summaryrefslogtreecommitdiff
path: root/libavcodec/aacenc_ltp.c
diff options
context:
space:
mode:
authorRostislav Pehlivanov <atomnuker@gmail.com>2016-10-08 15:59:14 +0100
committerRostislav Pehlivanov <atomnuker@gmail.com>2016-10-18 21:41:18 +0100
commitd2ae5f77c61a29c3c63cc4c41c74ccfca4167649 (patch)
treebd615f22e6807e025da052c411e12e9a7be0852e /libavcodec/aacenc_ltp.c
parent3b02f6dd7be880fd6c1bcaf2fd0c1314dcee7aa6 (diff)
downloadffmpeg-d2ae5f77c61a29c3c63cc4c41c74ccfca4167649.tar.gz
aacenc: add SIMD optimizations for abs_pow34 and quantization
Performance improvements: quant_bands: with: 681 decicycles in quant_bands, 8388453 runs, 155 skips without: 1190 decicycles in quant_bands, 8388386 runs, 222 skips Around 42% for the function Twoloop coder: abs_pow34: with/without: 7.82s/8.17s Around 4% for the entire encoder Both: with/without: 7.15s/8.17s Around 12% for the entire encoder Fast coder: abs_pow34: with/without: 3.40s/3.77s Around 10% for the entire encoder Both: with/without: 3.02s/3.77s Around 20% faster for the entire encoder Signed-off-by: Rostislav Pehlivanov <atomnuker@gmail.com> Tested-by: Michael Niedermayer <michael@niedermayer.cc> Reviewed-by: James Almer <jamrial@gmail.com>
Diffstat (limited to 'libavcodec/aacenc_ltp.c')
-rw-r--r--libavcodec/aacenc_ltp.c4
1 files changed, 2 insertions, 2 deletions
diff --git a/libavcodec/aacenc_ltp.c b/libavcodec/aacenc_ltp.c
index b9d43b470a..1bec85b9e3 100644
--- a/libavcodec/aacenc_ltp.c
+++ b/libavcodec/aacenc_ltp.c
@@ -190,8 +190,8 @@ void ff_aac_search_for_ltp(AACEncContext *s, SingleChannelElement *sce,
FFPsyBand *band = &s->psy.ch[s->cur_channel].psy_bands[(w+w2)*16+g];
for (i = 0; i < sce->ics.swb_sizes[g]; i++)
PCD[i] = sce->coeffs[start+(w+w2)*128+i] - sce->lcoeffs[start+(w+w2)*128+i];
- abs_pow34_v(C34, &sce->coeffs[start+(w+w2)*128], sce->ics.swb_sizes[g]);
- abs_pow34_v(PCD34, PCD, sce->ics.swb_sizes[g]);
+ s->abs_pow34(C34, &sce->coeffs[start+(w+w2)*128], sce->ics.swb_sizes[g]);
+ s->abs_pow34(PCD34, PCD, sce->ics.swb_sizes[g]);
dist1 += quantize_band_cost(s, &sce->coeffs[start+(w+w2)*128], C34, sce->ics.swb_sizes[g],
sce->sf_idx[(w+w2)*16+g], sce->band_type[(w+w2)*16+g],
s->lambda/band->threshold, INFINITY, &bits_tmp1, NULL, 0);