close
http://hi.baidu.com/wadeswb/blog/item/12bd4c19868c030c34fa4129.html
需include xmmintrin.h 和 windows.h
// Timer Class
class CTimer
{
public:
__forceinline CTimer( void )
{
QueryPerformanceFrequency( &m_Frequency );
QueryPerformanceCounter( &m_StartCount );
}
__forceinline void Reset( void )
{
QueryPerformanceCounter( &m_StartCount );
}
__forceinline double End( void )
{
static __int64 nCurCount;
QueryPerformanceCounter( (PLARGE_INTEGER)&nCurCount );
return double( nCurCount * ( *(__int64*)&m_StartCount ) ) / double( *(__int64*)&m_Frequency );
}
private:
LARGE_INTEGER m_Frequency;
LARGE_INTEGER m_StartCount;
};
//向量運算
void ScaleValue1( float *pArray, DWORD dwCount, float fScale )
{
DWORD dwGroupCount = dwCount / 4;
__m128 e_Scale = _mm_set_ps1( fScale );
for ( DWORD i = 0; i < dwGroupCount; i++ )
{
*(__m128*)( pArray + i * 4 ) = _mm_mul_ps( *(__m128*)( pArray + i * 4 ), e_Scale );
}
}
//純量運算
void ScaleValue2( float *pArray, DWORD dwCount, float fScale )
{
for ( DWORD i = 0; i < dwCount; i++ )
{
pArray[i] *= fScale;
}
}
//主程式
#define ARRAYCOUNT 10000
int __cdecl main()
{
float __declspec(align(16)) Array[ARRAYCOUNT];
memset( Array, 0, sizeof(float) * ARRAYCOUNT );
CTimer t;
double dTime;
t.Reset();
for ( int i = 0; i < 100000; i++ ) //向量運算
{
ScaleValue1( Array, ARRAYCOUNT, 1000.0f );
}
dTime = t.End();
cout << "Use SSE:" << dTime << "秒" << endl;
t.Reset();
for ( int i = 0; i < 100000; i++ ) //純量運算
{
ScaleValue2( Array, ARRAYCOUNT, 1000.0f );
}
dTime = t.End();
cout << "Not Use SSE:" << dTime << "秒" << endl;
system( "pause" );
return 0;
}
Use SSE:0.997817
Not Use SSE:2.84963
全站熱搜
留言列表