1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-23 12:43:46 +02:00

aac: avoid a memcpy in sbr_qmf_analysis

Swapping buffer indices allows saving one memcpy that accounts for 1% of the
runtime, according to oprofile.

Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
This commit is contained in:
Christophe Gisquet 2012-11-28 22:47:25 +01:00 committed by Luca Barbato
parent 7e9e7cc236
commit e32bea8eb4

View File

@ -1153,10 +1153,9 @@ static void sbr_dequant(SpectralBandReplication *sbr, int id_aac)
*/ */
static void sbr_qmf_analysis(DSPContext *dsp, FFTContext *mdct, static void sbr_qmf_analysis(DSPContext *dsp, FFTContext *mdct,
SBRDSPContext *sbrdsp, const float *in, float *x, SBRDSPContext *sbrdsp, const float *in, float *x,
float z[320], float W[2][32][32][2]) float z[320], float W[2][32][32][2], int buf_idx)
{ {
int i; int i;
memcpy(W[0], W[1], sizeof(W[0]));
memcpy(x , x+1024, (320-32)*sizeof(x[0])); memcpy(x , x+1024, (320-32)*sizeof(x[0]));
memcpy(x+288, in, 1024*sizeof(x[0])); memcpy(x+288, in, 1024*sizeof(x[0]));
for (i = 0; i < 32; i++) { // numTimeSlots*RATE = 16*2 as 960 sample frames for (i = 0; i < 32; i++) { // numTimeSlots*RATE = 16*2 as 960 sample frames
@ -1165,7 +1164,7 @@ static void sbr_qmf_analysis(DSPContext *dsp, FFTContext *mdct,
sbrdsp->sum64x5(z); sbrdsp->sum64x5(z);
sbrdsp->qmf_pre_shuffle(z); sbrdsp->qmf_pre_shuffle(z);
mdct->imdct_half(mdct, z, z+64); mdct->imdct_half(mdct, z, z+64);
sbrdsp->qmf_post_shuffle(W[1][i], z); sbrdsp->qmf_post_shuffle(W[buf_idx][i], z);
x += 32; x += 32;
} }
} }
@ -1301,7 +1300,8 @@ static void sbr_chirp(SpectralBandReplication *sbr, SBRData *ch_data)
/// Generate the subband filtered lowband /// Generate the subband filtered lowband
static int sbr_lf_gen(AACContext *ac, SpectralBandReplication *sbr, static int sbr_lf_gen(AACContext *ac, SpectralBandReplication *sbr,
float X_low[32][40][2], const float W[2][32][32][2]) float X_low[32][40][2], const float W[2][32][32][2],
int buf_idx)
{ {
int i, k; int i, k;
const int t_HFGen = 8; const int t_HFGen = 8;
@ -1309,14 +1309,15 @@ static int sbr_lf_gen(AACContext *ac, SpectralBandReplication *sbr,
memset(X_low, 0, 32*sizeof(*X_low)); memset(X_low, 0, 32*sizeof(*X_low));
for (k = 0; k < sbr->kx[1]; k++) { for (k = 0; k < sbr->kx[1]; k++) {
for (i = t_HFGen; i < i_f + t_HFGen; i++) { for (i = t_HFGen; i < i_f + t_HFGen; i++) {
X_low[k][i][0] = W[1][i - t_HFGen][k][0]; X_low[k][i][0] = W[buf_idx][i - t_HFGen][k][0];
X_low[k][i][1] = W[1][i - t_HFGen][k][1]; X_low[k][i][1] = W[buf_idx][i - t_HFGen][k][1];
} }
} }
buf_idx = 1-buf_idx;
for (k = 0; k < sbr->kx[0]; k++) { for (k = 0; k < sbr->kx[0]; k++) {
for (i = 0; i < t_HFGen; i++) { for (i = 0; i < t_HFGen; i++) {
X_low[k][i][0] = W[0][i + i_f - t_HFGen][k][0]; X_low[k][i][0] = W[buf_idx][i + i_f - t_HFGen][k][0];
X_low[k][i][1] = W[0][i + i_f - t_HFGen][k][1]; X_low[k][i][1] = W[buf_idx][i + i_f - t_HFGen][k][1];
} }
} }
return 0; return 0;
@ -1665,8 +1666,8 @@ void ff_sbr_apply(AACContext *ac, SpectralBandReplication *sbr, int id_aac,
/* decode channel */ /* decode channel */
sbr_qmf_analysis(&ac->dsp, &sbr->mdct_ana, &sbr->dsp, ch ? R : L, sbr->data[ch].analysis_filterbank_samples, sbr_qmf_analysis(&ac->dsp, &sbr->mdct_ana, &sbr->dsp, ch ? R : L, sbr->data[ch].analysis_filterbank_samples,
(float*)sbr->qmf_filter_scratch, (float*)sbr->qmf_filter_scratch,
sbr->data[ch].W); sbr->data[ch].W, sbr->data[ch].Ypos);
sbr_lf_gen(ac, sbr, sbr->X_low, sbr->data[ch].W); sbr_lf_gen(ac, sbr, sbr->X_low, sbr->data[ch].W, sbr->data[ch].Ypos);
sbr->data[ch].Ypos ^= 1; sbr->data[ch].Ypos ^= 1;
if (sbr->start) { if (sbr->start) {
sbr_hf_inverse_filter(&sbr->dsp, sbr->alpha0, sbr->alpha1, sbr->X_low, sbr->k[0]); sbr_hf_inverse_filter(&sbr->dsp, sbr->alpha0, sbr->alpha1, sbr->X_low, sbr->k[0]);