thrust exception bulk_kernel_by_value in transform_reduce

I'm working on a optimization problem which contains various math functions which resembles in similar form, so I warp them in a FunctionObj

template <typename T>
struct FunctionObj
{
    T a;
     FunctionObj(): a(1)
    {
    }
};

And defines a FuncEval to evaluate

template <typename T>
__host__ __device__  inline T FuncEval(const FunctionObj<T> &f_obj, T x)
{
    return f_obj.a+x;
}

What I really want to do is sum {func(x)}, so I defines a FuncEvalF functor to make use of thrust::tranform_reduce

template <typename T>
struct FuncEvalF
{
    const FunctionObj<T>& f_obj;
    __host__ __device__ inline FuncEvalF(const FunctionObj<T>& in_f_obj) :f_obj(in_f_obj)
{

}
    __host__ __device__ inline T operator()(T x)
    {
        return FuncEval(f_obj, x);
    }
};

template <typename T>
__host__ __device__ inline T BatchFuncEval(const FunctionObj<T>  &f_obj, int size, const T *x_in);
template<>
inline float BatchFuncEval< float>(const FunctionObj<float>  &f_obj, int size, const float *x_in)
{
    return thrust::transform_reduce(thrust::device, thrust::device_pointer_cast(x_in), thrust::device_pointer_cast(x_in + size), FuncEvalF<float>(f_obj), static_cast<float>(0), thrust::plus<float>());
}

Finally in the main.cu I call the transform_reduce

auto func = FuncEvalF<float>(FunctionObj<float>());
    float result = 0;
    try
    {
        result = thrust::transform_reduce(thrust::device, thrust::device_pointer_cast(dev_a), thrust::device_pointer_cast(dev_a + 10000), func, static_cast<float>(0), thrust::plus<float>());

    }
    catch (std::exception e)
    {
        printf("%s in thurst \n ", e.what());
    }

Here the exception comes : bulk_kernel_by_value, even I change the 10000 to 10. Thing only goes better when I change the defintion of FuncEval to

return x;

The program would output the right but meaningless answer . I can't help asking what's wrong with my code ? Thank you for your attention.