{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

func.func private @test_fuse_dynamic_dimension_ops(%arg0: tensor<?x?xi32>, %arg1: tensor<*x!tf_type.resource>, %arg2: tensor<2xi64>, %arg3: tensor<?xi64>, %arg4: tensor<?xi64>) -> tensor<*xi32> {
  // CHECK-NOT: tf._TPUCompileMlirOp
  // CHECK-NOT: tf.TPUCompileSucceededAssert
  // CHECK-NOT: tf.TPUExecuteOp
  // CHECK-NOT: tf.SetStaticDimensionBounds

  // CHECK: [[read_result:%.*]] = "tf.ReadVariableOp"(%arg1)

func.func @num_replicas_replicated(%arg0: tensor<i32>, %arg1: tensor<i32>, %arg2: tensor<i32>, %arg3: tensor<i32>) -> (tensor<i32>, tensor<i32>) {
  %0:2 = tf_executor.graph {
    %control = tf_executor.island() wraps "tf.TPUReplicateMetadata"() {_tpu_replicate = "cluster", device = "/device:TPU:0", num_replicas = 2, topology = "topology"} : () -> ()

		{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

// CHECK-NEXT:  [[ADD_2:%.*]] = "tf.AddV2"(%arg0, [[CST]])
// CHECK-NEXT:  return [[ADD_2]], %arg1, [[ADD]], [[TENSOR_MAP_INSERT_RESULT]]

func.func @otherVariantWhileCond(%arg0: tensor<i32>, %arg1: tensor<i32>, %arg2: tensor<i32>, %arg3: tensor<!tf_type.variant>) -> tensor<i1> {
  %0 = "tf.Const"() {value = dense<10> : tensor<i32>} : () -> tensor<i32>

// CHECK:           return %[[VAL_9]] : tensor<384x512xf32>
// CHECK:         }

// -----

func.func @padConcatTo4D(%arg0: tensor<384x384xf32>, %arg1: tensor<384x384xf32>, %arg2: tensor<384x384xf32>, %arg3: tensor<384x384xf32>) -> tensor<1536x384xf32> {

```
func @simpleTest(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>, %arg2: tensor<1xf32>, %arg3: tensor<1xf32>) -> tensor<2x1xf32> {
    %0 = call @func_0_GPU_FLOAT(%arg0, %arg1, %arg2) {tac.device = "GPU", tac.inference_type = "FLOAT", tac.interface_name = "func_0"} : (tensor<1xf32>, tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>

func.func @generator_op(%str : tensor<!tf_type.string>, %arg0: tensor<*x!tf_type.string>, %arg1: tensor<!tf_type.string>, %arg2: tensor<*xi64>, %arg3: tensor<!tf_type.string>) {
  tf_executor.graph {
    tf_executor.island {
      // CHECK: %{{.*}}, %[[CONTROL:[^ ,]*]] = tf_executor.island wraps "tf.GeneratorDataset"
      %gen0 = "tf.GeneratorDataset"(%str, %arg0, %arg1, %arg2, %arg3) {
        finalize_func = @__finalize_func_790,

module {
  func.func @main(%arg0: tensor<100xf32>, %arg1: tensor<100xf32>, %arg2: tensor<100xf32>, %arg3: tensor<100xf32>) -> tensor<2x100xf32> {
    %0 = func.call @func_0_GPU_FLOAT(%arg0, %arg1, %arg2) {tac.device = "GPU", tac.inference_type = "FLOAT", tac.interface_name = "func_0"} : (tensor<100xf32>, tensor<100xf32>, tensor<100xf32>) -> tensor<100xf32>

  }
// CHECK: func private @mul1(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>) -> tensor<1xf32> attributes {tf.entry_function = {inputs = "mul1_y:0,mul1_x:0", outputs = "PartitionedCall:0"}}
// CHECK:   %[[MUL_0:.*]] = "tf.Mul"(%arg1, %arg0) : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
// CHECK:   return %[[MUL_0]] : tensor<1xf32>
// CHECK: }