使用SSE内在函数编译简单的c ++程序

smi*_*dha 5 c++ x86 sse simd

我是SSE指令的新手,我试图从这个网站上学习它们:http: //www.codeproject.com/Articles/4522/Introduction-to-SSE-Programming

我在Ubuntu 10.10上使用GCC编译器和Intel Core i7 960 CPU

这是基于我尝试的文章的代码:

对于两个长度为ARRAY_SIZE的数组,它会计算出来

fResult[i] = sqrt( fSource1[i]*fSource1[i] + fSource2[i]*fSource2[i] ) + 0.5

这是代码

#include <iostream>
#include <iomanip>
#include <ctime>
#include <stdlib.h>
#include <xmmintrin.h> // Contain the SSE compiler intrinsics
#include <malloc.h>
void myssefunction(
          float* pArray1,                   // [in] first source array
          float* pArray2,                   // [in] second source array
          float* pResult,                   // [out] result array
          int nSize)                        // [in] size of all arrays
{
    int nLoop = nSize/ 4;

    __m128 m1, m2, m3, m4;

    __m128* pSrc1 = (__m128*) pArray1;
    __m128* pSrc2 = (__m128*) pArray2;
    __m128* pDest = (__m128*) pResult;


    __m128 m0_5 = _mm_set_ps1(0.5f);        // m0_5[0, 1, 2, 3] = 0.5

    for ( int i = 0; i < nLoop; i++ )
    {
        m1 = _mm_mul_ps(*pSrc1, *pSrc1);        // m1 = *pSrc1 * *pSrc1
        m2 = _mm_mul_ps(*pSrc2, *pSrc2);        // m2 = *pSrc2 * *pSrc2
        m3 = _mm_add_ps(m1, m2);                // m3 = m1 + m2
        m4 = _mm_sqrt_ps(m3);                   // m4 = sqrt(m3)
        *pDest = _mm_add_ps(m4, m0_5);          // *pDest = m4 + 0.5

        pSrc1++;
        pSrc2++;
        pDest++;
    }
}

int main(int argc, char *argv[])
{
  int ARRAY_SIZE = atoi(argv[1]);
  float* m_fArray1 = (float*) _aligned_malloc(ARRAY_SIZE * sizeof(float), 16);
  float* m_fArray2 = (float*) _aligned_malloc(ARRAY_SIZE * sizeof(float), 16);
  float* m_fArray3 = (float*) _aligned_malloc(ARRAY_SIZE * sizeof(float), 16);

  for (int i = 0; i < ARRAY_SIZE; ++i)
    {
      m_fArray1[i] = ((float)rand())/RAND_MAX;
      m_fArray2[i] = ((float)rand())/RAND_MAX;
    }

  myssefunction(m_fArray1 , m_fArray2 , m_fArray3, ARRAY_SIZE);

  _aligned_free(m_fArray1);
   _aligned_free(m_fArray2);
   _aligned_free(m_fArray3);

  return 0;
}
Run Code Online (Sandbox Code Playgroud)

我得到以下compiltation错误

[Programming/SSE]$ g++ -g -Wall -msse sseintro.cpp 
sseintro.cpp: In function ‘int main(int, char**)’:
sseintro.cpp:41: error: ‘_aligned_malloc’ was not declared in this scope
sseintro.cpp:53: error: ‘_aligned_free’ was not declared in this scope
[Programming/SSE]$ 
Run Code Online (Sandbox Code Playgroud)

我搞砸了哪里?我错过了一些头文件吗?我似乎已经包括了所有相关的.

Pau*_*l R 15

_aligned_malloc_aligned_free是Microsoft- isms.在Linux 等人上使用posix_memalignmemalign.对于Mac OS X,您可以使用malloc,因为它始终是16字节对齐的.对于可移植的SSE代码,您通常希望为对齐的内存分配实现包装函数,例如

void * malloc_simd(const size_t size)
{
#if defined WIN32           // WIN32
    return _aligned_malloc(size, 16);
#elif defined __linux__     // Linux
    return memalign(16, size);
#elif defined __MACH__      // Mac OS X
    return malloc(size);
#else                       // other (use valloc for page-aligned memory)
    return valloc(size);
#endif
}
Run Code Online (Sandbox Code Playgroud)

实施free_simd是留给读者的练习.