Re: [FFmpeg-devel] [PATCH 4/4] lavc/rv34dsp: R-V V rv34_idct_dc_add

[flow gg]

I tested this in '[FFmpeg-devel] [PATCH] lavc/vc1dsp: R-V V inv_trans'. The
logic here is the same, using vext can reduce vset, making it a bit faster

Rémi Denis-Courmont  于2024年2月13日周二 03:46写道：

> Le keskiviikkona 31. tammikuuta 2024, 19.58.55 EET flow gg a écrit :
> > Fixed the rv32 break in this reply
>
> It looks like widening add would avoid the sign extension.
>
> Although you'd need as many instructions, since V lacks signed to unsigned
> clipping.
>
> --
> Rémi Denis-Courmont
> http://www.remlab.net/
>
>
>
> ___
> 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".
>
___
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".

Re: [FFmpeg-devel] [PATCH 4/4] lavc/rv34dsp: R-V V rv34_idct_dc_add

[Rémi Denis-Courmont]

Le keskiviikkona 31. tammikuuta 2024, 19.58.55 EET flow gg a écrit :
> Fixed the rv32 break in this reply

It looks like widening add would avoid the sign extension.

Although you'd need as many instructions, since V lacks signed to unsigned 
clipping.

-- 
Rémi Denis-Courmont
http://www.remlab.net/



___
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".

Re: [FFmpeg-devel] [PATCH 4/4] lavc/rv34dsp: R-V V rv34_idct_dc_add

[flow gg]

Fixed the rv32 break in this reply

flow gg  于2024年1月31日周三 20:01写道：

>
>
From 0874f319e1c26aa0eeb5ed0d4e00d29aec4c5af8 Mon Sep 17 00:00:00 2001
From: sunyuechi 
Date: Wed, 31 Jan 2024 19:04:11 +0800
Subject: [PATCH 4/4] lavc/rv34dsp: R-V V rv34_idct_dc_add

C908:
rv34_idct_dc_add_c: 134.7
rv34_idct_dc_add_rvv_i32: 45.5
---
 libavcodec/riscv/rv34dsp_init.c |  2 ++
 libavcodec/riscv/rv34dsp_rvv.S  | 20 
 2 files changed, 22 insertions(+)

diff --git a/libavcodec/riscv/rv34dsp_init.c b/libavcodec/riscv/rv34dsp_init.c
index 852c8ad9a8..7dcadc7e43 100644
--- a/libavcodec/riscv/rv34dsp_init.c
+++ b/libavcodec/riscv/rv34dsp_init.c
@@ -26,6 +26,7 @@
 #include "libavcodec/rv34dsp.h"
 
 void ff_rv34_inv_transform_dc_rvv(int16_t *block);
+void ff_rv34_idct_dc_add_rvv(uint8_t *dst, ptrdiff_t stride, int dc);
 
 av_cold void ff_rv34dsp_init_riscv(RV34DSPContext *c)
 {
@@ -34,6 +35,7 @@ av_cold void ff_rv34dsp_init_riscv(RV34DSPContext *c)
 
 if (flags & AV_CPU_FLAG_RVV_I32 && ff_get_rv_vlenb() >= 16) {
 c->rv34_inv_transform_dc = ff_rv34_inv_transform_dc_rvv;
+c->rv34_idct_dc_add = ff_rv34_idct_dc_add_rvv;
 }
 #endif
 }
diff --git a/libavcodec/riscv/rv34dsp_rvv.S b/libavcodec/riscv/rv34dsp_rvv.S
index 4b7a071f7c..450226f742 100644
--- a/libavcodec/riscv/rv34dsp_rvv.S
+++ b/libavcodec/riscv/rv34dsp_rvv.S
@@ -36,3 +36,23 @@ func ff_rv34_inv_transform_dc_rvv, zve32x
 
 ret
 endfunc
+
+func ff_rv34_idct_dc_add_rvv, zve32x
+vsetivli  zero, 4, e8, mf4, ta, ma
+vlse32.v  v0, (a0), a1
+lit1, 169
+mul   t1, t1, a2
+lia2, 255
+addi  t1, t1, 512
+srai  t1, t1, 10
+vsetivli  zero, 4*4, e16, m2, ta, ma
+vzext.vf2 v2, v0
+vadd.vx   v2, v2, t1
+vmax.vx   v2, v2, zero
+vsetvli   zero, zero, e8, m1, ta, ma
+vnclipu.wiv0, v2, 0
+vsetivli  zero, 4, e8, mf4, ta, ma
+vsse32.v  v0, (a0), a1
+
+ret
+endfunc
-- 
2.43.0

___
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".

[FFmpeg-devel] [PATCH 4/4] lavc/rv34dsp: R-V V rv34_idct_dc_add

[flow gg]

From aec115a7179f23642c2b1c1a1cae3253a40c38fc Mon Sep 17 00:00:00 2001
From: sunyuechi 
Date: Wed, 31 Jan 2024 19:04:11 +0800
Subject: [PATCH 4/4] lavc/rv34dsp: R-V V rv34_idct_dc_add

C908:
rv34_idct_dc_add_c: 134.7
rv34_idct_dc_add_rvv_i32: 45.5
---
 libavcodec/riscv/rv34dsp_init.c |  2 ++
 libavcodec/riscv/rv34dsp_rvv.S  | 20 
 2 files changed, 22 insertions(+)

diff --git a/libavcodec/riscv/rv34dsp_init.c b/libavcodec/riscv/rv34dsp_init.c
index 852c8ad9a8..7dcadc7e43 100644
--- a/libavcodec/riscv/rv34dsp_init.c
+++ b/libavcodec/riscv/rv34dsp_init.c
@@ -26,6 +26,7 @@
 #include "libavcodec/rv34dsp.h"
 
 void ff_rv34_inv_transform_dc_rvv(int16_t *block);
+void ff_rv34_idct_dc_add_rvv(uint8_t *dst, ptrdiff_t stride, int dc);
 
 av_cold void ff_rv34dsp_init_riscv(RV34DSPContext *c)
 {
@@ -34,6 +35,7 @@ av_cold void ff_rv34dsp_init_riscv(RV34DSPContext *c)
 
 if (flags & AV_CPU_FLAG_RVV_I32 && ff_get_rv_vlenb() >= 16) {
 c->rv34_inv_transform_dc = ff_rv34_inv_transform_dc_rvv;
+c->rv34_idct_dc_add = ff_rv34_idct_dc_add_rvv;
 }
 #endif
 }
diff --git a/libavcodec/riscv/rv34dsp_rvv.S b/libavcodec/riscv/rv34dsp_rvv.S
index acf5b0c3e8..c73b9c4555 100644
--- a/libavcodec/riscv/rv34dsp_rvv.S
+++ b/libavcodec/riscv/rv34dsp_rvv.S
@@ -36,3 +36,23 @@ func ff_rv34_inv_transform_dc_rvv, zve32x
 
 ret
 endfunc
+
+func ff_rv34_idct_dc_add_rvv, zve32x
+vsetivli  zero, 4, e8, mf4, ta, ma
+vlse32.v  v0, (a0), a1
+lit1, 169
+mulw  t1, t1, a2
+lia2, 255
+addiw t1, t1, 512
+sraiw t1, t1, 10
+vsetivli  zero, 4*4, e16, m2, ta, ma
+vzext.vf2 v2, v0
+vadd.vx   v2, v2, t1
+vmax.vx   v2, v2, zero
+vsetvli   zero, zero, e8, m1, ta, ma
+vnclipu.wiv0, v2, 0
+vsetivli  zero, 4, e8, mf4, ta, ma
+vsse32.v  v0, (a0), a1
+
+ret
+endfunc
-- 
2.43.0

___
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".