今週、boost::object_pool について知り、通常の new & delete よりも約 20 ~ 30% 高速であることに驚きました。
テストのために、boost::chrono を使用して異なるヒープ アロケーター/デアロケーター (shared_ptr) の時間を計測する小さな C++ アプリを作成しました。関数自体は、'new' と 'delete' を使用して 60M 反復の単純なループを実行します。コードの下:
#include <iostream>
#include <memory>
using std::shared_ptr;
#include <boost/smart_ptr.hpp>
#include <boost/chrono.hpp>
#include <boost/chrono/chrono_io.hpp>
#include <boost/pool/object_pool.hpp>
#include <SSVUtils/SSVUtils.h>
#include "TestClass.h"
const long lTestRecursion = 60000000L;
void WithSmartPtrs()
{
boost::chrono::system_clock::time_point startTime = boost::chrono::system_clock::now();
std::cout << "Start time: " << startTime << std::endl;
for (long i=0; i < lTestRecursion; ++i)
{
boost::shared_ptr<TestClass> spTC = boost::make_shared<TestClass>("Test input data!");
}
boost::chrono::system_clock::time_point endTime = boost::chrono::system_clock::now();
std::cout << "End time: " << endTime << std::endl;
boost::chrono::duration<double> d = endTime - startTime;
std::cout << "Duration: " << d << std::endl;
}
void WithSTDSmartPtrs()
{
boost::chrono::system_clock::time_point startTime = boost::chrono::system_clock::now();
std::cout << "Start time: " << startTime << std::endl;
for (long i=0; i < lTestRecursion; ++i)
{
std::shared_ptr<TestClass> spTC = std::make_shared<TestClass>("Test input data!");
}
boost::chrono::system_clock::time_point endTime = boost::chrono::system_clock::now();
std::cout << "End time: " << endTime << std::endl;
boost::chrono::duration<double> d = endTime - startTime;
std::cout << "Duration: " << d << std::endl;
}
template<typename T> struct Deleter {
void operator()(T *p)
{
delete p;
}
};
void WithSmartPtrsUnique()
{
boost::chrono::system_clock::time_point startTime = boost::chrono::system_clock::now();
std::cout << "Start time: " << startTime << std::endl;
for (long i=0; i < lTestRecursion; ++i)
{
boost::unique_ptr<TestClass, Deleter<TestClass> > spTC = boost::unique_ptr<TestClass, Deleter<TestClass> >(new TestClass("Test input data!"));
}
boost::chrono::system_clock::time_point endTime = boost::chrono::system_clock::now();
std::cout << "End time: " << endTime << std::endl;
boost::chrono::duration<double> d = endTime - startTime;
std::cout << "Duration: " << d << std::endl;
}
void WithSmartPtrsNoMakeShared()
{
boost::chrono::system_clock::time_point startTime = boost::chrono::system_clock::now();
std::cout << "Start time: " << startTime << std::endl;
for (long i=0; i < lTestRecursion; ++i)
{
boost::shared_ptr<TestClass> spTC = boost::shared_ptr<TestClass>( new TestClass("Test input data!"));
}
boost::chrono::system_clock::time_point endTime = boost::chrono::system_clock::now();
std::cout << "End time: " << endTime << std::endl;
boost::chrono::duration<double> d = endTime - startTime;
std::cout << "Duration: " << d << std::endl;
}
void WithoutSmartPtrs()
{
boost::chrono::system_clock::time_point startTime = boost::chrono::system_clock::now();
std::cout << "Start time: " << startTime << std::endl;
for (long i=0; i < lTestRecursion; ++i)
{
TestClass* pTC = new TestClass("Test input data!");
delete pTC;
}
boost::chrono::system_clock::time_point endTime = boost::chrono::system_clock::now();
std::cout << "End time: " << endTime << std::endl;
boost::chrono::duration<double> d = endTime - startTime;
std::cout << "Duration: " << d << std::endl;
}
void WithObjectPool()
{
boost::chrono::system_clock::time_point startTime = boost::chrono::system_clock::now();
std::cout << "Start time: " << startTime << std::endl;
{
boost::object_pool<TestClass> pool;
for (long i=0; i < lTestRecursion; ++i)
{
TestClass* pTC = pool.construct("Test input data!");
pool.destroy(pTC);
}
}
boost::chrono::system_clock::time_point endTime = boost::chrono::system_clock::now();
std::cout << "End time: " << endTime << std::endl;
boost::chrono::duration<double> d = endTime - startTime;
std::cout << "Duration: " << d << std::endl;
}
void WithObjectPoolNoDestroy()
{
boost::chrono::system_clock::time_point startTime = boost::chrono::system_clock::now();
std::cout << "Start time: " << startTime << std::endl;
//{
boost::object_pool<TestClass> pool;
for (long i=0; i < lTestRecursion; ++i)
{
TestClass* pTC = pool.construct("Test input data!");
//pool.destroy(pTC);
}
//}
boost::chrono::system_clock::time_point endTime = boost::chrono::system_clock::now();
std::cout << "End time: " << endTime << std::endl;
boost::chrono::duration<double> d = endTime - startTime;
std::cout << "Duration: " << d << std::endl;
}
void WithSSVUtilsPreAllocDyn()
{
boost::chrono::system_clock::time_point startTime = boost::chrono::system_clock::now();
std::cout << "Start time: " << startTime << std::endl;
{
ssvu::PreAlloc::PreAllocDyn preAllocatorDyn(1024*1024);
for (long i=0; i < lTestRecursion; ++i)
{
TestClass* pTC = preAllocatorDyn.create<TestClass>("Test input data!");
preAllocatorDyn.destroy(pTC);
}
}
boost::chrono::system_clock::time_point endTime = boost::chrono::system_clock::now();
std::cout << "End time: " << endTime << std::endl;
boost::chrono::duration<double> d = endTime - startTime;
std::cout << "Duration: " << d << std::endl;
}
void WithSSVUtilsPreAllocStatic()
{
boost::chrono::system_clock::time_point startTime = boost::chrono::system_clock::now();
std::cout << "Start time: " << startTime << std::endl;
{
ssvu::PreAlloc::PreAllocStatic<TestClass> preAllocatorStat(10);
for (long i=0; i < lTestRecursion; ++i)
{
TestClass* pTC = preAllocatorStat.create<TestClass>("Test input data!");
preAllocatorStat.destroy(pTC);
}
}
boost::chrono::system_clock::time_point endTime = boost::chrono::system_clock::now();
std::cout << "End time: " << endTime << std::endl;
boost::chrono::duration<double> d = endTime - startTime;
std::cout << "Duration: " << d << std::endl;
}
int main()
{
std::cout << " With OUT smartptrs (new and delete): " << std::endl;
WithoutSmartPtrs();
std::cout << std::endl << " With smartptrs (boost::shared_ptr withOUT make_shared): " << std::endl;
WithSmartPtrsNoMakeShared();
std::cout << std::endl << " With smartptrs (boost::shared_ptr with make_shared): " << std::endl;
WithSmartPtrs();
std::cout << std::endl << " With STD smart_ptr (std::shared_ptr with make_shared): " << std::endl;
WithSTDSmartPtrs();
std::cout << std::endl << " With Object Pool (boost::object_pool<>): " << std::endl;
WithObjectPool();
std::cout << std::endl << " With Object Pool (boost::object_pool<>) but without destroy called!: " << std::endl;
WithObjectPoolNoDestroy();
std::cout << std::endl << " With SSVUtils PreAllocDyn(1024*1024)!: " << std::endl;
WithSSVUtilsPreAllocDyn();
std::cout << std::endl << " With SSVUtils PreAllocStatic(10)!: " << std::endl;
WithSSVUtilsPreAllocStatic();
return 0;
}
結果:
On Ubuntu LTS 12.04 x64 with GNU C++ 4.6 and boost 1.49
No smart ptrs (new/delete) 5,08024 100 5,1387 100 5,1108 100 5,1099 100
With boost::shared_ptr No boost::make_shared 7,36128 2,2810 145 7,34522 2,2065 143 7,28801 2,1772 143 7,3315 143
With boost::shared_ptr and boost::make_shared 6,60351 1,5233 130 6,82849 1,6898 133 6,61059 1,4998 129 6,6809 131
With std::shared_ptr and std::make_shared 6,07756 0,9973 120 5,93100 0,7923 115 5,9037 0,7929 116 5,9708 117
With boost::unique_ptr 4,97147 -0,1088 100 5,0428 -0,0959 98 4,96625 -0,1445 97 4,9935 98
With boost::object_pool 3,53291 -1,5473 70 3,60357 -1,5351 70 3,52986 -1,5809 69 3,5554 70
With boost::object_pool (Without calling Destroy) 4,52430 -0,5559 89 4,51602 -0,6227 88 4,52137 -0,5894 88 4,5206 88
私の MacBook Pro での SSVUtils PreAllocDyn を含む結果: 以下でコンパイル:
g++-mp-4.8 -I$BOOSTHOME/include -I$SSVUTILSHOME/include -std=c++11 -O2 -L$BOOSTHOME/lib -lboost_system -lboost_chrono -o smartptrtest smartptr.cpp
With OUT smartptrs (new and delete):
Start time: 1381596718412786000 nanoseconds since Jan 1, 1970
End time: 1381596731642044000 nanoseconds since Jan 1, 1970
Duration: 13.2293 seconds
With smartptrs (boost::shared_ptr withOUT make_shared):
Start time: 1381596731642108000 nanoseconds since Jan 1, 1970
End time: 1381596753651561000 nanoseconds since Jan 1, 1970
Duration: 22.0095 seconds
With smartptrs (boost::shared_ptr with make_shared):
Start time: 1381596753651611000 nanoseconds since Jan 1, 1970
End time: 1381596768909452000 nanoseconds since Jan 1, 1970
Duration: 15.2578 seconds
With STD smart_ptr (std::shared_ptr with make_shared):
Start time: 1381596768909496000 nanoseconds since Jan 1, 1970
End time: 1381596785500599000 nanoseconds since Jan 1, 1970
Duration: 16.5911 seconds
With Object Pool (boost::object_pool<>):
Start time: 1381596785500638000 nanoseconds since Jan 1, 1970
End time: 1381596793484515000 nanoseconds since Jan 1, 1970
Duration: 7.98388 seconds
With Object Pool (boost::object_pool<>) but without destroy called!:
Start time: 1381596793484551000 nanoseconds since Jan 1, 1970
End time: 1381596805774318000 nanoseconds since Jan 1, 1970
Duration: 12.2898 seconds
With SSVUtils PreAllocDyn(1024*1024)!:
Start time: 1381596815742696000 nanoseconds since Jan 1, 1970
End time: 1381596824173405000 nanoseconds since Jan 1, 1970
Duration: 8.43071 seconds
With SSVUtils PreAllocStatic(10)!:
Start time: 1381596824173448000 nanoseconds since Jan 1, 1970
End time: 1381596832034965000 nanoseconds since Jan 1, 1970
Duration: 7.86152 seconds
私の質問: shared_ptr/unique_ptr/boost::object_pool 以外に、オブジェクトの大規模なセットの迅速なヒープ割り当て/割り当て解除に使用できるヒープ/割り当てメカニズムはありますか?
注: 他のマシンやオペレーティング システムでもより多くの結果が得られています。
編集 1: SSVUtils PreAllocDyn の結果を追加しました 編集 4: コンパイラのコマンドライン オプションを追加し、SSVUtils PreAllocStatic(10) で再テストしました
ありがとう