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, 18 insertions, 1 deletions

diff --git a/lib/rbcodec/codecs/libopus/celt/fixed_generic.h b/lib/rbcodec/codecs/libopus/celt/fixed_generic.h
index ecf018a244..ac67d37ce8 100644
--- a/lib/rbcodec/codecs/libopus/celt/fixed_generic.h
+++ b/lib/rbcodec/codecs/libopus/celt/fixed_generic.h
@@ -113,7 +113,11 @@
 /** 16x32 multiply, followed by a 15-bit shift right and 32-bit add.
     b must fit in 31 bits.
     Result fits in 32 bits. */
-#define MAC16_32_Q15(c,a,b) ADD32(c,ADD32(MULT16_16((a),SHR((b),15)), SHR(MULT16_16((a),((b)&0x00007fff)),15)))
+#define MAC16_32_Q15(c,a,b) ADD32((c),ADD32(MULT16_16((a),SHR((b),15)), SHR(MULT16_16((a),((b)&0x00007fff)),15)))
+
+/** 16x32 multiplication, followed by a 16-bit shift right and 32-bit add.
+    Results fits in 32 bits */
+#define MAC16_32_Q16(c,a,b) ADD32((c),ADD32(MULT16_16((a),SHR((b),16)), SHR(MULT16_16SU((a),((b)&0x0000ffff)),16)))
 
 #define MULT16_16_Q11_32(a,b) (SHR(MULT16_16((a),(b)),11))
 #define MULT16_16_Q11(a,b) (SHR(MULT16_16((a),(b)),11))
@@ -131,4 +135,17 @@
 /** Divide a 32-bit value by a 32-bit value. Result fits in 32 bits */
 #define DIV32(a,b) (((opus_val32)(a))/((opus_val32)(b)))
 
+#if defined(MIPSr1_ASM)
+#include "mips/fixed_generic_mipsr1.h"
+#endif
+
+static OPUS_INLINE opus_val16 SIG2WORD16_generic(celt_sig x)
+{
+   x = PSHR32(x, SIG_SHIFT);
+   x = MAX32(x, -32768);
+   x = MIN32(x, 32767);
+   return EXTRACT16(x);
+}
+#define SIG2WORD16(x) (SIG2WORD16_generic(x))
+
 #endif