我正在创建一种机制,允许用户使用装饰器模式从基本构建块形成任意复杂的功能。这在功能方面工作得很好,但我不喜欢它涉及大量虚拟调用的事实,尤其是当嵌套深度变大时。这让我很担心,因为复杂的函数可能会经常调用(> 100.000 次)。
为了避免这个问题,我尝试在装饰器方案std::function
完成后将其转换为 a (to_function()
参见 SSCCE 中的)。所有内部函数调用都在std::function
. 我认为这会比原始装饰器方案更快地评估,因为不需要在std::function
版本中执行虚拟查找。
唉,基准测试证明我错了:装饰器方案实际上比std::function
我用它构建的更快。所以现在我想知道为什么。也许我的测试设置有问题,因为我只使用了两个微不足道的基本功能,这意味着可能会缓存 vtable 查找?
我使用的代码包含在下面,不幸的是它很长。
SSCCE
// sscce.cpp
#include <iostream>
#include <vector>
#include <memory>
#include <functional>
#include <random>
/**
* Base class for Pipeline scheme (implemented via decorators)
*/
class Pipeline {
protected:
std::unique_ptr<Pipeline> wrappee;
Pipeline(std::unique_ptr<Pipeline> wrap)
:wrappee(std::move(wrap)){}
Pipeline():wrappee(nullptr){}
public:
typedef std::function<double(double)> FnSig;
double operator()(double input) const{
if(wrappee.get()) input=wrappee->operator()(input);
return process(input);
}
virtual double process(double input) const=0;
virtual ~Pipeline(){}
// Returns a std::function which contains the entire Pipeline stack.
virtual FnSig to_function() const=0;
};
/**
* CRTP for to_function().
*/
template <class Derived>
class Pipeline_CRTP : public Pipeline{
protected:
Pipeline_CRTP(const Pipeline_CRTP<Derived> &o):Pipeline(o){}
Pipeline_CRTP(std::unique_ptr<Pipeline> wrappee)
:Pipeline(std::move(wrappee)){}
Pipeline_CRTP():Pipeline(){};
public:
typedef typename Pipeline::FnSig FnSig;
FnSig to_function() const override{
if(Pipeline::wrappee.get()!=nullptr){
FnSig wrapfun = Pipeline::wrappee->to_function();
FnSig processfun = std::bind(&Derived::process,
static_cast<const Derived*>(this),
std::placeholders::_1);
FnSig fun = [=](double input){
return processfun(wrapfun(input));
};
return std::move(fun);
}else{
FnSig processfun = std::bind(&Derived::process,
static_cast<const Derived*>(this),
std::placeholders::_1);
FnSig fun = [=](double input){
return processfun(input);
};
return std::move(fun);
}
}
virtual ~Pipeline_CRTP(){}
};
/**
* First concrete derived class: simple scaling.
*/
class Scale: public Pipeline_CRTP<Scale>{
private:
double scale_;
public:
Scale(std::unique_ptr<Pipeline> wrap, double scale) // todo move
:Pipeline_CRTP<Scale>(std::move(wrap)),scale_(scale){}
Scale(double scale):Pipeline_CRTP<Scale>(),scale_(scale){}
double process(double input) const override{
return input*scale_;
}
};
/**
* Second concrete derived class: offset.
*/
class Offset: public Pipeline_CRTP<Offset>{
private:
double offset_;
public:
Offset(std::unique_ptr<Pipeline> wrap, double offset) // todo move
:Pipeline_CRTP<Offset>(std::move(wrap)),offset_(offset){}
Offset(double offset):Pipeline_CRTP<Offset>(),offset_(offset){}
double process(double input) const override{
return input+offset_;
}
};
int main(){
// used to make a random function / arguments
// to prevent gcc from being overly clever
std::default_random_engine generator;
auto randint = std::bind(std::uniform_int_distribution<int>(0,1),std::ref(generator));
auto randdouble = std::bind(std::normal_distribution<double>(0.0,1.0),std::ref(generator));
// make a complex Pipeline
std::unique_ptr<Pipeline> pipe(new Scale(randdouble()));
for(unsigned i=0;i<100;++i){
if(randint()) pipe=std::move(std::unique_ptr<Pipeline>(new Scale(std::move(pipe),randdouble())));
else pipe=std::move(std::unique_ptr<Pipeline>(new Offset(std::move(pipe),randdouble())));
}
// make a std::function from pipe
Pipeline::FnSig fun(pipe->to_function());
double bla=0.0;
for(unsigned i=0; i<100000; ++i){
#ifdef USE_FUNCTION
// takes 110 ms on average
bla+=fun(bla);
#else
// takes 60 ms on average
bla+=pipe->operator()(bla);
#endif
}
std::cout << bla << std::endl;
}
基准
使用pipe
:
g++ -std=gnu++11 sscce.cpp -march=native -O3
sudo nice -3 /usr/bin/time ./a.out
-> 60 ms
使用fun
:
g++ -DUSE_FUNCTION -std=gnu++11 sscce.cpp -march=native -O3
sudo nice -3 /usr/bin/time ./a.out
-> 110 ms