatMul"}} {
# CHECK:     %[[VAL_2:.*]] = "tfl.batch_matmul"(%[[VAL_0]], %[[VAL_1]]) <{adj_x = false, adj_y = false}> : (tensor<2x5x3xf32>, tensor<3x7xf32>) -> tensor<2x5x7xf32>
# CHECK:     return %[[VAL_2]] : tensor<2x5x7xf32>

func.func @lower_einsum(%arg0: tensor<3x4x5xf32>, %arg1: tensor<3x5x6xf32>) -> tensor<3x4x6xf32> {
  %0 = "tf.Einsum"(%arg0, %arg1) {T = "tfdtype$DT_FLOAT", equation = "ijk,ikm->ijm"}: (tensor<3x4x5xf32>, tensor<3x5x6xf32>) -> tensor<3x4x6xf32>
  func.return %0 : tensor<3x4x6xf32>
}
// CHECK-LABEL: lower_einsum
// CHECK: "tf.BatchMatMulV2"(%arg0, %arg1) <{adj_x = false, adj_y = false}> : (tensor<3x4x5xf32>, tensor<3x5x6xf32>) -> tensor<3x4x6xf32>

// RUN: odml-to-stablehlo-opt %s -tfl-legalize-hlo -split-input-file | FileCheck %s --dump-input=fail

func.func @main(%arg0: tensor<5x7xf32>) -> tensor<5x7xf32> {
  func.return %arg0: tensor<5x7xf32>
// CHECK-LABEL: main
// CHECK: return %arg0 : tensor<5x7xf32>
}

// - transpose
//
func.func @transpose_2d(%arg0: tensor<2x3xf32>) -> tensor<3x2xf32> {

  func.func private @not_quantize_singular_op_without_static_range_ptq(%arg: tensor<3x4x2xf32>) -> tensor<2x3x2x2xf32> attributes {tf._original_func_name = "main_0"} {
    %cst = "tf.Const"() {value = dense<1> : tensor<2x3x2xi32>} : () -> tensor<2x3x2xi32>
    %0 = "quantfork.stats"(%arg) {layerStats = dense<[4.00000000e-6, 9.80000000e-1]> : tensor<2xf32>} : (tensor<3x4x2xf32>) -> tensor<3x4x2xf32>

  constexpr absl::string_view kModuleGather = R"mlir(
    module {
      func.func @main() -> (tensor<2x3x2x2xf32>) {
        %0 = stablehlo.constant dense<1.0> : tensor<3x4x2xf32>
        %1 = stablehlo.constant dense<2> : tensor<2x3x2xi64>
        %2 = "stablehlo.gather"(%0, %1) {
          dimension_numbers = #stablehlo.gather<
            offset_dims = [2, 3],

func.func @no_qdq_except_conv_and_dot_general(%arg0: tensor<2x3x2xi64>) -> tensor<2x3x2x2xf32> attributes {tf._original_func_name = "main_0"} {
  %cst = "tf.Const"() {value = dense<3.000000e-01> : tensor<3x4x2xf32>} : () -> tensor<3x4x2xf32>
  %0 = "tf.XlaCallModule"(%cst, %arg0) {
    Sout = [#tf_type.shape<1x3>], _entry_function = @composite_gather_fn,
    _original_entry_function = "composite_gather_fn", _quantization_method = "weight_only_ptq { }",