Commit c8780822 authored by Ganesh Ajjanagadde's avatar Ganesh Ajjanagadde

swresample/resample: speed up build_filter for Blackman-Nuttall filter

This uses the trigonometric double and triple angle formulae to avoid
repeated (expensive) evaluation of libc's cos().

Sample benchmark (x86-64, Haswell, GNU/Linux)
test: fate-swr-resample-dblp-44100-2626
old:
1104466600 decicycles in build_filter(loop 1000),     256 runs,      0 skips
1096765286 decicycles in build_filter(loop 1000),     512 runs,      0 skips
1070479590 decicycles in build_filter(loop 1000),    1024 runs,      0 skips

new:
588861423 decicycles in build_filter(loop 1000),     256 runs,      0 skips
591262754 decicycles in build_filter(loop 1000),     512 runs,      0 skips
577355145 decicycles in build_filter(loop 1000),    1024 runs,      0 skips

This results in small differences with the old expression:
difference (worst case on [0, 2*M_PI]), argmax 0.008:
max diff (relative): 0.000000000000157289807188
blackman_old(0.008): 0.000363951585488813192382
blackman_new(0.008): 0.000363951585488755946507

These are judged to be insignificant for the performance gain. PSNR to
reference file is unchanged up to second decimal point for instance.
Reviewed-by: 's avatarMichael Niedermayer <michael@niedermayer.cc>
Signed-off-by: 's avatarGanesh Ajjanagadde <gajjanagadde@gmail.com>
parent 7d6a4797
......@@ -73,7 +73,7 @@ static double bessel(double x){
static int build_filter(ResampleContext *c, void *filter, double factor, int tap_count, int alloc, int phase_count, int scale,
int filter_type, int kaiser_beta){
int ph, i;
double x, y, w;
double x, y, w, t;
double *tab = av_malloc_array(tap_count+1, sizeof(*tab));
const int center= (tap_count-1)/2;
......@@ -100,7 +100,8 @@ static int build_filter(ResampleContext *c, void *filter, double factor, int tap
break;}
case SWR_FILTER_TYPE_BLACKMAN_NUTTALL:
w = 2.0*x / (factor*tap_count) + M_PI;
y *= 0.3635819 - 0.4891775 * cos(w) + 0.1365995 * cos(2*w) - 0.0106411 * cos(3*w);
t = cos(w);
y *= 0.3635819 - 0.4891775 * t + 0.1365995 * (2*t*t-1) - 0.0106411 * (4*t*t*t - 3*t);
break;
case SWR_FILTER_TYPE_KAISER:
w = 2.0*x / (factor*tap_count*M_PI);
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment