Sync to upstream libopus

Sync to commit bb4b6885a139644cf3ac14e7deda9f633ec2d93c

This brings in a bunch of optimizations to decode speed
and memory usage. Allocations are switched from using
the pseudostack to using the real stack. Enabled hacks
to reduce stack usage.

This should fix crashes on sansa clip, although some
files will not play due to failing allocations in the
codec buffer.

Speeds up decoding of the following test files:

                 H300 (cf)   C200 (arm7tdmi)  ipod classic (arm9e)
16 kbps (silk)   14.28 MHz   4.00 MHz         2.61 MHz
64 kbps (celt)   4.09 MHz    8.08 MHz         6.24 MHz
128 kbps (celt)  1.93 MHz    8.83 MHz         6.53 MHz

Change-Id: I851733a8a5824b61feb363a173091bc7e6629b58

1 files changed, 17 insertions, 1 deletions

diff --git a/lib/rbcodec/codecs/libopus/celt/pitch.h b/lib/rbcodec/codecs/libopus/celt/pitch.h
index df317ecc1d..96dbc0d794 100644
--- a/lib/rbcodec/codecs/libopus/celt/pitch.h
+++ b/lib/rbcodec/codecs/libopus/celt/pitch.h
@@ -41,8 +41,12 @@
 #include "x86/pitch_sse.h"
 #endif
 
+#if defined(MIPSr1_ASM)
+#include "mips/pitch_mipsr1.h"
+#endif
+
 #if defined(OPUS_ARM_ASM) && defined(FIXED_POINT)
-# include "arm/pitch_arm.h"
+//# include "arm/pitch_arm.h"
 #endif
 
 void pitch_downsample(celt_sig * OPUS_RESTRICT x[], opus_val16 * OPUS_RESTRICT x_lp,
@@ -141,6 +145,18 @@ static OPUS_INLINE void dual_inner_prod(const opus_val16 *x, const opus_val16 *y
 }
 #endif
 
+#ifndef OVERRIDE_CELT_INNER_PROD
+static OPUS_INLINE opus_val32 celt_inner_prod(const opus_val16 *x, const opus_val16 *y,
+      int N)
+{
+   int i;
+   opus_val32 xy=0;
+   for (i=0;i<N;i++)
+      xy = MAC16_16(xy, x[i], y[i]);
+   return xy;
+}
+#endif
+
 #ifdef FIXED_POINT
 opus_val32
 #else