{name: "SUBshiftRLreg", argLength: 3, reg: gp31, asm: "SUB"}, // arg0 - arg1>>arg2, unsigned shift
		{name: "SUBshiftRAreg", argLength: 3, reg: gp31, asm: "SUB"}, // arg0 - arg1>>arg2, signed shift
		{name: "RSBshiftLLreg", argLength: 3, reg: gp31, asm: "RSB"}, // arg1<<arg2 - arg0
		{name: "RSBshiftRLreg", argLength: 3, reg: gp31, asm: "RSB"}, // arg1>>arg2 - arg0, unsigned shift

// CHECK-LABEL: func private @quantized_conv2d_with_bias_and_relu6_fn_0
// CHECK-SAME: (%arg0: tensor<1x2x2x3xi8>, %arg1: tensor<2x2x3x2xi8>, %arg2: tensor<2xi32>, %arg3: tensor<f32>, %arg4: tensor<i32>, %arg5: tensor<2xf32>, %arg6: tensor<2xi32>, %arg7: tensor<2xf32>, %arg8: tensor<2xi32>, %arg9: tensor<f32>, %arg10: tensor<i32>) -> tensor<*xi8>
// CHECK:      %[[CONV2D_0:.*]] = "tf.Conv2D"

// CHECK: func private @tf.IfRegion_else(%arg0: tensor<i1>, %arg1: tensor<2xf32>, %arg2: tensor<2xf32>, %arg3: tensor<2xf32>) -> tensor<2xf32>
// CHECK-NEXT: "tf.Select"(%arg0, %arg2, %arg3)
// CHECK: func private @tf.IfRegion_then(%arg0: tensor<i1>, %arg1: tensor<2xf32>, %arg2: tensor<2xf32>, %arg3: tensor<2xf32>) -> tensor<2xf32>
// CHECK-NEXT: "tf.Select"(%arg0, %arg1, %arg2)
func.func @testIfCondition(%arg0: tensor<i1>, %arg1: tensor<2xf32>) -> tensor<2xf32> {

func.func @func_with_sharding_inside_while_body(%arg0: tensor<i32>, %arg1: tensor<128x1024xf32>) -> (tensor<128x1024xf32>) {
  %cst = "tf.Const"() <{value = dense<0> : tensor<i32>}> {device = ""} : () -> tensor<i32>
  %0:2 = "tf.WhileRegion"(%cst, %arg1) <{is_stateless = false, parallel_iterations = 1 : i64}> ({
    ^bb0(%arg2: tensor<i32>, %arg3: tensor<128x1024xf32>):
      %1 = "tf.Less"(%arg2, %arg0) : (tensor<i32>, tensor<i32>) -> tensor<i1>

  // CHECK: [[PI_0:%.*]] = "tf.TPUPartitionedInputV2"([[ARG0]], [[ARG1]])
  %pi_0 = "tf.TPUPartitionedInputV2"(%arg0, %arg1) {device = "", partition_dims = []} : (tensor<!tf_type.resource<tensor<10x3xf32>>>, tensor<!tf_type.resource<tensor<10x3xf32>>>) -> tensor<!tf_type.resource<tensor<10x3xf32>>>
  // CHECK: [[PI_1:%.*]] = "tf.TPUPartitionedInputV2"([[ARG2]], [[ARG3]])

  %0 = "tfl.transpose"(%arg0, %cst_1) : (tensor<4x4x3xf32>, tensor<3xi32>) -> tensor<4x4x3xf32>
  %1:6 = "tfl.while"(%cst_7, %cst_7, %cst_2, %cst, %cst, %0) ({
  ^bb0(%arg1: tensor<i32>, %arg2: tensor<i32>, %arg3: tensor<*xf32>, %arg4: tensor<4x2xf32>, %arg5: tensor<4x2xf32>, %arg6: tensor<*xf32>):
    %5 = "tfl.less"(%arg2, %cst_3) : (tensor<i32>, tensor<i32>) -> tensor<i1>

		{name: "SUBLloadidx4", argLength: 4, reg: gp21loadidx, asm: "SUBL", aux: "SymOff", resultInArg0: true, clobberFlags: true, symEffect: "Read"},  // arg0 - tmp, tmp loaded from  arg1+arg2*4+auxint+aux, arg3 = mem

		{name: "ADDF", argLength: 2, reg: fp21, asm: "ADDF", commutative: true}, // arg0 + arg1
		{name: "ADDD", argLength: 2, reg: fp21, asm: "ADDD", commutative: true}, // arg0 + arg1
		{name: "SUBF", argLength: 2, reg: fp21, asm: "SUBF"},                    // arg0 - arg1
		{name: "SUBD", argLength: 2, reg: fp21, asm: "SUBD"},                    // arg0 - arg1

  }

  func.func private @while_cond(%arg0: tensor<i32>, %arg1: tensor<i32>, %arg2: tensor<i32>, %arg3: tensor<1x1024xbf16>, %arg4: tensor<1024x1024xbf16>) -> tensor<i1>
  {
    %cst = "tf.Const"() {value = dense<1> : tensor<i32>} : () -> tensor<i32>
    %0 = "tf.Less"(%arg0, %cst) : (tensor<i32>, tensor<i32>) -> tensor<i1>
    func.return %0 : tensor<i1>

  func.return %4 : tensor<128x128x!quant.uniform<u8:f32, 0.2:125>>

// CHECK: %4 = "tfl.custom_tf"(%arg0, %arg1, %arg2, %arg3) ({
// CHECK-NEXT: ^bb0(%arg4: tensor<128x128xf32>, %arg5: tensor<1xf32>, %arg6: tensor<1xf32>, %arg7: tensor<1xi32>):