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: lift sample peak calculation out of main loop

Browse Source 
This is substantially faster (~55%) than the transposed loop, and also
avoids an unnecessary macro.
This commit is contained in:
Niklas Haas
2025-06-13 17:00:50 +02:00
parent 229393d8dc
commit f362bacd27
1 changed files with 18 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
libavfilter/f_ebur128.c
View File

@ -687,6 +687,24 @@ static int filter_frame(AVFilterLink *inlink, AVFrame *insamples)
}
#endif
if (ebur128->peak_mode & PEAK_MODE_SAMPLES_PEAKS) {
double maxpeak = 0.0;
for (int ch = 0; ch < nb_channels; ch++) {
const double *restrict samples_ch = &samples[ch];
double sp = ebur128->sample_peaks[ch];
for (int i = ebur128->idx_insample; i < nb_samples; i++) {
const double sample = fabs(samples_ch[nb_channels * i]);
sp = FFMAX(sp, sample);
}
maxpeak = FFMAX(maxpeak, sp);
ebur128->sample_peaks[ch] = sp;
}
ebur128->sample_peak = DBFS(maxpeak);
}
for (idx_insample = ebur128->idx_insample; idx_insample < nb_samples; idx_insample++) {
const int bin_id_400 = ebur128->i400.cache_pos++;
const int bin_id_3000 = ebur128->i3000.cache_pos++;
@ -707,26 +725,6 @@ static int filter_frame(AVFilterLink *inlink, AVFrame *insamples)
ebur128->i400.sum, ebur128->i3000.sum,
nb_channels);
#define FIND_PEAK(global, sp, ptype) do { \
int ch; \
double maxpeak; \
maxpeak = 0.0; \
if (ebur128->peak_mode & PEAK_MODE_ ## ptype ## _PEAKS) { \
for (ch = 0; ch < ebur128->nb_channels; ch++) \
maxpeak = FFMAX(maxpeak, sp[ch]); \
global = DBFS(maxpeak); \
} \
} while (0)
if (ebur128->peak_mode & PEAK_MODE_SAMPLES_PEAKS) {
for (ch = 0; ch < nb_channels; ch++) {
const double sample = samples[idx_insample * nb_channels + ch];
ebur128->sample_peaks[ch] = FFMAX(ebur128->sample_peaks[ch], fabs(sample));
}
}
FIND_PEAK(ebur128->sample_peak, ebur128->sample_peaks, SAMPLES);
/* For integrated loudness, gating blocks are 400ms long with 75%
* overlap (see BS.1770-2 p5), so a re-computation is needed each 100ms
* (4800 samples at 48kHz). */