ARM NEON加速引擎使用C语言实现RGB图像转灰度图 -

标题: ARM NEON加速引擎使用C语言实现RGB图像转灰度图 [打印本页]

作者: chendi 时间: 2017-3-13 22:45
标题: ARM NEON加速引擎使用C语言实现RGB图像转灰度图
//使用C语言实现RGB图像转灰度图
//Gray = (R * 77 + G * 151 + B * 28 ) / 256
void reference_convert (uint8_t * __restrict dest, uint8_t * __restrict src, int n)
{
  int i;
  for (i=0; i<n; i++)
  {
int r = *src++; // load red
int g = *src++; // load green
int b = *src++; // load blue

// build weighted average:
int y = (r*77)+(g*151)+(b*28);

// undo the scale by 256 and write to memory:
*dest++ = (y>>8);
  }
}

//使用NEON Intrinsics优化
void neon_convert (uint8_t * __restrict dest, uint8_t * __restrict src, int n)
{
  int i;
  //读取8字节的预设值到64位寄存器
  uint8x8_t rfac = vdup_n_u8 (77);// 转换权值 R
  uint8x8_t gfac = vdup_n_u8 (151);// 转换权值 G
  uint8x8_t bfac = vdup_n_u8 (28);// 转换权值 B
  n/=8;

  for (i=0; i<n; i++)
  {
uint16x8_t  temp;
uint8x8x3_t rgb  = vld3_u8 (src);//一次读取3个unit8x8到3个64位寄存器
uint8x8_t result;

temp = vmull_u8 (rgb.val[0],    rfac); // temp=rgb.val[0]*rfac
temp = vmlal_u8 (temp,rgb.val[1], gfac);// temp=temp+rgb.val[1]*gfac
temp = vmlal_u8 (temp,rgb.val[2], bfac);//temp=temp+rgb.val[2]*bfac

result = vshrn_n_u16 (temp, 8); // 128位寄存器每16位右移第二个参数位
vst1_u8 (dest, result); // 转存运算结果到dest
src  += 8*3;
dest += 8;
  }
}

//NEON汇编代码优化:
static void neon_asm_convert(uint8_t * __restrict dest, uint8_t * __restrict src, int numPixels)
{
  asm volatile("lsr       %2, %2, #3    \n"
            "# build the three constants: \n"
            "mov       r4, #28       \n" // Blue channel multiplier
            "mov       r5, #151       \n" // Green channel multiplier
            "mov       r6, #77       \n" // Red channel multiplier
            "vdup.8    d4, r4          \n"
            "vdup.8    d5, r5          \n"
            "vdup.8    d6, r6          \n"
            ".loop:                      \n"
            "# load 8 pixels:          \n"
            "vld4.8    {d0-d3}, [%1]! \n"
            "# do the weight average:    \n"
            "vmull.u8 q7, d0, d4    \n"
            "vmlal.u8 q7, d1, d5    \n"
            "vmlal.u8 q7, d2, d6    \n"
            "# shift and store:          \n"
            "vshrn.u16 d7, q7, #8    \n" // Divide q3 by 256 and store in the d7
            "vst1.8    {d7}, [%0]!    \n"
            "subs       %2, %2, #1    \n" // Decrement iteration count
            "bne       .loop          \n" // Repeat unil iteration count is not zero
            :
            : "r"(dest), "r"(src), "r"(numPixels)
            : "r4", "r5", "r6"
            );
}

作者: xql2008 时间: 2020-3-8 22:54
牛逼！牛逼！

欢迎光临 (http://www.51hei.com/bbs/)