Ok, maybe sws_scale running on 24 CPU cores is faster than this https://github.com/lemenkov/libyuv on one core. Seriously, what do you mean by "initialize the context manually". How to force it to use SSSE3 instruction and so on?
ср, 14 сент. 2022 г. в 13:25, wolverin via Libav-user <[email protected] >: > > > I recommend not to use sws_sclale at all. It is a real bottleneck of all > encoding process. > > > > If you use the multithreaded version of AVFilter or initialize the context > manually to use multithreading, then everything works fast enough. > > _______________________________________________ > Libav-user mailing list > [email protected] > https://ffmpeg.org/mailman/listinfo/libav-user > > To unsubscribe, visit link above, or email > [email protected] with subject "unsubscribe". > -- С уважением Алексей Комаров.
_______________________________________________ Libav-user mailing list [email protected] https://ffmpeg.org/mailman/listinfo/libav-user To unsubscribe, visit link above, or email [email protected] with subject "unsubscribe".
