Radu Velea authored 9 years ago and Timothy B. Terriberry committed 9 years ago

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

Jonathan Lennox authored 9 years ago and Timothy B. Terriberry committed 9 years ago

Fixes build failure on platforms with MAY_HAVE_SSE4_1 (but not PRESUME_SSE4_1) with --enable-intrinsics.

Rhishikesh Agashe authored 9 years ago and Jean-Marc Valin committed 9 years ago

Brings MIPS in sync with the ARM/SSE optimizations that added "arch" parameters.

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

Jonathan Lennox authored 9 years ago and Jean-Marc Valin committed 9 years ago

This patch adds a macro abstracting the condition under which the silk
math macros use opus_int64-based calculations rather than opus_int32.
No substantive change, but will make it easier to adjust if additional
such platforms are found in the future.

Jonathan Lennox authored 9 years ago and Jean-Marc Valin committed 9 years ago

Enable x86 intrinsics when building in floating-point mode.
Support SSE as an arch value.
Use RTCD to conditionally enable existing floating-point Celt SSE code.
Call functions directly (without RTCD) when their architecture can be presumed.
Use SSE4.1 intrinsics optimized code for Silk even in floating-point mode.

Koen Vos authored 9 years ago and Jean-Marc Valin committed 9 years ago

The bug was caused by an improper feedback of the per-frame bitrate, causing
the bitrate to jump up and down from frame to frame, within a packet.
The patch avoids this, and also gives a slight improvement in general for
multi-frame packets, even without FEC.

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

During review of c95c9a04, I replaced a call to
 _mm_cvtepi8_epi32() with the OP_CVTEPI16_EPI32_M64() macro (note
 the 16 instead of 8).
Make a separate OP_CVTEPI8_EPI32_M32() macro and use that instead.

Thaks to Wei Zhou for the report.

There is also no trailing whitespace.

xiangmingzhu authored 10 years ago and Jean-Marc Valin committed 10 years ago

1. Only for fixed point on x86 platform (32bit and 64bit, uses SIMD
   intrinsics up to SSE4.2)
2. Use "configure --enable-fixed-point --enable-intrinsics" to enable
   optimization, default is disabled.
3. Official test cases are verified and passed.

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

Marcello Caramma (mcaramma) authored 10 years ago and Jean-Marc Valin committed 10 years ago

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

Koen Vos authored 10 years ago and Jean-Marc Valin committed 10 years ago

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

Koen Vos authored 10 years ago and Jean-Marc Valin committed 10 years ago

- Bug fix: the CNG synthesis filter output consisted of only the prediction
  values, now added the input to that.
- CNG excitation level now takes into account the level from the PLC (since
  both PLC and CNG can be active at the same time).
- CNG is now called before PLC_glue() to smoothen the transition out of CNG.

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

Rhishikesh Agashe authored 10 years ago and Jean-Marc Valin committed 10 years ago

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

When an overflow happened in silk_sum_sqr_shift(), the sample pair causing
the overflow would be counted twice. This would lead to the C0 in
silk_burg_modified() being too large and cause problems on loud, tonal
signals. Thanks to Marcello Caramma for tracking down the problem.

maks authored 11 years ago and Jean-Marc Valin committed 11 years ago

The code was wrong, but did not have any impact on user-visible behaviour
because all it did was change an internal-only error code.

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

Also minor C89 fix for the previous commit

This saves 640 bytes on the peak stack usage.

Should make it easier when writing assembly.

Koen Vos authored 11 years ago and Jean-Marc Valin committed 11 years ago

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

Timothy B. Terriberry authored 11 years ago and Jean-Marc Valin committed 11 years ago

Optimizing celt_pitch_xcorr()/xcorr_kernel() which also speeds up
FIRs, IIRs and auto-correlations

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

Works by turning off pitch and energy prediction in CELT, while
setting first_frame_after_reset in SILK to disable pitch and LSF interpolation
and reduce LPC gain.

Code behaviour is unchanged

Newer versions of MSVC are unhappy with the strategy of the build
 environment redefining "inline" (even though they don't support the
 actual keyword). Instead we define OPUS_INLINE to the right thing
 in opus_defines.h.

This is the same approach we use for restrict.

Stefan Beller authored 11 years ago and Jean-Marc Valin committed 11 years ago

The compiler warned:
silk/float/pitch_analysis_core_FLP.c: In function 'silk_P_Ana_calc_corr_st3':
silk/float/pitch_analysis_core_FLP.c:499:36: warning: variable 'basis_ptr' set but not used [-Wunused-but-set-variable]
     const silk_float *target_ptr, *basis_ptr;

This means we can safely remove it.

Signed-off-by: Stefan Beller <stefanbeller@googlemail.com>
Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>

Saves 2.5% on ARM without any asm. The float build still uses the old
code because celt_fir() then becomes a float function.

bit-exact with original version

Should gives us ARM/SSE optimizations for free.

By default Visual Studio warns about various C stdlib calls,
recommending non-portable replacements instead. We disable
this warning in a number of places in the source.

Since they're specific to the Visual Studio build, it's better
to disable them just in the project files where they always
apply to the correct toolchain.

I have only added the disable setting to project files which
need it currently: opus, test_opus_encode, and test_opus_decode.

This warning disable was conditional on _WIN32, which mingw
also defines, resulting in a warning about the unknown pragma
on gcc. Instead make it depend on something only the Visual
Studio compiler defines.