Question

我在同一台计算机上使用Visual C ++和MINGW-64编译的相同代码之间的速度差异大约是15到45倍。

MSVC可以加速吗？

最近我一直在寻找一个C ++随机数生成器，它可以生成介于0和1之间的双重类型。我使用了stdlib的erand48（）函数，因为我不需要高质量的PRN，但它是不适用于MSVC。我在MSVC 14（2015）社区中编译了代码（下面），并通过MSYS编译了MINGW-64。 MINGW编译的结果比MSVC编译快15到45倍。

两者都在同一台计算机上运行。

g ++结果（所有时间以毫秒为单位），使用命令行

编译

g++ -o RandSpeedTest -std=c++11 -O3 RandSpeedTest.cpp

可生产

| ranlux64_base_01                | 169 | ms |
| linear_congruential             | 184 | ms |
| minstd_rand0                    |  78 | ms |
| minstd_rand                     |  68 | ms |
| mt19937 (default_random_engine) |  53 | ms |

MSVC 2015社区结果用x64目标编译。使用/ O2启用优化。我尝试使用vary / arch：SSE，/ arch：SSE2，/ arch：AVX和/ arch：AVX2。它们都是微不足道的。

| ranlux64_base_01                |  7794 | ms |
| linear_congruential             |  7746 | ms |
| minstd_rand0                    |  1181 | ms |
| minstd_rand                     |  1221 | ms |
| mt19937 (default_random_engine) |  1045 | ms |
| knuth_b                         |  1575 | ms |
| mt19937_64                      |  1009 | ms |
| ranlux24                        |  5639 | ms |
| ranlux48                        | 10687 | ms |

我还没有找到一种模板引擎的聪明方法，因此代码有大量的重复。遗憾。

#ifdef __GNUC__
#include <tr1/random>
//#include <cstdlib>

#elif _MSC_VER
#include <random>
#endif //__GNUC__

#include <iostream>
#include <chrono>
#include <vector>

using namespace std;
using std::chrono::high_resolution_clock;
using std::chrono::duration_cast;

void dump_time(
  std::chrono::time_point<std::chrono::high_resolution_clock> t1,
  std::chrono::time_point<std::chrono::high_resolution_clock> t2)
{
  cout << std::chrono::duration_cast<std::chrono::milliseconds>(t2-t1).count() << " | ms |\n";
}

int main()
{
  const unsigned long numToGen = 10000000;
  std::tr1::uniform_real<double>  dist(0,1.); 
  volatile double f;
  std::chrono::time_point<std::chrono::high_resolution_clock> t1, t2;

  cout << "| ranlux64_base_01 | ";
  dist.reset(); // discard any cached values
  std::tr1::ranlux64_base_01 eng0;
  eng0.seed( (unsigned int) 357);
  t1 = high_resolution_clock::now();
  for (int i = 0; i < numToGen; i++, f=dist(eng0));
  t2 = high_resolution_clock::now();
  dump_time(t1, t2);
  /*
  // verify that it produces output
  for(int i =0; i < 10; i++)
    {
    cout << dist(eng0) << endl;
    }
  */

  cout << "| linear_congruential | ";
  std::tr1::ranlux64_base_01 eng1;
  eng1.seed( (unsigned int) 357);
  t1 = high_resolution_clock::now();
  for (int i = 0; i < numToGen; i++, f=dist(eng1));
  t2 = high_resolution_clock::now();
  dump_time(t1, t2);

  cout << "| minstd_rand0 | ";
  std::tr1::minstd_rand0 eng2;
  eng2.seed( (unsigned int) 357);
  t1 = high_resolution_clock::now();
  for (int i = 0; i < numToGen; i++, f=dist(eng2));
  t2 = high_resolution_clock::now();
  dump_time(t1, t2);

  cout << "| minstd_rand |";
  std::tr1::minstd_rand eng4;
  eng4.seed( (unsigned int) 357);
  t1 = high_resolution_clock::now();
  for (int i = 0; i < numToGen; i++, f=dist(eng4));
  t2 = high_resolution_clock::now();
  dump_time(t1, t2);

  cout << "| mt19937 (default_random_engine) | ";
  std::tr1::mt19937 eng5;
  eng5.seed( (unsigned int) 357);
  t1 = high_resolution_clock::now();
  for (int i = 0; i < numToGen; i++, f=dist(eng5));
  t2 = high_resolution_clock::now();
  dump_time(t1, t2);

#ifdef _MSC_VER
  cout << "| knuth_b | ";
  std::tr1::knuth_b eng3;
  eng3.seed( (unsigned int) 357);
  t1 = high_resolution_clock::now();
  for (int i = 0; i < numToGen; i++, f=dist(eng3));
  t2 = high_resolution_clock::now();
  dump_time(t1, t2);

  cout << "| mt19937_64 | ";
  std::tr1::mt19937_64 eng6;
  eng6.seed( (unsigned int) 357);
  t1 = high_resolution_clock::now();
  for (int i = 0; i < numToGen; i++, f=dist(eng6));
  t2 = high_resolution_clock::now();
  dump_time(t1, t2);

  cout << "| ranlux24 | ";
  std::tr1::ranlux24 eng7;
  eng7.seed( (unsigned int) 357);
  t1 = high_resolution_clock::now();
  for (int i = 0; i < numToGen; i++, f=dist(eng7));
  t2 = high_resolution_clock::now();
  dump_time(t1, t2);

  cout << "| ranlux48 |";
  std::tr1::ranlux48 eng8;
  eng8.seed( (unsigned int) 357);
  t1 = high_resolution_clock::now();
  for (int i = 0; i < numToGen; i++, f=dist(eng8));
  t2 = high_resolution_clock::now();
  dump_time(t1, t2);

#endif  // _MSC_VER

/*
// Not available in MINGW-64, not available in MSVC
  cout << "erand48" << endl;
  unsigned short int seed16v[3];
  t1 = high_resolution_clock::now();
  for (int i = 0; i < numToGen; i++, f=erand48(seed16v));
  t2 = high_resolution_clock::now();
  dump_time(t1, t2);
*/

  return (0);
}

Answer 1

根据@NeilButterworth评论，手动删除正在替换的呼叫，例如

dist(eng6())

与

eng6()

产生与g ++类似的速度结果。如下图所示。

| ranlux64_base_01                 |  162 | ms |
| linear_congruential              |  127 | ms |
| minstd_rand0                     |   71 | ms |
| minstd_rand                      |   71 | ms |
| mt19937 (default_random_engine)  |   69 | ms |
| knuth_b                          |  115 | ms |
| mt19937_64 (__int64 not divided) |  151 | ms |
| ranlux24                         | 1211 | ms |
| ranlux48 (__int64 not divided)   | 4046 | ms |

两个引擎生成__int64值，这些值不会转换为0到1之间的浮点数。但是，其他引擎与GNU编译器一致，删除了对dist的调用。

C ++随机生成器在g ++中比MSVC快10倍？

1 个答案: