Okay, learned it
Rémi Denis-Courmont 于2024年5月15日周三 01:00写道：
> Le tiistaina 14. toukokuuta 2024, 7.45.29 EEST flow gg a écrit :
> > I am locally using:
> > if (bpp == 8 && (flags & AV_CPU_FLAG_RVI) && (flags &
> > AV_CPU_FLAG_RVB_ADDR)) {
>
> There is no point testing the I flag if you test a
Le tiistaina 14. toukokuuta 2024, 7.45.29 EEST flow gg a écrit :
> I am locally using:
> if (bpp == 8 && (flags & AV_CPU_FLAG_RVI) && (flags &
> AV_CPU_FLAG_RVB_ADDR)) {
There is no point testing the I flag if you test any other flag. The I flag is
always set (since we don't, and probably nev
I am locally using:
if (bpp == 8 && (flags & AV_CPU_FLAG_RVI) && (flags &
AV_CPU_FLAG_RVB_ADDR)) {
this performs better on k230/banana_f3 than C.
For email, refer to [FFmpeg-devel] [PATCH 2/2] lavc/vp8dsp: restrict RVI
optimisations and change it to
if (bpp == 8 && (flags & AV_CPU_FLAG_RV_M
Le maanantaina 13. toukokuuta 2024, 19.59.18 EEST u...@foxmail.com a écrit :
> From: sunyuechi
>
> C908:
> vp9_vert_8x8_8bpp_c: 22.0
> vp9_vert_8x8_8bpp_rvi: 15.7
> vp9_vert_16x16_8bpp_c: 71.2
> vp9_vert_16x16_8bpp_rvi: 39.0
> vp9_vert_32x32_8bpp_c: 300.2
> vp9_vert_32x32_8bpp_rvi: 135.2
Not sur
Le maanantaina 13. toukokuuta 2024, 19.59.18 EEST u...@foxmail.com a écrit :
> From: sunyuechi
>
> C908:
> vp9_vert_8x8_8bpp_c: 22.0
> vp9_vert_8x8_8bpp_rvi: 15.7
> vp9_vert_16x16_8bpp_c: 71.2
> vp9_vert_16x16_8bpp_rvi: 39.0
> vp9_vert_32x32_8bpp_c: 300.2
> vp9_vert_32x32_8bpp_rvi: 135.2
> ---
>
just rebase
于2024年5月14日周二 01:00写道：
> From: sunyuechi
>
> C908:
> vp9_vert_8x8_8bpp_c: 22.0
> vp9_vert_8x8_8bpp_rvi: 15.7
> vp9_vert_16x16_8bpp_c: 71.2
> vp9_vert_16x16_8bpp_rvi: 39.0
> vp9_vert_32x32_8bpp_c: 300.2
> vp9_vert_32x32_8bpp_rvi: 135.2
> ---
> libavcodec/riscv/Makefile| 1 +
From: sunyuechi
C908:
vp9_vert_8x8_8bpp_c: 22.0
vp9_vert_8x8_8bpp_rvi: 15.7
vp9_vert_16x16_8bpp_c: 71.2
vp9_vert_16x16_8bpp_rvi: 39.0
vp9_vert_32x32_8bpp_c: 300.2
vp9_vert_32x32_8bpp_rvi: 135.2
---
libavcodec/riscv/Makefile| 1 +
libavcodec/riscv/vp9_intra_rvi.S | 71 +++
> It should be possible to improve ordering to avoid immediate dependency
from ADD to SD
Okay, updated it.
Additionally improved the mc-tap_64 on vlen>=256 and something
于2024年5月12日周日 18:04写道：
> From: sunyuechi
>
> C908:
> vp9_vert_8x8_8bpp_c: 22.0
> vp9_vert_8x8_8bpp_rvi: 15.7
> vp9_vert_16x
From: sunyuechi
C908:
vp9_vert_8x8_8bpp_c: 22.0
vp9_vert_8x8_8bpp_rvi: 15.7
vp9_vert_16x16_8bpp_c: 71.2
vp9_vert_16x16_8bpp_rvi: 39.0
vp9_vert_32x32_8bpp_c: 300.2
vp9_vert_32x32_8bpp_rvi: 135.2
---
libavcodec/riscv/Makefile| 1 +
libavcodec/riscv/vp9_intra_rvi.S | 71 +++
