Question

您好，
关于我之前的帖子，我解决了SSE中的比较操作但是在得到输出后我发现我的输出是浮点数而我的预期输出是在uchar中例如，我期望输出为8，输出以浮点格式显示为8.0（32位浮点格式）。转换后的值为1字节无符号，远远不同于8 ..
PFB我在C中的原始代码及其在SSE中的对应代码：

C代码：

unsigned char *destination_buff = (unsigned char *)malloc(sizeof(unsigned char)*height*width);
float *d1 = inputbuffer;
float *d2 = d1 + width;
float *d3 = d2 + width;

for(int i=1;i<height;i++)
{
    for(int j=1;j<width;j++)
    {
       int val = d2[j];
       int temp1 = 0x00FF;
       int temp2 = 0;   
       if(val <= d1[j-1]) temp2 += 0x80;
       if(val <= d1[j])   temp2 += 0x40;
       if(val <= d1[j+1]) temp2 += 0x20;    }
       if(val <= d2[j-1]) temp2 += 0x10;}
       if(val <= d2[j+1]) temp2 += 0x08;
       if(val <= d3[j-1]) temp2 += 0x04;
       if(val <= d3[j])   temp2 += 0x02;
       if(val <= d3[j+1]) temp2 ++;    
       temp1 &= (~temp2);
       destination_buff[j-1] = temp1;       
    }
        d1 += width;
        d2 += width;
        d3 += width;

        destination_buff += (width);
}

这是我的SSE代码：

float *destination_buff = (float *)malloc(sizeof(float)*height*width);

uchar *dst_d = outputbuffer; //Pointer to the destination buffer which is already present and need to fill the output data in this
float *CT_image_0 = m_dat;
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;

      __m128 t1 = _mm_set1_ps(0x80);
      __m128 t2 = _mm_set1_ps(0x40);
      __m128 t3 = _mm_set1_ps(0x20);
      __m128 t4 = _mm_set1_ps(0x10);
      __m128 t5 = _mm_set1_ps(0x08);
      __m128 t6 = _mm_set1_ps(0x04);
      __m128 t7 = _mm_set1_ps(0x02);
      __m128 t8 = _mm_set1_ps(0x01);

      __m128 out = _mm_setzero_ps();                 // init output flags to all zeroes


      __m128 sample = _mm_cmple_ps(val,CT_current_00);
             sample = _mm_and_ps(sample,t1);
               out  = _mm_or_ps(out,sample);
             sample = _mm_cmple_ps(val,CT_current_01);
             sample = _mm_and_ps(sample,t2);
               out  = _mm_or_ps(out,sample);
            sample = _mm_cmple_ps(val,CT_current_02);
            sample = _mm_and_ps(sample,t3);
              out  = _mm_or_ps(out,sample);

            sample = _mm_cmple_ps(val,CT_current_10);
            sample = _mm_and_ps(sample,t4);
              out  = _mm_or_ps(out,sample);
            sample = _mm_cmple_ps(val,CT_current_12);
            sample = _mm_and_ps(sample,t5);
              out  = _mm_or_ps(out,sample);

            sample = _mm_cmple_ps(val,CT_current_20);
            sample = _mm_and_ps(sample,t6);
              out  = _mm_or_ps(out,sample);
            sample = _mm_cmple_ps(val,CT_current_21);
            sample = _mm_and_ps(sample,t7);
              out  = _mm_or_ps(out,sample);
            sample = _mm_cmple_ps(val,CT_current_22);
            sample = _mm_and_ps(sample,t8);
              out  = _mm_or_ps(out,sample);

            _mm_storeu_ps((destination_buff+(j-1)),out);
            dst_d =  (uchar *)destination_buff;

        }

    CT_image_0  += width;
    CT_image_1  += width;
    CT_image_2  += width;

    dst_d += (width);

}

所有商店操作都在float和__m128i。如何将结果存储到uchar中？

Answer 1

您可以执行packed-compare来获取掩码，但是然后将该掩码与整数操作一起使用。 _mm_set1_ps(0x80)表示你正在做一些奇怪的事情。您可能不应该将两个功率位掩码转换为浮点数，因为使用_mm_add_ps添加它们比将它们与_mm_or_si128组合要慢得多。

对于某些偏移负载，您可能更适合palignr，以平衡加载端口和ALU端口之间的代码。

在SSE中浮点到uchar转换问题

1 个答案: