I was looking at this question because I had the same question. I had some thoughts to give a more rigorous test.
- As rodrigob pointed out, there are flaws in the loop order such that any results in the code that you originally attached will give misleading data
- Also, there are rather small sized arrays that are being set using constants. The compiler may be optimize out the loops, when in reality the compiler will not know the size of the arrays. The sizes of the arrays and number of iterations should be runtime inputs just in case.
On a Mac, the following code is configured to give more meaningful answers. There are 4 tests here.
#define BOOST_DISABLE_ASSERTS
#include "boost/multi_array.hpp"
#include <sys/time.h>
#include <stdint.h>
#include<string>
uint64_t GetTimeMs64()
{
struct timeval tv;
gettimeofday( &tv, NULL );
uint64_t ret = tv.tv_usec;
/* Convert from micro seconds (10^-6) to milliseconds (10^-3) */
ret /= 1000;
/* Adds the seconds (10^0) after converting them to milliseconds (10^-3) */
ret += ( tv.tv_sec * 1000 );
return ret;
}
void function1( const int X_SIZE, const int Y_SIZE, const int ITERATIONS )
{
double nativeMatrix1add[X_SIZE*Y_SIZE];
for( int x = 0 ; x < X_SIZE ; ++x )
{
for( int y = 0 ; y < Y_SIZE ; ++y )
{
nativeMatrix1add[y + ( x * Y_SIZE )] = rand();
}
}
// Create the native array
double* __restrict const nativeMatrix1p = new double[X_SIZE * Y_SIZE];
uint64_t startTime = GetTimeMs64();
for( int i = 0 ; i < ITERATIONS ; ++i )
{
for( int xy = 0 ; xy < X_SIZE*Y_SIZE ; ++xy )
{
nativeMatrix1p[xy] += nativeMatrix1add[xy];
}
}
uint64_t endTime = GetTimeMs64();
printf( "[Native Pointer] Elapsed time: %6.3f seconds\n", ( endTime - startTime ) / 1000.0 );
}
void function2( const int X_SIZE, const int Y_SIZE, const int ITERATIONS )
{
double nativeMatrix1add[X_SIZE*Y_SIZE];
for( int x = 0 ; x < X_SIZE ; ++x )
{
for( int y = 0 ; y < Y_SIZE ; ++y )
{
nativeMatrix1add[y + ( x * Y_SIZE )] = rand();
}
}
// Create the native array
double* __restrict const nativeMatrix1 = new double[X_SIZE * Y_SIZE];
uint64_t startTime = GetTimeMs64();
for( int i = 0 ; i < ITERATIONS ; ++i )
{
for( int x = 0 ; x < X_SIZE ; ++x )
{
for( int y = 0 ; y < Y_SIZE ; ++y )
{
nativeMatrix1[y + ( x * Y_SIZE )] += nativeMatrix1add[y + ( x * Y_SIZE )];
}
}
}
uint64_t endTime = GetTimeMs64();
printf( "[Native 1D Array] Elapsed time: %6.3f seconds\n", ( endTime - startTime ) / 1000.0 );
}
void function3( const int X_SIZE, const int Y_SIZE, const int ITERATIONS )
{
double nativeMatrix2add[X_SIZE][Y_SIZE];
for( int x = 0 ; x < X_SIZE ; ++x )
{
for( int y = 0 ; y < Y_SIZE ; ++y )
{
nativeMatrix2add[x][y] = rand();
}
}
// Create the native array
double nativeMatrix2[X_SIZE][Y_SIZE];
uint64_t startTime = GetTimeMs64();
for( int i = 0 ; i < ITERATIONS ; ++i )
{
for( int x = 0 ; x < X_SIZE ; ++x )
{
for( int y = 0 ; y < Y_SIZE ; ++y )
{
nativeMatrix2[x][y] += nativeMatrix2add[x][y];
}
}
}
uint64_t endTime = GetTimeMs64();
printf( "[Native 2D Array] Elapsed time: %6.3f seconds\n", ( endTime - startTime ) / 1000.0 );
}
void function4( const int X_SIZE, const int Y_SIZE, const int ITERATIONS )
{
boost::multi_array<double, 2> boostMatrix2add( boost::extents[X_SIZE][Y_SIZE] );
for( int x = 0 ; x < X_SIZE ; ++x )
{
for( int y = 0 ; y < Y_SIZE ; ++y )
{
boostMatrix2add[x][y] = rand();
}
}
// Create the native array
boost::multi_array<double, 2> boostMatrix( boost::extents[X_SIZE][Y_SIZE] );
uint64_t startTime = GetTimeMs64();
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] += boostMatrix2add[x][y];
}
}
}
uint64_t endTime = GetTimeMs64();
printf( "[Boost Array] Elapsed time: %6.3f seconds\n", ( endTime - startTime ) / 1000.0 );
}
int main( int argc, char* argv[] )
{
srand( time( NULL ) );
const int X_SIZE = std::stoi( argv[1] );
const int Y_SIZE = std::stoi( argv[2] );
const int ITERATIONS = std::stoi( argv[3] );
function1( X_SIZE, Y_SIZE, ITERATIONS );
function2( X_SIZE, Y_SIZE, ITERATIONS );
function3( X_SIZE, Y_SIZE, ITERATIONS );
function4( X_SIZE, Y_SIZE, ITERATIONS );
return 0;
}
One with just a single dimensional array using the [] with integer math and a double loop
One with the same single dimensional array using pointer incrementing
A multidimensional C array
A boost multi_array
so run from a command line, run
./test_array xsize ysize iterations"
and you can get a good idea of how these approaches will perform. Here is what I got with the following compiler flags:
g++4.9.2 -O3 -march=native -funroll-loops -mno-avx --fast-math -DNDEBUG -c -std=c++11
./test_array 51200 1 20000
[Native 1-Loop ] Elapsed time: 0.537 seconds
[Native 1D Array] Elapsed time: 2.045 seconds
[Native 2D Array] Elapsed time: 2.749 seconds
[Boost Array] Elapsed time: 1.167 seconds
./test_array 25600 2 20000
[Native 1-Loop ] Elapsed time: 0.531 seconds
[Native 1D Array] Elapsed time: 1.241 seconds
[Native 2D Array] Elapsed time: 1.631 seconds
[Boost Array] Elapsed time: 0.954 seconds
./test_array 12800 4 20000
[Native 1-Loop ] Elapsed time: 0.536 seconds
[Native 1D Array] Elapsed time: 1.214 seconds
[Native 2D Array] Elapsed time: 1.223 seconds
[Boost Array] Elapsed time: 0.798 seconds
./test_array 6400 8 20000
[Native 1-Loop ] Elapsed time: 0.540 seconds
[Native 1D Array] Elapsed time: 0.845 seconds
[Native 2D Array] Elapsed time: 0.878 seconds
[Boost Array] Elapsed time: 0.803 seconds
./test_array 3200 16 20000
[Native 1-Loop ] Elapsed time: 0.537 seconds
[Native 1D Array] Elapsed time: 0.661 seconds
[Native 2D Array] Elapsed time: 0.673 seconds
[Boost Array] Elapsed time: 0.708 seconds
./test_array 1600 32 20000
[Native 1-Loop ] Elapsed time: 0.532 seconds
[Native 1D Array] Elapsed time: 0.592 seconds
[Native 2D Array] Elapsed time: 0.596 seconds
[Boost Array] Elapsed time: 0.764 seconds
./test_array 800 64 20000
[Native 1-Loop ] Elapsed time: 0.546 seconds
[Native 1D Array] Elapsed time: 0.594 seconds
[Native 2D Array] Elapsed time: 0.606 seconds
[Boost Array] Elapsed time: 0.764 seconds
./test_array 400 128 20000
[Native 1-Loop ] Elapsed time: 0.536 seconds
[Native 1D Array] Elapsed time: 0.560 seconds
[Native 2D Array] Elapsed time: 0.564 seconds
[Boost Array] Elapsed time: 0.746 seconds
So, I think that it is safe to say that the boost multi_array performs pretty good. Nothing beats a single loop evaluation, but depending on the dimension of the array, the boost::multi_array may beat a standard c-array with a double loop.
