// CHECK-LABEL: float_matmul
func.func @float_matmul(
  %arg0: tensor<1x10xf32>, %arg1: tensor<10x10xf32>) -> (tensor<*xf32>, tensor<*xf32>, tensor<*xf32>) {
  %cst = "tf.Const"() {value = dense<0.000000e+00> : tensor<10xf32>} : () -> tensor<10xf32>
  %0 = "tf.MatMul"(%arg0, %arg1) {
    transpose_a = false, transpose_b = false
  } : (tensor<1x10xf32>, tensor<10x10xf32>) -> tensor<*xf32>

  func.return %1 : tensor<16x128xf32>
  // CHECK: return %0 : tensor<16x128xf32>
}

// CHECK-LABEL: FuseTransposeFCLhsToBatchMatmul

}

// CHECK-LABEL: @broadcast_batch_matmul_v2_lhs
func.func @broadcast_batch_matmul_v2_lhs(%arg0: tensor<17x17xf32>, %arg1: tensor<17x17x24xf32>) -> tensor<17x17x24xf32> {
  %cst = arith.constant dense<[17, 17, 17]> : tensor<3xi64>
  %0 = "tf.BroadcastTo"(%arg0, %cst) : (tensor<17x17xf32>, tensor<3xi64>) -> tensor<17x17x17xf32>

// NOFALLBACK-LABEL: @xla_svd
func.func @xla_svd(%arg0: tensor<1x1xf32>) -> (tensor<1xf32>, tensor<1x1xf32>, tensor<1x1xf32>) {
  // NOFALLBACK: XlaSvd
  %s, %u, %v = "tf.XlaSvd"(%arg0) {max_iter = 1, epsilon = 1.0E-09 : f32, precision_config = ""} : (tensor<1x1xf32>) -> (tensor<1xf32>, tensor<1x1xf32>, tensor<1x1xf32>)
  func.return %s, %u, %v : tensor<1xf32>, tensor<1x1xf32>, tensor<1x1xf32>
}

  func.return %0 : tensor<8x16xf32>
}

// -----

func.func @testCumprod(%arg: tensor<8x16xf32>) -> tensor<8x16xf32> {
  %axis = arith.constant dense<-3> : tensor<i32>
  // expected-error @+1 {{axis operand should be within range [-2, 2)}}
  %0 = "tf.Cumprod"(%arg, %axis) : (tensor<8x16xf32>, tensor<i32>) -> tensor<8x16xf32>
  func.return %0 : tensor<8x16xf32>
}

    %cst = "tf.Const"() {value = dense<0.000000e+00> : tensor<10xf32>} : () -> tensor<10xf32>
    %cst_0 = "tf.Const"() {value = dense<[-1, 10]> : tensor<2xi32>} : () -> tensor<2xi32>
    %1 = "tf.MatMul"(%arg0, %arg1) {
      transpose_a = false, transpose_b = false

  constexpr absl::string_view kProgram = R"mlir(
func.func @main(
    %arg0: tensor<10x10xf32>, %scale: tensor<10xf32>, %zp: tensor<10xi32>
  ) -> tensor<10x10xi8> {
  %0 = "tf.UniformQuantize"(%arg0, %scale, %zp) {
    quantization_axis = 1 : i64,
    quantization_min_val = -128 : i64,
    quantization_max_val = 127 : i64
  } : (tensor<10x10xf32>, tensor<10xf32>, tensor<10xi32>) -> tensor<10x10x!tf_type.qint8>

func.func @QuantizedCatsAddRequantsTest(%arg0: tensor<1x1xf32>, %arg1: tensor<1x1xf32>, %arg2: tensor<1x1xf32>, %arg3: tensor<1x1xf32>) -> (tensor<1x4xf32>, tensor<1x3xf32>) {
  %0 = "quantfork.stats"(%arg0) {layerStats = dense<[-0.440728068, 0.189515018]> : tensor<2xf32>} : (tensor<1x1xf32>) -> tensor<1x1xf32>
  %1 = "quantfork.stats"(%arg1) {layerStats = dense<[-0.154693216, 0.26483655]> : tensor<2xf32>} : (tensor<1x1xf32>) -> tensor<1x1xf32>

// CHECK: return %[[identity]] : tensor<1x3x2x2xf32>

func.func @cast_bf16_matmul_to_fp32(%arg0: tensor<1x10xf32>) -> (tensor<1x2xf32>) {
  %cst = "tf.Const"() {device = "", value = dense<1.000000e+01> : tensor<10x2xbf16>} : () -> tensor<10x2xbf16>
  %0 = "tf.Cast"(%arg0) {Truncate = false, device = ""} : (tensor<1x10xf32>) -> tensor<1x10xbf16>

    "tfl.yield"(%1#0, %1#1, %1#2) : (tensor<1x?x16xf32>, tensor<1x!tf_type.string>, tensor<1xi32>) -> ()
  }) {_tfl_quant_trait = "fully_quantizable"} : (tensor<1x!tf_type.string>) -> (tensor<1x?x16xf32>, tensor<1x!tf_type.string>, tensor<1xi32>)