[FFmpeg-devel] Extend/optimize RGB to RGB conversions funcs intorgb2rgb.c

[Don Moir]

> void rgb24to32(const uint8_t *src, uint8_t *dst, int src_size )
> {
>    int i;
>    uint8_t *psrc = src;
>
>    for ( i = 0 ; i < src_size ; i += 3, psrc +=3, dst +=4 )
>    {
> #if HAVE_BIGENDIAN
>        /* RGB24 (= R,G,B) -> BGR32 (= 255,R,G,B) */
>        dst[0] = 255;
>        dst[1] = psrc[0];
>        dst[2] = psrc[1];
>        dst[3] = psrc[2];
> #else
>        dst[0] = psrc[2];
>        dst[1] = psrc[1];
>        dst[2] = psrc[0];
>        dst[3] = 255;
> #endif
>    }
> }

You might try something like this that does 4 pixels within the loop. It 
might be interesting to see if performance is better for this. I do it asm 
and don't do it line by line for my own purposes.

Note: somewhat pseudo code. I do it differently so modified here.

 void rgb24to32(const uint8_t *src, uint8_t *dst, int src_size )
{
    int nPixels = src_size / 3;
    int pixels4 = nPixels >> 2;
    int extra = nPixels % 4;
    uint32_t* pDst (uint32_t*)dst;
    uint32_t* pSrc (uint32_t*)src;

    for (int i = 0; i < pixels4; ++i)
    {
#if HAVE_BIGENDIAN
        pDst[0] = 0xFF000000 | (pSrc[0] >> 8);
        pDst[1] = 0xFF000000 | (pSrc[0] << 16) | (pSrc[1] >> 16);
        pDst[2] = 0xFF000000 | (pSrc[1] << 8) | (pSrc[2] >> 24);
        pDst[3] = 0xFF000000 | pSrc[2];
#else
        pDst[0] = 0xFF000000 | pSrc[0];
        pDst[1] = 0xFF000000 | (pSrc[1] << 8) | (pSrc[0] >> 24);
        pDst[2] = 0xFF000000 | ((pSrc[2] << 16) | (pSrc[1] >> 16);
        pDst[3] = 0xFF000000 | (pSrc[2] >> 8);
#endif
        pDst +=4;
        pSrc +=3;
    }

    uint8_t* pBytes = (uint8_t*)pDst;
    for (int i = 0; i < extra; i++)
    {
#if HAVE_BIGENDIAN
        *pDst++ = 0xFF000000 | (pBytes[0] << 16) | (pBytes[1] << 8) | 
(pBytes[2]);
#else
        *pDst++ = 0xFF000000 | (pBytes[2] << 16) | (pBytes[1] << 8) | 
(pBytes[0]);
#endif
        pBytes += 3;
    }
}