[FFmpeg-devel] [PATCH] PPC64: Add versions of functions in libswscale/input.c optimized for POWER8 VSX SIMD.

[Ronald S. Bultje]

Hi,

On Wed, Jul 6, 2016 at 10:14 AM, Ronald S. Bultje <rsbultje at gmail.com>
wrote:

> +            v_rslt += vec_sl(vec_splats((int)32), v_opr1);
>> +            v_rslt += vec_sl(vec_splats((int)1), v_opr2);
>>
>
> vec_splats outside loop.
>

While we're at it, is the += SIMD'ed? And why aren't v_opr1/2 merged in a
single variable to save an add?

Ronald