Question

我是SSE编码的新手。我想为我的算法编写一个SSE代码。我想将以下C代码转换为SSE代码。

for(int i=1;i<height;i++)
{
    for(int j=1;j<width;j++)
    {
        int index = 0;
        if(input[width*i + j]<=input[width*(i-1)+(j-1)])) index += 0x80;
        if(input[width*i + j]<=input[width*(i-1)+(j  )])) index += 0x40;
        if(input[width*i + j]<=input[width*(i-1)+(j+1)])) index += 0x20;
        if(input[width*i + j]<=input[width*(i  )+(j-1)])) index += 0x10;
        if(input[width*i + j]<=input[width*(i  )+(j+1)])) index += 0x08;
        if(input[width*i + j]<=input[width*(i+1)+(j-1)])) index += 0x04;
        if(input[width*i + j]<=input[width*(i+1)+(j  )])) index += 0x02;
        if(input[width*i + j]<=input[width*(i+1)+(j+1)])) index ++;
        output[width*(i-1)+(j-1)] = index;

    }
}

这是我的SSE代码：

unsigned char *dst_d = outputbuffer
float *CT_image_0 = inputbuffer;
float *CT_image_1 = CT_image_0 + width;
float *CT_image_2 = CT_image_1 + width; 
for(int i=1;i<height;i++)
{
    for(int j=1;j<width;j+=4)
    {

      __m128 CT_current_00 = _mm_loadu_ps((CT_image_0+j-1));
      __m128 CT_current_10 = _mm_loadu_ps((CT_image_1+j-1));
      __m128 CT_current_20 = _mm_loadu_ps((CT_image_2+j-1));

      __m128 CT_current_01 = _mm_loadu_ps(((CT_image_0+1)+j-1));
      __m128 CT_current_11 = _mm_loadu_ps(((CT_image_1+1)+j-1));
      __m128 CT_current_21 = _mm_loadu_ps(((CT_image_2+1)+j-1));

      __m128 CT_current_02 = _mm_loadu_ps(((CT_image_0+2)+j-1));
      __m128 CT_current_12 = _mm_loadu_ps(((CT_image_1+2)+j-1));
      __m128 CT_current_22 = _mm_loadu_ps(((CT_image_2+2)+j-1));

      __m128 val    =  CT_current_11;

      //Below I tried to write the SSE instruction but that was wrong :( 
      //--How I can do index + ...operation with this _mm_cmple_ss return value ????
      __m128 sample6= _mm_cmple_ss(val,CT_current_00);
       sample6 += _mm_cmple_ss(val,CT_current_01);
       sample6 += _mm_cmple_ss(val,CT_current_02);
       sample6 += _mm_cmple_ss(val,CT_current_10);
       sample6 +=_mm_cmple_ss(val,CT_current_12);
       sample6 +=_mm_cmple_ss(val,CT_current_20);
       sample6 +=_mm_cmple_ss(val,CT_current_21);
       sample6 +=_mm_cmple_ss(val,CT_current_22);
    }
    CT_image_0 +=width;
    CT_image_1 +=width;
    CT_image_2 +=width;
    dst_d += (width-2);
}

我摔断了头，试图（作为一个外行人）使用条件......请给我一些想法???

Answer 1

需要工作的部分显然是这样的：

  __m128 sample6= _mm_cmple_ss(val,CT_current_00);
   sample6 += _mm_cmple_ss(val,CT_current_01);
   sample6 += _mm_cmple_ss(val,CT_current_02);
   sample6 += _mm_cmple_ss(val,CT_current_10);
   sample6 +=_mm_cmple_ss(val,CT_current_12);
   sample6 +=_mm_cmple_ss(val,CT_current_20);
   sample6 +=_mm_cmple_ss(val,CT_current_21);
   sample6 +=_mm_cmple_ss(val,CT_current_22);

您需要将所有比较结果合并到一组标记中，例如像这样：

   __m128i out = _mm_setzero_si128();                // init output flags to all zeroes
   __m128i test;

   test = _mm_cmple_ss(val, CT_current_00);          // compare
   test = _mm_and_si128(test, _mm_set1_epi32(0x80)); // mask all but required flag
   out = _mm_or_si128(out, test);                    // merge flags to output mask
   test = _mm_cmple_ss(val, CT_current_01);
   test = _mm_and_si128(test, _mm_set1_epi32(0x40));
   out = _mm_or_si128(out, test);
   // ... repeat for each offset and flag value
   // ... then finally extract 4 bytes from `out`
   // ... and store at output[width*(i-1)+(j-1)]

Answer 2

我不知道SSE是什么代码，但很可能你想要运行一个/或者将CT_current变量组合成一个字符串数组的组合，然后将它们连接到一个List中，前面提到（通过你的代码），CT = **规范（其中CT **是你之后提出的所有内容）;为了迭代回到你打印到的_m128，然后如你所知，你可以在你完成时进行双重迭代。

祝你好运。

上证所比较操作

2 个答案: