[PATCH 2/2] fbdev: Improve performance of sys_imageblit()

[Gerd Hoffmann]

> -		for (j = k; j--; ) {
> -			shift -= ppw;
> -			end_mask = tab[(*src >> shift) & bit_mask];
> -			*dst++ = (end_mask & eorx) ^ bgx;
> -			if (!shift) {
> -				shift = 8;
> -				src++;
> +		for (j = k; j; j -= jdecr, ++src) {
> +			switch (ppw) {
> +			case 4: /* 8 bpp */
> +				*dst++ = colortab[(*src >> 4) & bit_mask];
> +				*dst++ = colortab[(*src >> 0) & bit_mask];
> +				break;
> +			case 2: /* 16 bpp */
> +				*dst++ = colortab[(*src >> 6) & bit_mask];
> +				*dst++ = colortab[(*src >> 4) & bit_mask];
> +				*dst++ = colortab[(*src >> 2) & bit_mask];
> +				*dst++ = colortab[(*src >> 0) & bit_mask];
> +				break;
> +			case 1: /* 32 bpp */
> +				*dst++ = colortab[(*src >> 7) & bit_mask];
> +				*dst++ = colortab[(*src >> 6) & bit_mask];
> +				*dst++ = colortab[(*src >> 5) & bit_mask];
> +				*dst++ = colortab[(*src >> 4) & bit_mask];
> +				*dst++ = colortab[(*src >> 3) & bit_mask];
> +				*dst++ = colortab[(*src >> 2) & bit_mask];
> +				*dst++ = colortab[(*src >> 1) & bit_mask];
> +				*dst++ = colortab[(*src >> 0) & bit_mask];
> +				break;
>  			}

How about moving the switch out of the loop, i.e.

switch (ppw) {
case 4:
    for (j = ...) {
        *dst++ = colortab[(*src >> 4) & bit_mask];
        *dst++ = colortab[(*src >> 0) & bit_mask];
    }
[ ... ]
}

?

take care,
  Gerd