[FFmpeg-devel] [PATCH v2 09/13] avfilter/f_ebur128: move true peak calculation out of main loop
Niklas Haas
ffmpeg at haasn.xyz
Fri Jun 13 19:37:52 EEST 2025
From: Niklas Haas <git at haasn.dev>
Easier to read, less convoluted, and ~30% faster. Most importantly, this
avoids repeating the redundant recalculation of the true peak on every single
sample, by moving the FIND_PEAK() loop out of the main loop. (Note that
FIND_PEAK() does not depend on the current sample index at all, so there is no
reason for it to ever be recomputed here)
---
libavfilter/f_ebur128.c | 23 ++++++++++++++---------
1 file changed, 14 insertions(+), 9 deletions(-)
diff --git a/libavfilter/f_ebur128.c b/libavfilter/f_ebur128.c
index 2e1eedd855..23092b597f 100644
--- a/libavfilter/f_ebur128.c
+++ b/libavfilter/f_ebur128.c
@@ -668,16 +668,22 @@ static int filter_frame(AVFilterLink *inlink, AVFrame *insamples)
(const uint8_t **)insamples->data, nb_samples);
if (ret < 0)
return ret;
- for (ch = 0; ch < nb_channels; ch++)
- ebur128->true_peaks_per_frame[ch] = 0.0;
- for (idx_insample = 0; idx_insample < ret; idx_insample++) {
- for (ch = 0; ch < nb_channels; ch++) {
- ebur128->true_peaks[ch] = FFMAX(ebur128->true_peaks[ch], fabs(*swr_samples));
- ebur128->true_peaks_per_frame[ch] = FFMAX(ebur128->true_peaks_per_frame[ch],
- fabs(*swr_samples));
- swr_samples++;
+
+ double maxpeak = 0.0;
+ for (int ch = 0; ch < nb_channels; ch++) {
+ double tp = ebur128->true_peaks[ch];
+ double tppf = 0.0;
+ for (int i = 0; i < ret; i++) {
+ const double sample = fabs(swr_samples[i * nb_channels]);
+ tp = FFMAX(tp, sample);
+ tppf = FFMAX(tppf, sample);
}
+ maxpeak = FFMAX(maxpeak, tp);
+ ebur128->true_peaks[ch] = tp;
+ ebur128->true_peaks_per_frame[ch] = tppf;
}
+
+ ebur128->true_peak = DBFS(maxpeak);
}
#endif
@@ -720,7 +726,6 @@ static int filter_frame(AVFilterLink *inlink, AVFrame *insamples)
}
FIND_PEAK(ebur128->sample_peak, ebur128->sample_peaks, SAMPLES);
- FIND_PEAK(ebur128->true_peak, ebur128->true_peaks, TRUE);
/* For integrated loudness, gating blocks are 400ms long with 75%
* overlap (see BS.1770-2 p5), so a re-computation is needed each 100ms
--
2.49.0
More information about the ffmpeg-devel
mailing list