[FFmpeg-devel] [PATCH] avcodec/rv60dec: Avoid branch when decoding cbp16

[FFmpeg-devel] [PATCH] avcodec/rv60dec: Avoid branch when decoding cbp16

[Andreas Rheinhardt]

[-- Attachment #1: Type: text/plain, Size: 27 bytes --]

Patch attached.

- Andreas

[-- Attachment #2: 0001-avcodec-rv60dec-Avoid-branch-when-decoding-cbp16.patch --]
[-- Type: text/x-patch, Size: 2069 bytes --]

From 02724d5792348bea618c049034dc0febf24a46ac Mon Sep 17 00:00:00 2001
From: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
Date: Sun, 18 May 2025 23:12:03 +0200
Subject: [PATCH] avcodec/rv60dec: Avoid branch when decoding cbp16

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
---
 libavcodec/rv60dec.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/libavcodec/rv60dec.c b/libavcodec/rv60dec.c
index d704ae512c..2bbcb1d620 100644
--- a/libavcodec/rv60dec.c
+++ b/libavcodec/rv60dec.c
@@ -82,7 +82,7 @@ enum {
 };
 
 static const VLCElem * cbp8_vlc[7][4];
-static const VLCElem * cbp16_vlc[7][3][4];
+static const VLCElem * cbp16_vlc[7][4][4];
 
 typedef struct {
     const VLCElem * l0[2];
@@ -137,12 +137,12 @@ static av_cold void rv60_init_static_data(void)
 
     for (int i = 0; i < 7; i++)
         for (int j = 0; j < 4; j++)
-            cbp8_vlc[i][j] = gen_vlc(rv60_cbp8_lens[i][j], 64, &state);
+            cbp16_vlc[i][0][j] = cbp8_vlc[i][j] = gen_vlc(rv60_cbp8_lens[i][j], 64, &state);
 
     for (int i = 0; i < 7; i++)
         for (int j = 0; j < 3; j++)
             for (int k = 0; k < 4; k++)
-                cbp16_vlc[i][j][k] = gen_vlc(rv60_cbp16_lens[i][j][k], 64, &state);
+                cbp16_vlc[i][j + 1][k] = gen_vlc(rv60_cbp16_lens[i][j][k], 64, &state);
 
     build_coeff_vlc(rv60_intra_lens, intra_coeff_vlc, 5, &state);
     build_coeff_vlc(rv60_inter_lens, inter_coeff_vlc, 7, &state);
@@ -1650,10 +1650,7 @@ static int decode_super_cbp(GetBitContext * gb, const VLCElem * vlc[4])
 static int decode_cbp16(GetBitContext * gb, int subset, int qp)
 {
     int cb_set = rv60_qp_to_idx[qp];
-    if (!subset)
-        return decode_super_cbp(gb, cbp8_vlc[cb_set]);
-    else
-        return decode_super_cbp(gb, cbp16_vlc[cb_set][subset - 1]);
+    return decode_super_cbp(gb, cbp16_vlc[cb_set][subset]);
 }
 
 static int decode_cu_r(RV60Context * s, AVFrame * frame, ThreadContext * thread, GetBitContext * gb, int xpos, int ypos, int log_size, int qp, int sel_qp)
-- 
2.45.2


[-- Attachment #3: Type: text/plain, Size: 251 bytes --]

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".

Re: [FFmpeg-devel] [PATCH] avcodec/rv60dec: Avoid branch when decoding cbp16

[Peter Ross]

[-- Attachment #1.1: Type: text/plain, Size: 2475 bytes --]

On Mon, May 19, 2025 at 12:06:02AM +0200, Andreas Rheinhardt wrote:
> Patch attached.
> 
> - Andreas

> From 02724d5792348bea618c049034dc0febf24a46ac Mon Sep 17 00:00:00 2001
> From: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
> Date: Sun, 18 May 2025 23:12:03 +0200
> Subject: [PATCH] avcodec/rv60dec: Avoid branch when decoding cbp16
> 
> Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
> ---
>  libavcodec/rv60dec.c | 11 ++++-------
>  1 file changed, 4 insertions(+), 7 deletions(-)
> 
> diff --git a/libavcodec/rv60dec.c b/libavcodec/rv60dec.c
> index d704ae512c..2bbcb1d620 100644
> --- a/libavcodec/rv60dec.c
> +++ b/libavcodec/rv60dec.c
> @@ -82,7 +82,7 @@ enum {
>  };
>  
>  static const VLCElem * cbp8_vlc[7][4];
> -static const VLCElem * cbp16_vlc[7][3][4];
> +static const VLCElem * cbp16_vlc[7][4][4];
>  
>  typedef struct {
>      const VLCElem * l0[2];
> @@ -137,12 +137,12 @@ static av_cold void rv60_init_static_data(void)
>  
>      for (int i = 0; i < 7; i++)
>          for (int j = 0; j < 4; j++)
> -            cbp8_vlc[i][j] = gen_vlc(rv60_cbp8_lens[i][j], 64, &state);
> +            cbp16_vlc[i][0][j] = cbp8_vlc[i][j] = gen_vlc(rv60_cbp8_lens[i][j], 64, &state);
>  
>      for (int i = 0; i < 7; i++)
>          for (int j = 0; j < 3; j++)
>              for (int k = 0; k < 4; k++)
> -                cbp16_vlc[i][j][k] = gen_vlc(rv60_cbp16_lens[i][j][k], 64, &state);
> +                cbp16_vlc[i][j + 1][k] = gen_vlc(rv60_cbp16_lens[i][j][k], 64, &state);
>  
>      build_coeff_vlc(rv60_intra_lens, intra_coeff_vlc, 5, &state);
>      build_coeff_vlc(rv60_inter_lens, inter_coeff_vlc, 7, &state);
> @@ -1650,10 +1650,7 @@ static int decode_super_cbp(GetBitContext * gb, const VLCElem * vlc[4])
>  static int decode_cbp16(GetBitContext * gb, int subset, int qp)
>  {
>      int cb_set = rv60_qp_to_idx[qp];
> -    if (!subset)
> -        return decode_super_cbp(gb, cbp8_vlc[cb_set]);
> -    else
> -        return decode_super_cbp(gb, cbp16_vlc[cb_set][subset - 1]);
> +    return decode_super_cbp(gb, cbp16_vlc[cb_set][subset]);
>  }
>  
>  static int decode_cu_r(RV60Context * s, AVFrame * frame, ThreadContext * thread, GetBitContext * gb, int xpos, int ypos, int log_size, int qp, int sel_qp)
> -- 
> 2.45.2

Looks okay. What was the motivation for this change. Speed up; any numbers?

-- Peter
(A907 E02F A6E5 0CD2 34CD 20D2 6760 79C5 AC40 DD6B)

[-- Attachment #1.2: signature.asc --]
[-- Type: application/pgp-signature, Size: 195 bytes --]

[-- Attachment #2: Type: text/plain, Size: 251 bytes --]

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".

Re: [FFmpeg-devel] [PATCH] avcodec/rv60dec: Avoid branch when decoding cbp16

[Andreas Rheinhardt]

Peter Ross:
> On Mon, May 19, 2025 at 12:06:02AM +0200, Andreas Rheinhardt wrote:
>> Patch attached.
>>
>> - Andreas
> 
>> From 02724d5792348bea618c049034dc0febf24a46ac Mon Sep 17 00:00:00 2001
>> From: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
>> Date: Sun, 18 May 2025 23:12:03 +0200
>> Subject: [PATCH] avcodec/rv60dec: Avoid branch when decoding cbp16
>>
>> Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
>> ---
>>  libavcodec/rv60dec.c | 11 ++++-------
>>  1 file changed, 4 insertions(+), 7 deletions(-)
>>
>> diff --git a/libavcodec/rv60dec.c b/libavcodec/rv60dec.c
>> index d704ae512c..2bbcb1d620 100644
>> --- a/libavcodec/rv60dec.c
>> +++ b/libavcodec/rv60dec.c
>> @@ -82,7 +82,7 @@ enum {
>>  };
>>  
>>  static const VLCElem * cbp8_vlc[7][4];
>> -static const VLCElem * cbp16_vlc[7][3][4];
>> +static const VLCElem * cbp16_vlc[7][4][4];
>>  
>>  typedef struct {
>>      const VLCElem * l0[2];
>> @@ -137,12 +137,12 @@ static av_cold void rv60_init_static_data(void)
>>  
>>      for (int i = 0; i < 7; i++)
>>          for (int j = 0; j < 4; j++)
>> -            cbp8_vlc[i][j] = gen_vlc(rv60_cbp8_lens[i][j], 64, &state);
>> +            cbp16_vlc[i][0][j] = cbp8_vlc[i][j] = gen_vlc(rv60_cbp8_lens[i][j], 64, &state);
>>  
>>      for (int i = 0; i < 7; i++)
>>          for (int j = 0; j < 3; j++)
>>              for (int k = 0; k < 4; k++)
>> -                cbp16_vlc[i][j][k] = gen_vlc(rv60_cbp16_lens[i][j][k], 64, &state);
>> +                cbp16_vlc[i][j + 1][k] = gen_vlc(rv60_cbp16_lens[i][j][k], 64, &state);
>>  
>>      build_coeff_vlc(rv60_intra_lens, intra_coeff_vlc, 5, &state);
>>      build_coeff_vlc(rv60_inter_lens, inter_coeff_vlc, 7, &state);
>> @@ -1650,10 +1650,7 @@ static int decode_super_cbp(GetBitContext * gb, const VLCElem * vlc[4])
>>  static int decode_cbp16(GetBitContext * gb, int subset, int qp)
>>  {
>>      int cb_set = rv60_qp_to_idx[qp];
>> -    if (!subset)
>> -        return decode_super_cbp(gb, cbp8_vlc[cb_set]);
>> -    else
>> -        return decode_super_cbp(gb, cbp16_vlc[cb_set][subset - 1]);
>> +    return decode_super_cbp(gb, cbp16_vlc[cb_set][subset]);
>>  }
>>  
>>  static int decode_cu_r(RV60Context * s, AVFrame * frame, ThreadContext * thread, GetBitContext * gb, int xpos, int ypos, int log_size, int qp, int sel_qp)
>> -- 
>> 2.45.2
> 
> Looks okay. What was the motivation for this change. Speed up; any numbers?
> 

I saw a branch that could be avoided. I don't think that this leads to
any measurable speedup.

- Andreas

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".