Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
 help / color / mirror / Atom feed
From: Ramiro Polla <ramiro.polla@gmail.com>
To: FFmpeg development discussions and patches <ffmpeg-devel@ffmpeg.org>
Subject: Re: [FFmpeg-devel] [PATCH 04/17] swscale/graph: move vshift() and shift_img() to shared header
Date: Fri, 16 May 2025 17:41:44 +0200
Message-ID: <CALweWgC_WGdTGZmWpUroYjXzafets79dqbRddXWkBDijyOOKrQ@mail.gmail.com> (raw)
In-Reply-To: <20250426175603.726924-5-ffmpeg@haasn.xyz>

On Sat, Apr 26, 2025 at 7:57 PM Niklas Haas <ffmpeg@haasn.xyz> wrote:
>
> From: Niklas Haas <git@haasn.dev>
>
> I need to reuse these inside `ops.c`.
> ---
>  libswscale/graph.c | 29 +++++++----------------------
>  libswscale/graph.h | 13 +++++++++++++
>  2 files changed, 20 insertions(+), 22 deletions(-)
>
> diff --git a/libswscale/graph.c b/libswscale/graph.c
> index c5a46eb257..b921b7ec02 100644
> --- a/libswscale/graph.c
> +++ b/libswscale/graph.c
> @@ -94,29 +94,14 @@ static int pass_append(SwsGraph *graph, enum AVPixelFormat fmt, int w, int h,
>      return 0;
>  }
>
> -static int vshift(enum AVPixelFormat fmt, int plane)
> -{
> -    const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(fmt);
> -    return (plane == 1 || plane == 2) ? desc->log2_chroma_h : 0;
> -}
> -
> -/* Shift an image vertically by y lines */
> -static SwsImg shift_img(const SwsImg *img_base, int y)
> -{
> -    SwsImg img = *img_base;
> -    for (int i = 0; i < 4 && img.data[i]; i++)
> -        img.data[i] += (y >> vshift(img.fmt, i)) * img.linesize[i];
> -    return img;
> -}
> -
>  static void run_copy(const SwsImg *out_base, const SwsImg *in_base,
>                       int y, int h, const SwsPass *pass)
>  {
> -    SwsImg in  = shift_img(in_base,  y);
> -    SwsImg out = shift_img(out_base, y);
> +    SwsImg in  = ff_sws_img_shift(*in_base,  y);
> +    SwsImg out = ff_sws_img_shift(*out_base, y);
>
>      for (int i = 0; i < FF_ARRAY_ELEMS(out.data) && out.data[i]; i++) {
> -        const int lines = h >> vshift(in.fmt, i);
> +        const int lines = h >> ff_fmt_vshift(in.fmt, i);
>          av_assert1(in.data[i]);
>
>          if (in.linesize[i] == out.linesize[i]) {
[...]
> diff --git a/libswscale/graph.h b/libswscale/graph.h
> index 62b622a065..191734b794 100644
> --- a/libswscale/graph.h
> +++ b/libswscale/graph.h
> @@ -34,6 +34,19 @@ typedef struct SwsImg {
>      int linesize[4];
>  } SwsImg;
>
> +static av_always_inline av_const int ff_fmt_vshift(enum AVPixelFormat fmt, int plane)
> +{
> +    const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(fmt);
> +    return (plane == 1 || plane == 2) ? desc->log2_chroma_h : 0;
> +}
> +
> +static av_const inline SwsImg ff_sws_img_shift(SwsImg img, const int y)
> +{
> +    for (int i = 0; i < 4 && img.data[i]; i++)
> +        img.data[i] += (y >> ff_fmt_vshift(img.fmt, i)) * img.linesize[i];
> +    return img;
> +}

I find it weird to pass the struct itself as an argument. The previous
version took a const * and made the copy itself. The new version uses
a dereference to make a copy at the call site. The compiler probably
optimizes both down to the same binary, since the function is inline.

Either are fine by me btw, I just wanted to point it out.
_______________________________________________
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".

  reply	other threads:[~2025-05-16 15:42 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-26 17:41 [FFmpeg-devel] [PATCH 00/17] swscale v2: new framework [RFC] Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 01/17] tests/swscale: improve colorization of speedup Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 02/17] swscale/graph: expose ff_sws_graph_add_pass Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 03/17] swscale/graph: make noop loop more robust Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 04/17] swscale/graph: move vshift() and shift_img() to shared header Niklas Haas
2025-05-16 15:41   ` Ramiro Polla [this message]
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 05/17] swscale/graph: prefer bools to ints Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 06/17] doc: add swscale rewrite design document Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 07/17] swscale: add SWS_EXPERIMENTAL flag Niklas Haas
2025-05-08 11:37   ` Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 08/17] swscale/ops: introduce new low level framework Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 09/17] swscale/ops_chain: add internal abstraction for kernel linking Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 10/17] swscale/ops_backend: add reference backend basend on C templates Niklas Haas
2025-05-02 15:06   ` Michael Niedermayer
2025-05-08 12:24     ` Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 11/17] swscale/x86: add SIMD backend Niklas Haas
2025-04-29 13:00   ` Michael Niedermayer
2025-04-30 16:24     ` Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 12/17] tests/checkasm: increase number of runs in between measurements Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 13/17] tests/checkasm: add checkasm_check_float Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 14/17] tests/checkasm: add checkasm tests for swscale ops Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 15/17] swscale/format: rename legacy format conversion table Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 16/17] swscale/format: add new format decode/encode logic Niklas Haas
2025-05-02 14:10   ` Michael Niedermayer
2025-05-02 14:36     ` Niklas Haas
2025-04-26 17:41 ` [FFmpeg-devel] [PATCH 17/17] swscale/graph: allow experimental use of new format handler Niklas Haas
2025-04-26 22:22 ` [FFmpeg-devel] [PATCH 00/17] swscale v2: new framework [RFC] Niklas Haas
2025-05-02 17:51 ` Niklas Haas
2025-05-16 11:09 ` Niklas Haas
2025-05-16 14:32   ` Ramiro Polla
2025-05-16 14:39     ` Niklas Haas
2025-05-16 15:44       ` Ramiro Polla

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CALweWgC_WGdTGZmWpUroYjXzafets79dqbRddXWkBDijyOOKrQ@mail.gmail.com \
    --to=ramiro.polla@gmail.com \
    --cc=ffmpeg-devel@ffmpeg.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

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