Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-09-21 Thread flow gg
It feels like this patch has been sitting idle for quite a long time... Maybe it's time to merge it Rémi Denis-Courmont 于2024年9月14日周六 22:45写道: > Hi, > > LGTM for the RISC-V side. No clue about the VVC side. > ___ > ffmpeg-devel mailing list > ffmpeg-de

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-09-15 Thread flow gg
> LGTM for the RISC-V side. No clue about the VVC side. Hi, Nuomi, could you please reply here? Thanks flow gg 于2024年9月13日周五 00:45写道: > ping > > flow gg 于2024年8月28日周三 14:38写道: > >> Updated: zve32x -> zve32x, zbb, zba >> >> 于2024年8月28日周三 14:37写道: >> >>> From: sunyuechi >>> >>>

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-09-14 Thread Rémi Denis-Courmont
Hi, LGTM for the RISC-V side. No clue about the VVC side. ___ 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 "uns

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-09-12 Thread flow gg
ping flow gg 于2024年8月28日周三 14:38写道: > Updated: zve32x -> zve32x, zbb, zba > > 于2024年8月28日周三 14:37写道: > >> From: sunyuechi >> >> C908 X60 >> avg_8_2x2_c:1.21.0 >> avg_8_2x2_rvv_i32

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-08-27 Thread flow gg
Updated: zve32x -> zve32x, zbb, zba 于2024年8月28日周三 14:37写道: > From: sunyuechi > > C908 X60 > avg_8_2x2_c:1.21.0 > avg_8_2x2_rvv_i32 :0.70.7 > avg_8_2x4_

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-08-27 Thread Rémi Denis-Courmont
Le sunnuntaina 18. elokuuta 2024, 13.19.33 EEST flow gg a écrit : > Based on the test results for 49 different resolutions, most of them were > significantly slower. OK, thanks for checking. The heights are probably not large enough for this to work. I don't have any objection on the RISC-V side

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-08-18 Thread flow gg
I wrote `ff_vvc_w_avg_8_rvv` by mimicking the h264 weight function. Based on the test results for 49 different resolutions, most of them were significantly slower. Only 2x32 and 2x64 had similar performance, without noticeable speed improvement. I'm not sure about the reason. Some differences ar

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-08-17 Thread flow gg
How can I test the weight and biweight of H.264? I haven't seen the related test code.. tests/checkasm/checkasm --bench --test=h264dsp Rémi Denis-Courmont 于2024年8月15日周四 16:10写道: > > > Le 3 août 2024 13:30:34 GMT+03:00, u...@foxmail.com a écrit : > >From: sunyuechi > > > >

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-08-15 Thread Rémi Denis-Courmont
Le 3 août 2024 13:30:34 GMT+03:00, u...@foxmail.com a écrit : >From: sunyuechi > > C908 X60 >avg_8_2x2_c:1.21.0 >avg_8_2x2_rvv_i32 :0.70.7 >avg_8_2x4_c

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-08-03 Thread flow gg
Added lpad and resolved conflicts with master. 于2024年8月3日周六 18:31写道: > From: sunyuechi > > C908 X60 > avg_8_2x2_c:1.21.0 > avg_8_2x2_rvv_i32 :0.70.7 >

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-07-21 Thread flow gg
Okay, updated it Rémi Denis-Courmont 于2024年7月19日周五 23:56写道: > Le torstaina 18. heinäkuuta 2024, 18.04.15 EEST flow gg a écrit : > > > Again, I don't think that a maximul multiplier belongs here. If the > > > calling code cannot scale the multiplier up, then it should be a normal > > > loop provi

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-07-19 Thread Rémi Denis-Courmont
Le torstaina 18. heinäkuuta 2024, 18.04.15 EEST flow gg a écrit : > > Again, I don't think that a maximul multiplier belongs here. If the > > calling code cannot scale the multiplier up, then it should be a normal > > loop providing the same code for all VLENs. > > I think it's acceptable to add s

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-07-18 Thread flow gg
> Again, I don't think that a maximul multiplier belongs here. If the calling > code cannot scale the multiplier up, then it should be a normal loop providing > the same code for all VLENs. I think it's acceptable to add such a parameter, which isn't particularly common in other files, because thi

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-07-16 Thread Rémi Denis-Courmont
Le keskiviikkona 10. heinäkuuta 2024, 13.02.44 EEST u...@foxmail.com a écrit : > From: sunyuechi > > C908 X60 > avg_8_2x2_c:1.21.2 > avg_8_2x2_rvv_i32 :0.7

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-05-25 Thread Rémi Denis-Courmont
Hi, Sorry for the delay, this is not my day job. Le tiistaina 21. toukokuuta 2024, 22.24.21 EEST u...@foxmail.com a écrit : > From: sunyuechi > --- > libavcodec/riscv/Makefile | 2 + > libavcodec/riscv/vvc_mc_rvv.S | 313 + > libavcodec/riscv/vvcd

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-05-21 Thread flow gg
Reordered some here. 于2024年5月22日周三 03:24写道: > From: sunyuechi > > C908 X60 > avg_8_2x2_c:1.01.0 > avg_8_2x2_rvv_i32 :0.70.7 > avg_8_2x4_c

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-05-21 Thread flow gg
> I would expect that you can get better performance by interleaving scalar and vector stuff, and possibly also vector loads and vector arithmetic. Okay, I will try > These labels lead to nowhere? If you actually mean to implicitly fall through to the next function, you can use the function name

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-05-21 Thread Rémi Denis-Courmont
Le tiistaina 21. toukokuuta 2024, 10.37.51 EEST u...@foxmail.com a écrit : > From: sunyuechi > --- > libavcodec/riscv/Makefile | 2 + > libavcodec/riscv/vvc_mc_rvv.S | 312 + > libavcodec/riscv/vvcdsp_init.c | 76 > libavcodec/vvc/dsp.c

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-05-21 Thread flow gg
There are three unused lines which I forgot to delete before submitting. I have updated them here. 于2024年5月21日周二 15:47写道: > From: sunyuechi > > C908 X60 > avg_8_2x2_c:1.01.0 > avg_8_2x2_rvv_i

Re: [FFmpeg-devel] [PATCH] lavc/vvc_mc: R-V V avg w_avg

2024-05-21 Thread flow gg
To obtain test results, need to comment out the if (w == h) in tests/checkasm/vvc_mc.c. Because vset needs to be used in the loop, I manually wrote a cumbersome vset macro. 于2024年5月21日周二 15:38写道: > From: sunyuechi > > C908 X60 > avg_8_2x2_