%cst = "tfl.pseudo_qconst"() {qtype = tensor<1x2x!quant.uniform<u8:f32, 1.0>>, value = dense<-76> : tensor<1x2xi8>} : () -> tensor<1x2x!quant.uniform<u8:f32, 1.0>>

}

// CHECK-LABEL: EliminateRedundantLogicalOr
func.func @EliminateRedundantLogicalOr(%arg0: tensor<1xi1>, %arg1: tensor<2x3xi1>) -> (tensor<1xi1>, tensor<2x3xi1>, tensor<2x3xi1>, tensor<2x3xi1>, tensor<2x3xi1>, tensor<2x3xi1>, tensor<1xi1>, tensor<2x3xi1>, tensor<2x3xi1>, tensor<2x3xi1>, tensor<2x3xi1>, tensor<2x3xi1>, tensor<2x3xi1>, tensor<2x3xi1>) {
  %cst_false0 = arith.constant dense<false> : tensor<1xi1>

}

TEST_F(ConvertTfQuantToMhloIntTest, UniformRequantizeToValidGraph) {
  constexpr absl::string_view kProgram = R"mlir(
func.func @main(%input: tensor<10xi8>) -> tensor<10xi8> {
  %input_scale = "tf.Const"() { value = dense<0.2235> : tensor<f32> } : () -> tensor<f32>
  %input_zp = "tf.Const"() { value = dense<-2> : tensor<i32> } : () -> tensor<i32>

  "tf_saved_model.asset"() {sym_name = "z", filename = "file"} : () -> ()
  func.func @serving_default(
      %arg0: tensor<1x3xi32> {tf_saved_model.index_path = ["x"]},
      %arg1: tensor<!tf_type.resource<tensor<3x1xi32>>> {tf_saved_model.bound_input = @y},
      %arg2: tensor<!tf_type.string> {tf_saved_model.bound_input = @z}

      return %1 : tensor<1x3x!quant.uniform<i8:f32, 5.000000e+0>>
    }
  )mlir";

  const OwningOpRef<ModuleOp> module_op =
      ParseModuleOpString(kQuantizedDotGeneral);
  ASSERT_TRUE(module_op);

  const QuantizationReport report(*module_op);
  const QuantizationResults& results = report.GetQuantizationResults();

func.func @equal_broadcast(%arg0: tensor<1xi32>, %arg1: tensor<1x2xi32>) -> tensor<1x2xi1> {
  // CHECK-DAG: %[[LHS_BCAST:.+]] = "mhlo.broadcast_in_dim"(%arg0) <{broadcast_dimensions = dense<1> : tensor<1xi64>}>
  // CHECK-NEXT: mhlo.compare EQ, %[[LHS_BCAST]], %arg1
  %0 = "tf.Equal"(%arg0, %arg1) : (tensor<1xi32>, tensor<1x2xi32>) -> tensor<1x2xi1>
  func.return %0: tensor<1x2xi1>
}

// CHECK-LABEL: func @equal_broadcast_no_incompatible_shapes_error

// CHECK: %[[quant:.*]] = "tfr.cast"(%arg0) : (tensor<1x10xi8>) -> !tfr.tensor
// CHECK: %[[scale_cast:.*]] = "tfr.cast"(%[[scale]])
// CHECK: %[[zp_cast:.*]] = "tfr.cast"(%[[zp]])
// CHECK: %[[requant:.*]] = tfr.call @tf__requantize(%[[quant]], %[[scale_cast]], %[[zp_cast]])
// CHECK: %[[result:.*]] = "tfr.cast"(%[[requant]])
// CHECK-NOT: quant.uniform
// CHECK: return %[[result]], %[[float_resunt:.*]] : tensor<1x10xi8>, tensor<1x5xf32>
}

// PerTensor-SAME: f = @quantized_matmul_fn_0}> : (tensor<2x12xf32>, tensor<12x2xi8>, tensor<f32>, tensor<i32>) -> tensor<*xf32>
// PerTensor: return %[[out]]

// PerChannel-LABEL: func @matmul
// PerChannel-DAG: %[[q_w:.*]] = "tf.Const"() <{value = dense<0> : tensor<12x2xi8>}> : () -> tensor<12x2xi8>
// PerChannel-DAG: %[[scale:.*]] = "tf.Const"() <{value = dense<3.93700805E-9> : tensor<f32>}> : () -> tensor<f32>

    return %0 : tensor<1x3xf32>
  }
}

// CHECK-LABEL: quantize_dot_general_per_tensor
// CHECK-SAME: %[[ARG0:.+]]: tensor<1x2xf32>
// CHECK: %[[CST:.+]] = stablehlo.constant() <{value = dense<127> : tensor<2x3xi8>}> : () -> tensor<2x3x!quant.uniform<i8<-127:127>:f32, 0.0023622048182750312>>

  // CHECK: %[[WHILE_RESULT:.*]]:2 = mhlo.while(%[[ARG0:.*]] = %[[INT0]], %[[ARG1:.*]] = %[[INT1]])
  // CHECK-SAME: tensor<2x2xi8>, tensor<2x2xi8>

  // CHECK: cond

  // CHECK: do
  // CHECK: mhlo.return %[[ARG0]], %[[ARG1]] : tensor<2x?xi8>, tensor<?x2xi8>

  %2:2 = "tf.WhileRegion"(%0, %1) ({
  ^bb0(%carg0: tensor<2x2x!tf_type.qint8>, %carg1: tensor<2x2x!tf_type.qint8>):