Tested on:
 - Linux/x86* with gcc
 - Android armv7 arm64 x86 x86_64 with clang
 - Windows x86 x86_64 with Visual Studio 2017
 - Windows x86 x86_64 with MinGW
 - macOS x86_64 with clang
 - iOS arm64 x86_64 with clang

Co-authored by: Nirbheek Chauhan <nirbheek@centricular.com>

https://gitlab.xiph.org/xiph/opus/-/merge_requests/13

Nirbheek Chauhan authored 4 years ago and Mark Harris committed 4 years ago

_WIN32 is defined on all Windows platforms by every compiler that
targets Windows. We do not need WIN32 at all.

Signed-off-by: Mark Harris <mark.hsj@gmail.com>
Resolves https://github.com/xiph/opus/pull/104

Nirbheek Chauhan authored 4 years ago and Mark Harris committed 4 years ago

Signed-off-by: Mark Harris <mark.hsj@gmail.com>

Marcus Asteborg authored 4 years ago and Jean-Marc Valin committed 4 years ago

Build time improvement, for MSVC use intrin0.h instead of intrin.h and remove usage of stdio.h in production code

Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>

Marcus Asteborg authored 4 years ago and Jean-Marc Valin committed 4 years ago

Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>

Jesús de Vicente Peña authored 5 years ago and Felicia Lim committed 5 years ago

This reverts commit 4f5557c3.

Signed-off-by: Felicia Lim <flim@google.com>

Thanks to Ray Essick

Broken by earlier ARM optimizations.

or "just" 1 year and 4 months for 10-ms frames.
The overflow can eventually cause a divide-by-zero when counter == -16

Thanks to Dmitry Malinin for reporting the bug.

clang -Wcast-align warnings with ambisonics enabled
clang -Wnull-pointer-arithmetic warnings in test_opus_api.c
gcc -Wimplicit-fallthrough warnings on arm
msvc warning C4244 in celt_encoder.c with fixed point

The bug was triggered because f982b84d started using prefill for
SILK bandwidth changes, which reinitialized the encoder state and
prevented the variable lowpass from working properly. To fix the problem,
we preserve the sampling rate and variable low-pass when prefilling.

Using a finer table for the rate to SNR curves in silk_control_SNR().
It's now possible to have an SNR that reaches 0, so we can lower bitrate
down to ~5 kbps for narrowband and 5.5 kbps for wideband.

Gustaf Ullberg authored 7 years ago and Jean-Marc Valin committed 6 years ago

Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>

Only converted the ones that are really sure (not signal-dependent)
and that shouldn't add much run-time complexity

Gustaf Ullberg authored 7 years ago and Jean-Marc Valin committed 7 years ago

Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>

Reported by Chandrakala Madhira on the mailing list

SILK was being allocated too few bits for stereo hybrid, often resulting
in forced narrowing of the width. We now allocate more bits to SILK
and reduce the threshold for narrowing. This improves quality enough that
the bitrate threshold for switching to SILK can be increased to 44 kb/s.

Distinguish source files for the SSE 4.1 instruction
set extension consistently by their filename. This makes
it easier to check the correct flags are being set at
build time.

Signed-off-by: Jonathan Lennox <jonathan@vidyo.com>

Both versions of silk/tables_NLSF_CB had symbols
named silk_NLSF_CB1_Wght_Q9 which causes problems
if both files are build as part of the same
compilation unit. Rename the wideband version
to include a 'WB' string to avoid the conflict.

Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>

Jonathan Lennox authored 7 years ago and Timothy B. Terriberry committed 7 years ago

It's unnecessary, and isn't defined correctly on floating-point.

This makes us correctly use Neon functions (in floating-point mode) on
platforms where Neon is detected by RTCD.

Signed-off-by: Timothy B. Terriberry <tterribe@xiph.org>

Thanks to petrufm for pointing that out:
https://github.com/xiph/opus/issues/35

Linfeng Zhang authored 8 years ago and Jean-Marc Valin committed 7 years ago

Change-Id: I607a8b75b0711a485384d6f854cf6e2ec18b38b7

Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>

Linfeng Zhang authored 8 years ago and Jean-Marc Valin committed 7 years ago

The optimization is bit exact with C function.

Change-Id: Ifb8f04b19f2d576e79ce5dcfa7e0fc374d71d6c8

Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>

Linfeng Zhang authored 8 years ago and Jean-Marc Valin committed 7 years ago

Split to silk_biquad_alt_stride1() and silk_biquad_alt_stride2(),
so that it can be optimized more efficiently when stride is 2.

This change in C code is bit exact with the origin.

Change-Id: Idaefe670397016ace2a489e3435ac61b7dbe79d5

Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>

Linfeng Zhang authored 8 years ago and Jean-Marc Valin committed 8 years ago

The optimization is bit exact with C function.

This optimization speeds up fixed-point SILK encoder on NEON about
5% to 8%. (Tested on Acer Chromebook, ARMv7 Processor rev 3 (v7l).)

Change-Id: I582f6f3585b7946149e16a2ad3084ebc0ae79a4f

Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>

- celt/modes.c:430:14: warning: cast from 'const unsigned char *' to
  'opus_int16 *' increases required alignment from 1 to 2 [-Wcast-align]
- 'C[0][1]' may be used uninitialized [-Wmaybe-uninitialized]
- Unused variable/parameter
- Value stored is never read
- MSVC warnings about "possible loss of data" due to type conversions
- MSVC warning C4146: unary minus operator applied to unsigned type
- silk/NLSF_del_dec_quant.c:137:20: warning: array subscript is above
  array bounds [-Warray-bounds] (gcc -O3 false positive)
- src/mlp_train.h:39:20: warning: function declaration isn't a prototype
  [-Wstrict-prototypes]
- Remove SMALL_FOOTPRINT code from SSE 4.1 FIR implementation, matching
  the C implementation.

The clang -Wcast-align warnings with SSE intrinsics are a known
clang issue: https://llvm.org/bugs/show_bug.cgi?id=20670

Linfeng Zhang authored 8 years ago and Jean-Marc Valin committed 8 years ago

The optimization is bit exact with C function.

Change-Id: Ib3bdc26a5a4ebe02e7f24be85104e8e9a2a9a738

Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>

It checks that no clearly unstable filter passes the LPC_inv_pred_gain()
test. Also, this will make it possible to check assembly for correctness.

Modified from an original patch from Linfeng Zhang <linfengz@google.com>.