一级缓存丢失的成本是多少?

编辑 :为了便于参考(如果有人偶然发现这个问题),伊戈尔·奥斯特洛夫斯基写了一篇 great post 关于缓存未命中。它讨论了几个不同的问题,并显示了示例编号。 结束编辑

我做了一些测试 <long story goes here> 我想知道性能差异是否是由于内存缓存未命中造成的。下面的代码演示了这个问题,并将其归结为关键的计时部分。下面的代码有几个循环,它们以随机顺序访问内存,然后以升序访问地址。

我在一台XP机器(用vs2005:cl/o2编译)和一个Linux设备(gcc_两者产生的时间相似。这些时间以毫秒为单位。我相信所有的循环都在运行并且没有被优化(否则它会立即运行)。

*** Testing 20000 nodes
Total Ordered Time: 888.822899
Total Random Time: 2155.846268

这些数字有意义吗?差异主要是由于一级缓存未命中还是其他原因造成的?有20000^2个内存访问,如果每一个都是缓存未命中,那么每一次未命中大约有3.2纳秒。我测试的XP(P4)机器是3.2GHz,我怀疑(但不知道)有32kb的一级缓存和512kb的二级缓存。对于20000个条目(80kb),我假设没有大量的二级未命中。所以这是 (3.2*10^9 cycles/second) * 3.2*10^-9 seconds/miss) = 10.1 cycles/miss . 我觉得很高。也许不是,或者我的数学不好。我尝试用vtune测量缓存未命中,但我得到了一个bsod。现在我可以让它连接到许可证服务器(GRRRR)。

typedef struct stItem
{
   long     lData;
   //char     acPad[20];
} LIST_NODE;



#if defined( WIN32 )
void StartTimer( LONGLONG *pt1 )
{
   QueryPerformanceCounter( (LARGE_INTEGER*)pt1 );
}

void StopTimer( LONGLONG t1, double *pdMS )
{
   LONGLONG t2, llFreq;

   QueryPerformanceCounter( (LARGE_INTEGER*)&t2 );
   QueryPerformanceFrequency( (LARGE_INTEGER*)&llFreq );
   *pdMS = ((double)( t2 - t1 ) / (double)llFreq) * 1000.0;
}
#else
// doesn't need 64-bit integer in this case
void StartTimer( LONGLONG *pt1 )
{
   // Just use clock(), this test doesn't need higher resolution
   *pt1 = clock();
}

void StopTimer( LONGLONG t1, double *pdMS )
{
   LONGLONG t2 = clock();
   *pdMS = (double)( t2 - t1 ) / ( CLOCKS_PER_SEC / 1000 );
}
#endif



long longrand()
{
   #if defined( WIN32 )
   // Stupid cheesy way to make sure it is not just a 16-bit rand value
   return ( rand() << 16 ) | rand();
   #else
   return rand();
   #endif
}

// get random value in the given range
int randint( int m, int n )
{
   int ret = longrand() % ( n - m + 1 );
   return ret + m;
}

// I think I got this out of Programming Pearls (Bentley).
void ShuffleArray
(
   long *plShuffle,  // (O) return array of "randomly" ordered integers
   long lNumItems    // (I) length of array
)
{
   long i;
   long j;
   long t;

   for ( i = 0; i < lNumItems; i++ )
      plShuffle[i] = i;

   for ( i = 0; i < lNumItems; i++ )
      {
      j = randint( i, lNumItems - 1 );

      t = plShuffle[i];
      plShuffle[i] = plShuffle[j];
      plShuffle[j] = t;
      }
}



int main( int argc, char* argv[] )
{
   long          *plDataValues;
   LIST_NODE     *pstNodes;
   long          lNumItems = 20000;
   long          i, j;
   LONGLONG      t1;  // for timing
   double dms;

   if ( argc > 1 && atoi(argv[1]) > 0 )
      lNumItems = atoi( argv[1] );

   printf( "\n\n*** Testing %u nodes\n", lNumItems );

   srand( (unsigned int)time( 0 ));

   // allocate the nodes as one single chunk of memory
   pstNodes = (LIST_NODE*)malloc( lNumItems * sizeof( LIST_NODE ));
   assert( pstNodes != NULL );

   // Create an array that gives the access order for the nodes
   plDataValues = (long*)malloc( lNumItems * sizeof( long ));
   assert( plDataValues != NULL );

   // Access the data in order
   for ( i = 0; i < lNumItems; i++ )
      plDataValues[i] = i;

   StartTimer( &t1 );

   // Loop through and access the memory a bunch of times
   for ( j = 0; j < lNumItems; j++ )
      {
      for ( i = 0; i < lNumItems; i++ )
         {
         pstNodes[plDataValues[i]].lData = i * j;
         }
      }

   StopTimer( t1, &dms );
   printf( "Total Ordered Time: %f\n", dms );

   // now access the array positions in a "random" order
   ShuffleArray( plDataValues, lNumItems );

   StartTimer( &t1 );

   for ( j = 0; j < lNumItems; j++ )
      {
      for ( i = 0; i < lNumItems; i++ )
         {
         pstNodes[plDataValues[i]].lData = i * j;
         }
      }

   StopTimer( t1, &dms );
   printf( "Total Random Time: %f\n", dms );

}