Ronald S. Bultje: > 发件人: Ronald S. Bultje <rsbul...@gmail.com> > 发送时间: 2024年5月29日 10:51 > 收件人: FFmpeg development discussions and patches > 抄送: James Almer; Wu Jianhua > 主题: Re: [FFmpeg-devel] [PATCH 1/3] avcodec/x86/vvc/vvc_alf: fix integer > overflow > > Hi, > > On Wed, May 29, 2024 at 11:38 AM > <toq...@outlook.com<mailto:toq...@outlook.com>> wrote: > +%else > + vpunpcklqdq m11, m2, m2 > + vpunpckhqdq m12, m2, m2 > + vpunpcklwd m11, m11, m14 > + vpunpcklwd m12, m12, m14 > + paddd m0, m11 > + paddd m1, m12 > + packssdw m0, m0, m1 > +%endif > > punpcklqdq a, src, src > punpckhqdq b, src, src > punpcklwd a, a, zero > punpcklwd b, b, zero > > is the same as > > punpcklwd a, src, zero > punpckhwd b, src, zero
Thank you for pointing out this. This modification is really helpful for my improvement! Andreas: >Can this happen with real inputs (like when called from the decoder)? If > not, then the test needs to be made more realistic. > Anyway, what is the performance impact of this? I didn't have a unit test, but the average FPS looks no change. Ronald: > Also, the whole thing just emulates a saturated add. Can't you use paddsw > instead of paddw and be done with it? To add to Andreas' question: is > saturating here normatively required? We didn't have any sample that failed for this issue except for the checksum with specific seeds. I think we can keep not changing it until a real sample has something wrong. @Nuomi to get more details. _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
