We already needed these macros for gcc with optimizations disabled,
 but it appears clang needs them all the time.

Thanks to Jonathan Lennox for the report.

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.

This should not take an arch parameter, so it can properly be used
 as a fallback for accelerated versions which do not.
This patch instead provides a separate version which can call
 accelerated helpers for platforms that have taken that approach.

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>

Also adds an SSE-optimized celt_inner_prod().

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.

Should make it easy to adapt to other architectures.

Should be trivial to adapt for Neon.

John Ridges authored 11 years ago and Jean-Marc Valin committed 11 years ago

The loop no longer reads past its buffer and is slightly faster.
Also fixes RESTORE_STACK in celt_iir().

There's no CPU detection for it, it only gets enabled by __SSE__
which gcc (other compilers?) defines automatically when supported
by -march=, which means at least all x86-64. For ia32, the user needs to
enable it in the CFLAGS.