// CHECK-NOT: tf
func.func @strips_attributes(%arg0: tensor<32x28x28x1xf32> {tf._user_specified_name = "x"},
                             %arg1: tensor<3x3x1x5xf32> {tf._user_specified_name = "w1"},
                             %arg2: tensor<5xf32> {tf._user_specified_name = "b1"},
                             %arg3: tensor<3920x10xf32> {tf._user_specified_name = "w2"},

  // CHECK-LABEL: @serving_default
  // CHECK-SAME: %[[ARG0:[^:[:space:]]+]]
  // CHECK-SAME: %[[ARG1:[^:[:space:]]+]]
  func.func private @serving_default(%arg0: tensor<1x4xf32>, %arg1: tensor<4x3xf32>) -> tensor<1x3xf32> {

		{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

    @Override
    public String generateType1Msg(final String arg0, final String arg1) throws NTLMEngineException {
        // TODO Auto-generated method stub
        return null;
    }

    @Override
    public String generateType3Msg(final String arg0, final String arg1, final String arg2, final String arg3, final String arg4)
            throws NTLMEngineException {
        // TODO Auto-generated method stub

// CHECK-LABEL:func @replicated
// CHECK-SAME: ([[ARG0:%.*]]: tensor<!tf_type.resource<tensor<10x3xf32>>>, [[ARG1:%.*]]: tensor<!tf_type.resource<tensor<10x3xf32>>>, [[ARG2:%.*]]: tensor<!tf_type.resource<tensor<10x3xf32>>>, [[ARG3:%.*]]: tensor<!tf_type.resource<tensor<10x3xf32>>>)

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 @main(%arg0: tensor<i32>, %arg1: tensor<1xf32>) -> tensor<1xf32> {
  // While %arg0 is greater than zero, element wise add %arg1 with itself.
  %0:2 = "tfl.while"(%arg0, %arg1) ({
  ^bb0(%arg2: tensor<*xi32>, %arg3: tensor<*xf32>):
    %1 = func.call @cond(%arg2, %arg3) : (tensor<*xi32>, tensor<*xf32>) -> tensor<i1>
    "tfl.yield"(%1) : (tensor<i1>) -> ()
  },  {
  ^bb0(%arg2: tensor<*xi32>, %arg3: tensor<*xf32>):

		{{end}}

		// round 1
		{{range $i, $s := dup 4 .Shift1 -}}
			{{printf "arg0 = arg1 + bits.RotateLeft32((((arg2^arg3)&arg1)^arg3)+arg0+x%x+%#08x, %d)" (idx 1 $i) (index $.Table1 $i) $s | relabel}}
			{{rotate -}}
		{{end}}

		// round 2
		{{range $i, $s := dup 4 .Shift2 -}}
			{{printf "arg0 = arg1 + bits.RotateLeft32((((arg1^arg2)&arg3)^arg2)+arg0+x%x+%#08x, %d)" (idx 2 $i) (index $.Table2 $i) $s | relabel}}
			{{rotate -}}

		// unsigned arg0 >> arg2, shifting in bits from arg1 (==(arg1<<64+arg0)>>arg2, keeping low 64 bits), shift amount is mod 64
		{name: "SHRDQ", argLength: 3, reg: gp31shift, asm: "SHRQ", resultInArg0: true, clobberFlags: true},
		// unsigned arg0 << arg2, shifting in bits from arg1 (==(arg0<<64+arg1)<<arg2, keeping high 64 bits), shift amount is mod 64

		{name: "FNMSUBS", argLength: 3, reg: fp31, asm: "FNMSUBS"}, // -arg0 + (arg1 * arg2)
		{name: "FNMSUBD", argLength: 3, reg: fp31, asm: "FNMSUBD"}, // -arg0 + (arg1 * arg2)
		{name: "MADD", argLength: 3, reg: gp31, asm: "MADD"},       // +arg0 + (arg1 * arg2)
		{name: "MADDW", argLength: 3, reg: gp31, asm: "MADDW"},     // +arg0 + (arg1 * arg2), 32-bit
		{name: "MSUB", argLength: 3, reg: gp31, asm: "MSUB"},       // +arg0 - (arg1 * arg2)