Looks like there is a sample that you can reference to now. #21757 - hevc intra pred neon optimizations - FFmpeg/FFmpeg - FFmpeg Forgejo<https://code.ffmpeg.org/FFmpeg/FFmpeg/pulls/21757>
Hi @Frank Plowman<mailto:[email protected]>, Would you be interested in being the mentor for the task? Not sure if we can catch the deadline. Thanks, Jianhua ________________________________ 发件人: Hank Li <[email protected]> 发送时间: 2026年3月30日 2:04 收件人: FFmpeg development discussions and patches <[email protected]> 抄送: Frank Plowman <[email protected]>; Wu Jianhua <[email protected]> 主题: Re: [FFmpeg-devel] 回复: Re: [GSoC 2026] Proposal/Mentorship Request: VVC x86 SIMD Optimization On Sun, Mar 29, 2026 at 5:29 AM Wu Jianhua via ffmpeg-devel <[email protected]> wrote: > > Hi there. > > Let me add some background here. > > The assembly optimization of inv is too complicated to be a GSOC task. > You can refer to the code of dav1d to see how it can be. > https://code.videolan.org/videolan/dav1d/-/blob/master/src/x86/itx_avx2.asm?ref_type=heads. > We do have an internal version of it. That's why we haven't posted and merged > it yet. > > About the intra prediction, some function of the current C code with the > compilation optimization enabled will run fast enough, so the handwritten > assembly will not definitely be faster than the C code. You may need to run > a performance test to evaluate it. > > Thanks, > Jianhua > > ________________________________ > 发件人: Frank Plowman via ffmpeg-devel <[email protected]> > 发送时间: 2026年3月29日 3:20 > 收件人: [email protected] <[email protected]> > 抄送: Frank Plowman <[email protected]> > 主题: [FFmpeg-devel] Re: [GSoC 2026] Proposal/Mentorship Request: VVC x86 SIMD > Optimization > > On 28/03/2026 16:01, Hank Li via ffmpeg-devel wrote: > > Hello, > > > > I'm a bit late to the party, but I'm interested in proposing a GSoC > > project on VVC x86 SIMD optimization. This was on the 2025 ideas list > > but there are currently no SIMD overrides for itx or intra_pred in > > avcodec/x86/vvc/dsp_init.c, only ALF and inter prediction have x86 > > assembly. > > > > I would like to propose implementing: > > -AVX2 inverse transforms for DCT-II, DST-VII, and DCT-VIII > > -Intra prediction for DC, planar, and angular modes > > -Corresponding checkasm tests and benchmarks > > > > For qualification, I'm currently working on a checkasm test for VVC > > inverse transforms (tests/checkasm/vvc_itx.c). > > > > I've emailed Nuo Mi about mentoring since he mentored the VVC SIMD > > projects in 2023 and 2024. If anyone else is interested in mentoring > > or has thoughts, I'd appreciate it. > > > > Best, > > Hankang Li > > _______________________________________________ > > ffmpeg-devel mailing list -- [email protected] > > To unsubscribe send an email to [email protected] > > Hi, > > Thanks for your interest in the VVC decoder. > > Writing assembly optimizations for the inverse transforms will be > significantly more difficult than for the intra prediction I believe. > There isn't much precedent for rectangular transforms available, whereas > the intra prediction functions are largely similar to HEVC's only with > an increased number of taps. Perhaps a more suitable plan would be to > begin with the intra prediction functions and then to have the inverse > transform functions as a "stretch goal". I don't know how familiar you > are with AVX2 and video coding, but that would represent a more natural > introduction and progression of difficulty. > > -- > Frank > _______________________________________________ > ffmpeg-devel mailing list -- [email protected] > To unsubscribe send an email to [email protected] Hello Frank, Jianhua, Thanks for the feedback. Since the remaining dsp contexts with no x86 SIMD are intra, itx, lmcs, and lf, would it make sense if I proposed intra prediction and deblock luma? I know work was done for deblock during GSoC 2023 but it doesn't look like it was merged. Is that available somewhere or would it need to be redone? Regarding compiler optimizations, I can write a checkasm test for intra prediction as a qualification task to profile the C code. Would the x86 assembly for HEVC intra prediction give a reasonable estimate of the speedup achievable for VVC? Also, would either of you consider mentoring this project? Thanks, Hankang _______________________________________________ ffmpeg-devel mailing list -- [email protected] To unsubscribe send an email to [email protected]
