virtualenv/FFmpeg
1
0
Fork 0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-23 12:43:46 +02:00
Code Issues Releases Activity

sbrdsp: Unroll sbr_autocorrelate_c

Browse Source 
1410 cycles to 1148 on Arrandale/Win64

Signed-off-by: Diego Biurrun <diego@biurrun.de>
This commit is contained in:
Christophe Gisquet 2013-04-09 21:57:09 +00:00 committed by Diego Biurrun
parent 5a97469a4f
commit 8394d9a676
1 changed files with 25 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
libavcodec/sbrdsp.c
View File

@ -122,9 +122,34 @@ static av_always_inline void autocorrelate(const float x[40][2],
static void sbr_autocorrelate_c(const float x[40][2], float phi[3][2][2])
{
#if 0
/* This code is slower because it multiplies memory accesses.
* It is left for educational purposes and because it may offer
* a better reference for writing arch-specific DSP functions. */
autocorrelate(x, phi, 0);
autocorrelate(x, phi, 1);
autocorrelate(x, phi, 2);
#else
float real_sum2 = x[0][0] * x[2][0] + x[0][1] * x[2][1];
float imag_sum2 = x[0][0] * x[2][1] - x[0][1] * x[2][0];
float real_sum1 = 0.0f, imag_sum1 = 0.0f, real_sum0 = 0.0f;
int i;
for (i = 1; i < 38; i++) {
real_sum0 += x[i][0] * x[i ][0] + x[i][1] * x[i ][1];
real_sum1 += x[i][0] * x[i + 1][0] + x[i][1] * x[i + 1][1];
imag_sum1 += x[i][0] * x[i + 1][1] - x[i][1] * x[i + 1][0];
real_sum2 += x[i][0] * x[i + 2][0] + x[i][1] * x[i + 2][1];
imag_sum2 += x[i][0] * x[i + 2][1] - x[i][1] * x[i + 2][0];
}
phi[2 - 2][1][0] = real_sum2;
phi[2 - 2][1][1] = imag_sum2;
phi[2 ][1][0] = real_sum0 + x[ 0][0] * x[ 0][0] + x[ 0][1] * x[ 0][1];
phi[1 ][0][0] = real_sum0 + x[38][0] * x[38][0] + x[38][1] * x[38][1];
phi[2 - 1][1][0] = real_sum1 + x[ 0][0] * x[ 1][0] + x[ 0][1] * x[ 1][1];
phi[2 - 1][1][1] = imag_sum1 + x[ 0][0] * x[ 1][1] - x[ 0][1] * x[ 1][0];
phi[0 ][0][0] = real_sum1 + x[38][0] * x[39][0] + x[38][1] * x[39][1];
phi[0 ][0][1] = imag_sum1 + x[38][0] * x[39][1] - x[38][1] * x[39][0];
#endif
}
static void sbr_hf_gen_c(float (*X_high)[2], const float (*X_low)[2],