Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
 help / color / mirror / Atom feed
From: Niklas Haas <ffmpeg@haasn.xyz>
To: ffmpeg-devel@ffmpeg.org
Cc: Niklas Haas <git@haasn.dev>
Subject: Re: [FFmpeg-devel] [PATCH v4 13/13] avfilter/x86/f_ebur128: implement AVX true peak calculation
Date: Tue, 17 Jun 2025 15:48:40 +0200
Message-ID: <20250617154840.GB2472956@haasn.xyz> (raw)
In-Reply-To: <20250617120609.1987435-13-ffmpeg@haasn.xyz>

On Tue, 17 Jun 2025 14:06:06 +0200 Niklas Haas <ffmpeg@haasn.xyz> wrote:
> From: Niklas Haas <git@haasn.dev>
>
> Stereo only, for simplicity. Slightly faster than the C code.

I will drop this and the prior commit and resubmit them in a refactored form
that also speeds up the sample peak calculation.

In the meantime, I would appreciate a review of the rest.

> ---
>  libavfilter/f_ebur128.c          |  8 +++-----
>  libavfilter/f_ebur128.h          |  2 +-
>  libavfilter/x86/f_ebur128.asm    | 25 +++++++++++++++++++++++++
>  libavfilter/x86/f_ebur128_init.c |  9 +++++++--
>  4 files changed, 36 insertions(+), 8 deletions(-)
>
> diff --git a/libavfilter/f_ebur128.c b/libavfilter/f_ebur128.c
> index 0adc89c823..c64f6ed032 100644
> --- a/libavfilter/f_ebur128.c
> +++ b/libavfilter/f_ebur128.c
> @@ -502,6 +502,9 @@ static int config_audio_output(AVFilterLink *outlink)
>              return AVERROR(ENOMEM);
>      }
>
> +#if ARCH_X86
> +    ff_ebur128_init_x86(&ebur128->dsp, nb_channels);
> +#endif
>      return 0;
>  }
>
> @@ -581,11 +584,6 @@ static av_cold int init(AVFilterContext *ctx)
>
>      ebur128->dsp.filter_channels = ff_ebur128_filter_channels_c;
>      ebur128->dsp.true_peak = ff_ebur128_true_peak_c;
> -
> -#if ARCH_X86
> -    ff_ebur128_init_x86(&ebur128->dsp);
> -#endif
> -
>      return 0;
>  }
>
> diff --git a/libavfilter/f_ebur128.h b/libavfilter/f_ebur128.h
> index 8aab7838a0..5fb9d4a8d5 100644
> --- a/libavfilter/f_ebur128.h
> +++ b/libavfilter/f_ebur128.h
> @@ -53,7 +53,7 @@ static_assert(offsetof(EBUR128DSPContext, pre) == 0,                   "struct l
>  static_assert(offsetof(EBUR128DSPContext, rlb) == 5  * sizeof(double), "struct layout mismatch");
>  static_assert(offsetof(EBUR128DSPContext, y)   == 10 * sizeof(double), "struct layout mismatch");
>
> -void ff_ebur128_init_x86(EBUR128DSPContext *dsp);
> +void ff_ebur128_init_x86(EBUR128DSPContext *dsp, int nb_channels);
>
>  void ff_ebur128_filter_channels_c(const EBUR128DSPContext *, const double *,
>                                    double *, double *, double *, double *, int);
> diff --git a/libavfilter/x86/f_ebur128.asm b/libavfilter/x86/f_ebur128.asm
> index d9cc8d9361..53dd3f858d 100644
> --- a/libavfilter/x86/f_ebur128.asm
> +++ b/libavfilter/x86/f_ebur128.asm
> @@ -39,6 +39,10 @@ struc DSP
>      .z resq 1
>  endstruc
>
> +SECTION_RODATA
> +
> +abs_mask: dq 0x7FFFFFFFFFFFFFFF
> +
>  SECTION .text
>
>  %macro MOVNQ 3 ; num, dst, src
> @@ -139,3 +143,24 @@ cglobal ebur128_filter_channels, 7, 9, 14, dsp, samples, cache400, cache3000, su
>      test channelsd, channelsd
>      jnz .loop
>      RET
> +
> +cglobal ebur128_true_peak_stereo, 5, 6, 4, tp, tppf, channels, samples, nb_samples
> +    vpbroadcastq m4, [abs_mask]
> +    pxor m0, m0      ; maxpeak
> +    movupd m1, [tpq] ; tp
> +    pxor m2, m2      ; tppf
> +.inner:
> +    movupd m3, [samplesq]
> +    add samplesq, 16
> +    pand m3, m4
> +    maxpd m1, m3
> +    maxpd m2, m3
> +    dec nb_samplesd
> +    jg .inner
> +    movupd [tpq],  m1
> +    movupd [tppfq], m2
> +    maxpd m0, m1
> +    shufpd m1, m0, m0, 1
> +    maxpd m0, m1
> +    movq rax, m0
> +    RET
> diff --git a/libavfilter/x86/f_ebur128_init.c b/libavfilter/x86/f_ebur128_init.c
> index 8f38aee967..527e5e4dbc 100644
> --- a/libavfilter/x86/f_ebur128_init.c
> +++ b/libavfilter/x86/f_ebur128_init.c
> @@ -26,10 +26,15 @@
>  void ff_ebur128_filter_channels_avx(const EBUR128DSPContext *, const double *,
>                                      double *, double *, double *, double *, int);
>
> -av_cold void ff_ebur128_init_x86(EBUR128DSPContext *dsp)
> +double ff_ebur128_true_peak_stereo_avx(double *, double *, int, const double *, int);
> +
> +av_cold void ff_ebur128_init_x86(EBUR128DSPContext *dsp, int nb_channels)
>  {
>      int cpu_flags = av_get_cpu_flags();
>
> -    if (ARCH_X86_64 && EXTERNAL_AVX(cpu_flags))
> +    if (ARCH_X86_64 && EXTERNAL_AVX(cpu_flags)) {
>          dsp->filter_channels = ff_ebur128_filter_channels_avx;
> +        if (nb_channels == 2)
> +            dsp->true_peak = ff_ebur128_true_peak_stereo_avx;
> +    }
>  }
> --
> 2.49.0
>
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

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

      reply	other threads:[~2025-06-17 13:48 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-17 12:05 [FFmpeg-devel] [PATCH v4 01/13] avfilter/f_ebur128: use transformed direct form II Niklas Haas
2025-06-17 12:05 ` [FFmpeg-devel] [PATCH v4 02/13] avfilter/f_ebur128: simplify sample cache array Niklas Haas
2025-06-17 12:05 ` [FFmpeg-devel] [PATCH v4 03/13] avfilter/f_ebur128: use structs for biquad weights Niklas Haas
2025-06-17 12:05 ` [FFmpeg-devel] [PATCH v4 04/13] avfilter/f_ebur128: use a single packed array for the integrator cache Niklas Haas
2025-06-17 12:05 ` [FFmpeg-devel] [PATCH v4 05/13] avfilter/f_ebur128: move weights and cache to EBUR128DSPContext Niklas Haas
2025-06-17 12:05 ` [FFmpeg-devel] [PATCH v4 06/13] avfilter/f_ebur128: split off C implementation to separate function Niklas Haas
2025-06-17 12:06 ` [FFmpeg-devel] [PATCH v4 07/13] avfilter/x86/f_ebur128: add x86 AVX implementation Niklas Haas
2025-06-17 12:06 ` [FFmpeg-devel] [PATCH v4 08/13] avfilter/f_ebur128: remove pointless macro Niklas Haas
2025-06-17 12:06 ` [FFmpeg-devel] [PATCH v4 09/13] avfilter/f_ebur128: move true peak calculation out of main loop Niklas Haas
2025-06-17 12:06 ` [FFmpeg-devel] [PATCH v4 10/13] avfilter/f_ebur128: lift sample " Niklas Haas
2025-06-17 12:06 ` [FFmpeg-devel] [PATCH v4 11/13] avfilter/f_ebur128: move variable declarations to usage site Niklas Haas
2025-06-17 12:06 ` [FFmpeg-devel] [PATCH v4 12/13] avfilter/f_ebur128: move true peak calculation to DSP function Niklas Haas
2025-06-17 12:06 ` [FFmpeg-devel] [PATCH v4 13/13] avfilter/x86/f_ebur128: implement AVX true peak calculation Niklas Haas
2025-06-17 13:48   ` Niklas Haas [this message]

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=20250617154840.GB2472956@haasn.xyz \
    --to=ffmpeg@haasn.xyz \
    --cc=ffmpeg-devel@ffmpeg.org \
    --cc=git@haasn.dev \
    /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