// CHECK: {
// CHECK-NEXT:  version: 3,
// CHECK-NEXT:  operator_codes: [ {
// CHECK-NEXT:    deprecated_builtin_code: 67,
// CHECK-NEXT:    version: 1,
// CHECK-NEXT:    builtin_code: TRANSPOSE_CONV
// CHECK-NEXT:  } ],
// CHECK-NEXT:  subgraphs: [ {
// CHECK-NEXT:    tensors: [ {
// CHECK-NEXT:      shape: [ 4 ],
// CHECK-NEXT:      type: INT32,
// CHECK-NEXT:      buffer: 1,

// tfl.relu / tfl.relu6 / tfl.rsqrt / tfl.sin / tfl.slice / tfl.softmax /
// tfl.space_to_depth / tfl.sqrt / tfl.square / tfl.squared_difference /
// tfl.strided_slice / tfl.tanh / tfl.transpose / tfl.transpose_conv
class GpuBasicSupportedOpNoCost : public TargetHardwareOperation {
  double GetOpCost(mlir::Operation* op) const override { return 0; }

  bool IsOpSupported(mlir::Operation* op) const override {

  %cst = "tfl.no_value"() {value = unit} : () -> none
  // CHECK: _arithmetic_count = 176160768 : i64
  %0 = "tfl.transpose_conv"(%arg0, %arg1, %arg2, %cst) {padding = "SAME", stride_h = 2 : i32, stride_w = 2 : i32, fused_activation_function = "NONE"} : (tensor<4xi32>, tensor<32x4x4x128xf32>, tensor<1x32x42x128xf32>, none) -> tensor<1x64x84x32xf32>