Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
 help / color / mirror / Atom feed
* [FFmpeg-devel] [PATCH] avutil/imgutils: optimize image copy efficiency
@ 2023-05-04  7:54 xufuji456
  2023-05-04  8:22 ` Martin Storsjö
  0 siblings, 1 reply; 4+ messages in thread
From: xufuji456 @ 2023-05-04  7:54 UTC (permalink / raw)
  To: ffmpeg-devel; +Cc: xufuji456

It makes sense when copying 4K/8K video, if linesize
equals to aligned linesize.

Signed-off-by: xufuji456 <839789740@qq.com>
---
 libavutil/imgutils.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/libavutil/imgutils.c b/libavutil/imgutils.c
index 9ab5757cf6..1d432e7a57 100644
--- a/libavutil/imgutils.c
+++ b/libavutil/imgutils.c
@@ -525,10 +525,17 @@ int av_image_copy_to_buffer(uint8_t *dst, int dst_size,
         const uint8_t *src = src_data[i];
         h = (height + (1 << shift) - 1) >> shift;
 
-        for (j = 0; j < h; j++) {
-            memcpy(dst, src, linesize[i]);
-            dst += FFALIGN(linesize[i], align);
-            src += src_linesize[i];
+        if (FFALIGN(linesize[i], align) == linesize[i] && src_linesize[i] == linesize[i]) {
+            int size = linesize[i] * h;
+            memcpy(dst, src, size);
+            dst += size;
+            src += size;
+        } else {
+            for (j = 0; j < h; j++) {
+                memcpy(dst, src, linesize[i]);
+                dst += FFALIGN(linesize[i], align);
+                src += src_linesize[i];
+            }
         }
     }
 
-- 
2.32.0 (Apple Git-132)

_______________________________________________
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".

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [FFmpeg-devel] [PATCH] avutil/imgutils: optimize image copy efficiency
  2023-05-04  7:54 [FFmpeg-devel] [PATCH] avutil/imgutils: optimize image copy efficiency xufuji456
@ 2023-05-04  8:22 ` Martin Storsjö
  2023-05-04 13:18   ` =?gb18030?B?0Oy4o8Kh?=
  2023-05-05  9:51   ` =?gb18030?B?0Oy4o8Kh?=
  0 siblings, 2 replies; 4+ messages in thread
From: Martin Storsjö @ 2023-05-04  8:22 UTC (permalink / raw)
  To: FFmpeg development discussions and patches; +Cc: xufuji456

On Thu, 4 May 2023, xufuji456 wrote:

> It makes sense when copying 4K/8K video, if linesize
> equals to aligned linesize.
>
> Signed-off-by: xufuji456 <839789740@qq.com>
> ---
> libavutil/imgutils.c | 15 +++++++++++----
> 1 file changed, 11 insertions(+), 4 deletions(-)
>
> diff --git a/libavutil/imgutils.c b/libavutil/imgutils.c
> index 9ab5757cf6..1d432e7a57 100644
> --- a/libavutil/imgutils.c
> +++ b/libavutil/imgutils.c
> @@ -525,10 +525,17 @@ int av_image_copy_to_buffer(uint8_t *dst, int dst_size,
>         const uint8_t *src = src_data[i];
>         h = (height + (1 << shift) - 1) >> shift;
>
> -        for (j = 0; j < h; j++) {
> -            memcpy(dst, src, linesize[i]);
> -            dst += FFALIGN(linesize[i], align);
> -            src += src_linesize[i];
> +        if (FFALIGN(linesize[i], align) == linesize[i] && src_linesize[i] == linesize[i]) {
> +            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
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".

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [FFmpeg-devel] [PATCH] avutil/imgutils: optimize image copy efficiency
  2023-05-04  8:22 ` Martin Storsjö
@ 2023-05-04 13:18   ` =?gb18030?B?0Oy4o8Kh?=
  2023-05-05  9:51   ` =?gb18030?B?0Oy4o8Kh?=
  1 sibling, 0 replies; 4+ messages in thread
From: =?gb18030?B?0Oy4o8Kh?= @ 2023-05-04 13:18 UTC (permalink / raw)
  To: =?gb18030?B?RkZtcGVnIGRldmVsb3BtZW50IGRpc2N1c3Npb25zIGFuZCBwYXRjaGVz?=
  Cc: =?gb18030?B?TWFydGluJm5ic3A7U3RvcnNqhDGkNw==?=

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset="gb18030", Size: 2955 bytes --]

Thank you for your review, Martin.
I try add some data, and submit again.




------------------&nbsp;Original&nbsp;------------------
From:                                                                                                                        "FFmpeg development discussions and patches"                                                                                    <martin@martin.st&gt;;
Date:&nbsp;Thu, May 4, 2023 04:22 PM
To:&nbsp;"FFmpeg development discussions and patches"<ffmpeg-devel@ffmpeg.org&gt;;
Cc:&nbsp;"Ð츣¡"<839789740@qq.com&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 <839789740@qq.com&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
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".
_______________________________________________
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".

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [FFmpeg-devel] [PATCH] avutil/imgutils: optimize image copy efficiency
  2023-05-04  8:22 ` Martin Storsjö
  2023-05-04 13:18   ` =?gb18030?B?0Oy4o8Kh?=
@ 2023-05-05  9:51   ` =?gb18030?B?0Oy4o8Kh?=
  1 sibling, 0 replies; 4+ messages in thread
From: =?gb18030?B?0Oy4o8Kh?= @ 2023-05-05  9:51 UTC (permalink / raw)
  To: =?gb18030?B?RkZtcGVnIGRldmVsb3BtZW50IGRpc2N1c3Npb25zIGFuZCBwYXRjaGVz?=
  Cc: =?gb18030?B?TWFydGluJm5ic3A7U3RvcnNqhDGkNw==?=

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset="gb18030", Size: 3224 bytes --]

There is an if condition "FFALIGN(linesize[i], align) == linesize[i] &amp;&amp; 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
&nbsp;




------------------&nbsp;Original&nbsp;------------------
From:                                                                                                                        "FFmpeg development discussions and patches"                                                                                    <martin@martin.st&gt;;
Date:&nbsp;Thu, May 4, 2023 04:22 PM
To:&nbsp;"FFmpeg development discussions and patches"<ffmpeg-devel@ffmpeg.org&gt;;
Cc:&nbsp;"Ð츣¡"<839789740@qq.com&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 <839789740@qq.com&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
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".
_______________________________________________
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".

^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2023-05-05  9:51 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2023-05-04  7:54 [FFmpeg-devel] [PATCH] avutil/imgutils: optimize image copy efficiency xufuji456
2023-05-04  8:22 ` Martin Storsjö
2023-05-04 13:18   ` =?gb18030?B?0Oy4o8Kh?=
2023-05-05  9:51   ` =?gb18030?B?0Oy4o8Kh?=

Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \
		ffmpegdev@gitmailbox.com
	public-inbox-index ffmpegdev

Example config snippet for mirrors.


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git