 Jean-Marc Valin
|
ef203135b4
Adding ENABLE_HARDENING
|
6 tahun lalu |
|
Jean-Marc Valin
|
2da3721b16
Simplifying celt_fir5() since x==y and mem[]={0}
|
7 tahun lalu |
 Linfeng Zhang
|
85fb8a1d17
Replace call of celt_inner_prod_c() (step 2)
|
8 tahun lalu |
|
Linfeng Zhang
|
a1ae821c96
Replace call of celt_inner_prod_c() (step 1)
|
8 tahun lalu |
|
Jean-Marc Valin
|
3609a2218e
Fixes some fixed-point 16-bit int overflows
|
7 tahun lalu |
|
Jean-Marc Valin
|
b66080a879
Fixes minor code quality issues in CELT
|
8 tahun lalu |
|
Jean-Marc Valin
|
ddea3a6fbf
Fixes a fixed-point precision issue in remove_doubling()
|
8 tahun lalu |
 Jonathan Lennox
|
43120f0075
Reorganize x86 SSE intrinsics code.
|
9 tahun lalu |
 Timothy B. Terriberry
|
aad281878d
Fix celt_pitch_xcorr_c signature.
|
10 tahun lalu |
 xiangmingzhu
|
c95c9a048f
Cisco optimization for x86 & fixed point
|
10 tahun lalu |
|
Jean-Marc Valin
|
29354ff6e0
Save more integer divisions on ARM when we know the operands are positive
|
11 tahun lalu |
 Gregory Maxwell
|
a65db56e54
Fix declaration after statement in fixed point.
|
11 tahun lalu |
|
Jean-Marc Valin
|
57cd849cf7
Defining celt_inner_prod() and using it instead of explicit loops.
|
11 tahun lalu |
|
Timothy B. Terriberry
|
5c02c5ffb5
Make celt_pitch_xcorr_edsp() work on ARMv5TE.
|
11 tahun lalu |
|
Timothy B. Terriberry
|
39386e0b85
Adds Neon assembly for correlation/convolution
|
11 tahun lalu |
|
Jean-Marc Valin
|
a156c5ece7
Makes the SILK pitch search use celt_pitch_xcorr()
|
11 tahun lalu |
|
Jean-Marc Valin
|
b9176a4c3e
Makes dual_inner_prod() more generic to increase its use
|
11 tahun lalu |
|
Jean-Marc Valin
|
71766ef7a4
Avoids symbol clashes with Speex (pitch_xcorr) and libm (y1)
|
11 tahun lalu |
|
Jean-Marc Valin
|
4e018b22bb
SSE optimization of remove_doubling()
|
11 tahun lalu |
|
Jean-Marc Valin
|
068cbd89bf
Creates xcorr_kernel() that gets used by pitch_xcorr, celt_fir and celt_iir.
|
11 tahun lalu |
|
Jean-Marc Valin
|
319fe445e3
oops (again)
|
11 tahun lalu |
|
Jean-Marc Valin
|
1cdc3f5a2d
oops
|
11 tahun lalu |
|
Jean-Marc Valin
|
64ba502e2c
Optimizes remove_doubling() by avoiding redundant calculations of yy
|
11 tahun lalu |
|
Jean-Marc Valin
|
319df9a836
Fixes two warnings in pitch_xcorr()
|
11 tahun lalu |
|
Jean-Marc Valin
|
e8e57a32f6
Optimizes _celt_autocorr() by using pitch_xcorr()
|
11 tahun lalu |
|
Jean-Marc Valin
|
fbf99981a6
Merges the 4th order FIR with the first order FIR in pitch_downsample()
|
11 tahun lalu |
|
Jean-Marc Valin
|
85a6618af8
Make pitch_xcorr() work when len and max_pitch aren't multiples of 4.
|
11 tahun lalu |
|
Jean-Marc Valin
|
088929d1f1
oops, removed a minus sign that should never have appeared
|
11 tahun lalu |
|
Jean-Marc Valin
|
559fbe8b16
Unrolled version of the pitch correlation
|
11 tahun lalu |
|
Jean-Marc Valin
|
b7bd4c20ac
celt_maxabs16() now returns an opus_val32 to avoid problems with -32768
|
11 tahun lalu |
