virtualenv/FFmpeg
1
0
Fork 0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2025-08-04 22:03:09 +02:00
Code Issues Releases Activity

avfilter/f_ebur128: move true peak calculation out of main loop

Browse Source 
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)
This commit is contained in:
Niklas Haas
2025-06-13 16:54:27 +02:00
parent a96175e76f
commit 229393d8dc
1 changed files with 14 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
libavfilter/f_ebur128.c
View File

@ -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