Re: [FFmpeg-devel] [PATCH] avutil/imgutils: optimize image copy efficiency

Fri, 05 May 2023 02:52:00 -0700 

There is an if condition "FFALIGN(linesize[i], align) == linesize[i] && 
src_linesize[i] == linesize[i]".
When src's linesize equals to dst, it has no padding in this case I think. If 
has padding, it will execute
previous process. As a result, we could ignore the situation of padding in this 
case.


Thank you


//frank
 




------------------ Original ------------------
From:                                                                           
                                             "FFmpeg development discussions 
and patches"                                                                    
                <[email protected]&gt;;
Date:&nbsp;Thu, May 4, 2023 04:22 PM
To:&nbsp;"FFmpeg development discussions and 
patches"<[email protected]&gt;;
Cc:&nbsp;"??????"<[email protected]&gt;;
Subject:&nbsp;Re: [FFmpeg-devel] [PATCH] avutil/imgutils: optimize image copy 
efficiency



On Thu, 4 May 2023, xufuji456 wrote:

&gt; It makes sense when copying 4K/8K video, if linesize
&gt; equals to aligned linesize.
&gt;
&gt; Signed-off-by: xufuji456 <[email protected]&gt;
&gt; ---
&gt; libavutil/imgutils.c | 15 +++++++++++----
&gt; 1 file changed, 11 insertions(+), 4 deletions(-)
&gt;
&gt; diff --git a/libavutil/imgutils.c b/libavutil/imgutils.c
&gt; index 9ab5757cf6..1d432e7a57 100644
&gt; --- a/libavutil/imgutils.c
&gt; +++ b/libavutil/imgutils.c
&gt; @@ -525,10 +525,17 @@ int av_image_copy_to_buffer(uint8_t *dst, int 
dst_size,
&gt;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; const uint8_t *src = 
src_data[i];
&gt;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; h = (height + (1 << shift) 
- 1) &gt;&gt; shift;
&gt;
&gt; -&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; for (j = 0; j < h; j++) {
&gt; -&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 
memcpy(dst, src, linesize[i]);
&gt; -&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; dst += 
FFALIGN(linesize[i], align);
&gt; -&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; src += 
src_linesize[i];
&gt; +&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; if (FFALIGN(linesize[i], 
align) == linesize[i] &amp;&amp; src_linesize[i] == linesize[i]) {
&gt; +&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; int 
size = linesize[i] * h;

For cases like these, I would prefer to use "linesize[i] * (h - 1) + w" 
instead. For cases if copying e.g. into an offsetted position within a 
buffer, writing the last trailing padding would end up writing out of 
bounds.

That said, I'm unsure about how much gain you get from this optimization 
here - some numbers to back it up would be useful.

// Martin

_______________________________________________
ffmpeg-devel mailing list
[email protected]
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
[email protected] with subject "unsubscribe".
_______________________________________________
ffmpeg-devel mailing list
[email protected]
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
[email protected] with subject "unsubscribe".

Reply via email to