shithub: opus

c7bfc72d – Michael Klingbeil <klingm@amazon.com> authored on 2023/11/29 16:40

use vec_avx.h for MSVC builds

8090aaca – Michael Klingbeil <klingm@amazon.com> authored on 2023/11/29 15:02

don't redefine _mm_loadu_si32 on MSVC

88fc2937 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/29 13:17

Defining __SSEx__ macros when needed for MSVC

f126bfc5 – Michael Klingbeil <klingm@amazon.com> authored on 2023/11/29 08:38

fix autogen.bat model download

0d823c13 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/28 21:50

Add a script to shrink the DNN models

443510c2 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2023/11/28 18:49

Fix Windows path

55788242 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2023/11/28 18:39

Fix model download path for windows

ddfa4804 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2023/11/28 18:32

Opus github ci files

08eefed7 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/28 18:18

Add dotprod support to meson

c28b0f10 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2023/11/28 14:14

Trying to fix/update meson build

147b7229 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/28 10:34

Oops, fix the fixed-point build

db26e381 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/28 09:16

Trying to use fma instructions when possible

72cc88df – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/27 23:11

FARGAN model update

df637713 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/27 17:57

Fixes for ARMv7/AArch32

c143b72c – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/27 13:08

Enabling DNN optimizations for ARMv7

ee1bb69f – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/27 12:55

Only force auto-vectorization for GCC >= 5.1

7cc30ec6 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/27 11:44

Force vectorization for DNN primitives

d4506af5 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/27 10:41

Enable floating-point approximations by default

db6dad44 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/26 17:21

Fix ARMv7 optimizations for DNN code

cc11c078 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/25 22:36

First step towards DNN optimization for ARMv7 Neon

c9af8f80 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/25 22:16

Fix potential read out of bounds in fargan

5c3795b2 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/22 14:05

Adding dotprod instruction to ARM rtcd

984f35b3 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/24 13:28

Speed up cross-correlation normalization

d65b7de3 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/24 13:08

Use arch-specific celt_inner_prod() for features

ddbdbec4 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/24 13:02

Optimize biquad() to reduce dependency chains

176507e4 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/24 08:33

Remove process_single_frame()

9d0425d8 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/24 08:23

Remove feature writing (fwrite()) from libopus

f5821193 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2023/11/21 11:59

Using the same condition for enabling rtcd

3e18d967 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2023/11/21 11:13

Trying to fix CMake build

239d223d – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/20 21:56

Add rtcd for silk_inner_product_FLP()

b93e4a14 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/20 21:13

Start enabling AVX2 silk_inner_product_FLP()

ed900603 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/20 20:26

Avoids AVX2 optimizations being disabled

c066af1b – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/20 20:13

Use SILK VBR when using CBR with DRED

6f99a338 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/17 20:39

Misc fixes on previous patch

735c4070 – Victor Ding <victording@google.com> authored and Jean-Marc Valin <jmvalin@amazon.com> committed on 2023/11/17 18:58

Optimize NSQ_del_dec() for AVX2

452aa952 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/20 12:53

AVX2 version of silk_inner_product_FLP()

10851260 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/20 11:18

Remove AVX pitch code for fixed-point

161358d6 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/20 11:12

Speeding up transient_analysis()

f42940be – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/20 09:13

Make sure weights files are marked as modified

d4b04d32 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/17 18:10

Speed up silk_warped_autocorrelation_FLP()

b2cfd877 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/17 14:36

Add rtcd support for celt_pitch_xcorr_avx2()

02938546 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/17 13:08

Fix non-RTCD case when SSE is not assumed present

7423ce59 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/17 11:59

Use celt_pitch_xcorr_avx2() when guaranteed

a93b09e2 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/17 09:14

Adding RTCD for compute_conv2d()

91d1f753 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/16 07:45

FARGAN model update

7f7b2a1c – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/15 07:58

Smaller version of fargan

19a5d6ec – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/15 20:27

Remove C99 comment

4bfc0f85 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/14 12:54

Adding RTCD for compute_activation()

2e034f6f – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/13 13:26

Adding RTCD for DNN code

b0620c0b – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/14 23:08

Using sparse GRUs in DRED decoder

58923f61 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2023/11/10 22:22

Fix non-AVX builds

77594bf1 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/08 12:32

Dumping RDOVAE stats from XML

222662da – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/07 12:46

DRED: quantize scale and dead zone to 8 bits

4e104555 – Jan Buethe <jbuethe@amazon.de> authored on 2023/11/07 10:12

added weight export script for LACE/NoLACE

8af5c6b4 – Jan Buethe <jbuethe@amazon.de> authored on 2023/11/07 06:54

added transposed 1d convolutions to wexchange

b6095cf2 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/06 21:52

DRED code cleanup

0ab0640d – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/06 12:49

Split stats in two and remove useless dimensions

2386a60e – Jan Buethe <jbuethe@amazon.de> authored on 2023/11/06 12:50

updated moc to match results in ietf118 presentation

544b3e57 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/05 22:10

DRED: quantize r and p0 parameters with 8 bits

98b8be09 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/03 13:28

Vectorize DRED quantization

fa5e960c – Felicia Lim <flim@google.com> authored and Jean-Marc Valin <jmvalin@jmvalin.ca> committed on 2023/11/03 10:53

Match silenced overflow checks in the sse4.1 version

cfeddc49 – Felicia Lim <flim@google.com> authored and Jean-Marc Valin <jmvalin@amazon.com> committed on 2023/10/20 09:24

Silence some overflow checks

1ada7d4d – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/11/02 22:46

Vectorizing sgemv for multiples of 4 with SSE

166a6c8e – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/30 22:14

Fix silly bug in CELT Deep PLC

74c67a8d – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/30 13:14

Fix CELT PLC for single packet between losses

da60266f – Jan Buethe <jbuethe@amazon.de> authored on 2023/11/02 12:52

updated moc method

feb32828 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/30 10:08

Don't try to use models that aren't loaded

62b54643 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/29 20:08

Speed up general case for float matrix multiply

61fb3b16 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2023/10/29 17:19

Don't use reserved identifiers for include guards

d53531d0 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/29 12:33

Update blob loading code

0b755012 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/28 22:38

Use log approximation when possible

4259d354 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/28 22:20

Reusing already-optimized celt_fir()

b22b11a4 – Jean-Marc Valin <jmvalin@jmvalin.ca> authored on 2023/10/28 20:12

Silence some warnings

ddd5669e – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/28 19:33

Pitch and fargan model updates

c99054da – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/26 21:29

Fix CELT deep PLC bugs

ccb244a7 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/24 05:27

cleanup

bc102f5f – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/24 05:19

Slightly more continuous analysis

64236e52 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/20 22:26

Removing more useless code

ef8115bd – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/20 18:07

Stop using tansig_table.h (both copies)

a30c96aa – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/20 17:31

Cleanup

88c58cfa – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/20 13:08

nnet.h no longer needs to #include "vec.h"

1032e47d – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/20 11:12

more cleanup

7f0d456c – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/20 11:05

Remove unneeded functions in nnet.c

4598fe54 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/20 08:54

Quantizing pitchdnn and rdovae weights

290be25b – Jan Buethe <jbuethe@amazon.de> authored on 2023/10/20 10:24

added 16kHz version of opus_compare in python

1accd247 – Jan Buethe <jbuethe@amazon.de> authored on 2023/10/20 10:14

finalized quantization option in export_rdovae_weights.py

88c8b307 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/19 23:28

Doing some unrolling on ARM/Neon

f512c920 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/19 21:33

Unroll the 3x3 convolution case

d720955d – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/19 12:06

Marking RDOVAE layers to quantize

60ac1c6c – Jan Buethe <jbuethe@amazon.de> authored on 2023/10/19 17:54

prepared quantization implementation for DRED

2192e85b – Jan Buethe <jbuethe@amazon.de> authored on 2023/10/19 17:45

restructured osce readme

055c6830 – Jan Buethe <jbuethe@amazon.de> authored on 2023/10/19 17:34

added LACE/NoLACE checkpoint URL

8d43b185 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/18 13:40

Support OPUS_SET_COMPLEXITY() on decoder side

000af034 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/18 09:00

Avoiding work on the PLC update side

d1309dd2 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/17 22:56

Simplifying the DRED/PLC code

8c7c03e5 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/17 21:44

Don't call the libm tanh()

0e397a72 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/17 20:43

Making the build possible without the models

aca04ce2 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/16 21:52

Default to int8 matrix multiplies when available

f82f9d1e – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/16 19:10

oops

e51d3da9 – Jean-Marc Valin <jmvalin@amazon.com> authored on 2023/10/16 19:01

Fix tests