[FFmpeg-devel] [PATCH 1/2] swscale: rgb_to_yuv neon optimizations

[Martin Storsjö]

On Fri, 30 May 2025, Dmitriy Kovalenko wrote:

> All the comments were addressed

If you fail to read the inline responses, we can end this conversation 
right here.

> And how did you test the prefetch, because I literally run a native 
> benchmarking on the device right now and I see that with the patch 
> applied I am getting 5% of performance improvement. Maybe there is an 
> issue in the way you measure the timers? I can for sure remove them 
> because I anyway use my own implementation that is 5-10x faster than the 
> ffmpeg's, but I am genuinely curious how is it possible that you see 
> different benchmarking results.

I tested with checkasm, with patch 1/2, on Linux on a Cortex A53, as-is 
and with the prefetch instructions removed.

// Martin