我使用了以下代码（从一个旧帖子借用），对blitz++、armadillo和boost::MultiArray进行了比较：
#include <iostream>
using namespace std;
#include <windows.h>
#define _SCL_SECURE_NO_WARNINGS
#define BOOST_DISABLE_ASSERTS
#include <boost/multi_array.hpp>
#include <blitz/array.h>
#include <armadillo>
int main(int argc, char* argv[])
{
const int X_SIZE = 1000;
const int Y_SIZE = 1000;
const int ITERATIONS = 100;
unsigned int startTime = 0;
unsigned int endTime = 0;
// Create the boost array
//------------------Measure boost Loop------------------------------------------
{
typedef boost::multi_array<double, 2> ImageArrayType;
ImageArrayType boostMatrix(boost::extents[X_SIZE][Y_SIZE]);
startTime = ::GetTickCount();
for (int i = 0; i < ITERATIONS; ++i)
{
for (int x = 0; x < X_SIZE; ++x)
{
for (int y = 0; y < Y_SIZE; ++y)
{
boostMatrix[x][y] = 1.0001;
}
}
}
endTime = ::GetTickCount();
printf("[Boost Loop] Elapsed time: %6.3f seconds\n", (endTime - startTime) / 1000.0);
}
//------------------Measure blitz Loop-------------------------------------------
{
blitz::Array<double, 2> blitzArray( X_SIZE, Y_SIZE );
startTime = ::GetTickCount();
for (int i = 0; i < ITERATIONS; ++i)
{
for (int x = 0; x < X_SIZE; ++x)
{
for (int y = 0; y < Y_SIZE; ++y)
{
blitzArray(x,y) = 1.0001;
}
}
}
endTime = ::GetTickCount();
printf("[Blitz Loop] Elapsed time: %6.3f seconds\n", (endTime - startTime) / 1000.0);
}
//------------------Measure armadillo loop----------------------------------------
{
arma::mat matArray( X_SIZE, Y_SIZE );
startTime = ::GetTickCount();
for (int i = 0; i < ITERATIONS; ++i)
{
for (int y = 0; y < Y_SIZE; ++y)
{
for (int x = 0; x < X_SIZE; ++x)
{
matArray(x,y) = 1.0001;
}
}
}
endTime = ::GetTickCount();
printf("[arma Loop] Elapsed time: %6.3f seconds\n", (endTime - startTime) / 1000.0);
}
//------------------Measure native loop----------------------------------------
// Create the native array
{
double *nativeMatrix = new double [X_SIZE * Y_SIZE];
startTime = ::GetTickCount();
for (int i = 0; i < ITERATIONS; ++i)
{
for (int y = 0; y < Y_SIZE*X_SIZE; ++y)
{
nativeMatrix[y] = 1.0001;
}
}
endTime = ::GetTickCount();
printf("[Native Loop]Elapsed time: %6.3f seconds\n", (endTime - startTime) / 1000.0);
delete[] nativeMatrix;
}
//------------------Measure boost computation-----------------------------------
{
typedef boost::multi_array<double, 2> ImageArrayType;
ImageArrayType boostMatrix(boost::extents[X_SIZE][Y_SIZE]);
for (int x = 0; x < X_SIZE; ++x)
{
for (int y = 0; y < Y_SIZE; ++y)
{
boostMatrix[x][y] = 1.0001;
}
}
startTime = ::GetTickCount();
for (int i = 0; i < ITERATIONS; ++i)
{
for (int x = 0; x < X_SIZE; ++x)
{
for (int y = 0; y < Y_SIZE; ++y)
{
boostMatrix[x][y] += boostMatrix[x][y] * 0.5;
}
}
}
endTime = ::GetTickCount();
printf("[Boost computation] Elapsed time: %6.3f seconds\n", (endTime - startTime) / 1000.0);
}
//------------------Measure blitz computation-----------------------------------
{
blitz::Array<double, 2> blitzArray( X_SIZE, Y_SIZE );
blitzArray = 1.0001;
startTime = ::GetTickCount();
for (int i = 0; i < ITERATIONS; ++i)
{
blitzArray += blitzArray*0.5;
}
endTime = ::GetTickCount();
printf("[Blitz computation] Elapsed time: %6.3f seconds\n", (endTime - startTime) / 1000.0);
}
//------------------Measure armadillo computation-------------------------------
{
arma::mat matArray( X_SIZE, Y_SIZE );
matArray.fill(1.0001);
startTime = ::GetTickCount();
for (int i = 0; i < ITERATIONS; ++i)
{
//matArray.fill(1.0001);
matArray += matArray*0.5;
}
endTime = ::GetTickCount();
printf("[arma computation] Elapsed time: %6.3f seconds\n", (endTime - startTime) / 1000.0);
}
//------------------Measure native computation------------------------------------------
// Create the native array
{
double *nativeMatrix = new double [X_SIZE * Y_SIZE];
for (int y = 0; y < Y_SIZE*X_SIZE; ++y)
{
nativeMatrix[y] = 1.0001;
}
startTime = ::GetTickCount();
for (int i = 0; i < ITERATIONS; ++i)
{
for (int y = 0; y < Y_SIZE*X_SIZE; ++y)
{
nativeMatrix[y] += nativeMatrix[y] * 0.5;
}
}
endTime = ::GetTickCount();
printf("[Native computation]Elapsed time: %6.3f seconds\n", (endTime - startTime) / 1000.0);
delete[] nativeMatrix;
}
return 0;
}
在Windows上，使用VS2010，结果如下：
[Boost Loop] Elapsed time: 1.217 seconds
[Blitz Loop] Elapsed time: 0.046 seconds
[arma Loop] Elapsed time: 0.078 seconds
[Native Loop]Elapsed time: 0.172 seconds
[Boost computation] Elapsed time: 2.152 seconds
[Blitz computation] Elapsed time: 0.156 seconds
[arma computation] Elapsed time: 0.078 seconds
[Native computation]Elapsed time: 0.078 seconds
在Windows上使用Intel C++的结果如下：
[Boost Loop] Elapsed time: 0.468 seconds
[Blitz Loop] Elapsed time: 0.125 seconds
[arma Loop] Elapsed time: 0.046 seconds
[Native Loop]Elapsed time: 0.047 seconds
[Boost computation] Elapsed time: 0.796 seconds
[Blitz computation] Elapsed time: 0.109 seconds
[arma computation] Elapsed time: 0.078 seconds
[Native computation]Elapsed time: 0.062 seconds
有些奇怪：
(1) with VS2010, native computation (including loop) is faster than native loop
(2) blitz loop behave so different under VS2010 and intel C++.
要使用Intel C++编译器编译Blitz++，需要在blitz/intel/文件夹中提供一个名为bzconfig.h的文件。但是这个文件不存在。我只是把blitz / ms / bzconfig.h中的文件复制进去了，但这可能会导致非最优配置。请问有谁知道如何使用Intel C++编译器编译Blitz ++吗？手册中说要运行bzconfig脚本以获取正确的bzconfig.h文件，但我不明白它的意思。
非常感谢！
我的结论：
1. Boost multi array is the slowest.
2. With intel c++ compiler, native pointers are very fast.
3. With intel c++ compiler, armadillo can achieve the performance of native pointers.
4. Also test eigen, it is x0% slower than armadillo in my simple cases.
5. Curious about blitz++'s behavior in intel c++ compiler with proper configuration.
Please see my question.