[FFmpeg-devel] [PATCH] dsputil: add bswap16_buf()

[Reimar Döffinger]

On Fri, Mar 11, 2011 at 12:12:29AM +0000, Mans Rullgard wrote:
> There several places where a buffer is byte-swapped in 16-bit units.
> This allows them to share code which can be optimised for various
> architectures.
> 
> Signed-off-by: Mans Rullgard <mans at mansr.com>
> ---
>  libavcodec/dsputil.c |    7 +++++++
>  libavcodec/dsputil.h |    1 +
>  2 files changed, 8 insertions(+), 0 deletions(-)
> 
> diff --git a/libavcodec/dsputil.c b/libavcodec/dsputil.c
> index 1f7bd4c..b293642 100644
> --- a/libavcodec/dsputil.c
> +++ b/libavcodec/dsputil.c
> @@ -222,6 +222,12 @@ static void bswap_buf(uint32_t *dst, const uint32_t *src, int w){
>      }
>  }
>  
> +static void bswap16_buf(uint16_t *dst, const uint16_t *src, int len)
> +{
> +    while (len--)
> +        *dst++ = av_bswap16(*src++);
> +}

Shouldn't this be unrolled like bswap_buf, for consistency at least if nothing else?