[Opus] Update to v1.2.1

third_party/opus/src/silk/arm/biquad_alt_arm.h

 /***********************************************************************
-Copyright (c) 2006-2011, Skype Limited. All rights reserved.
+Copyright (c) 2017 Google Inc.
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions
 are met:
 - Redistributions of source code must retain the above copyright notice,
 this list of conditions and the following disclaimer.
 - Redistributions in binary form must reproduce the above copyright
 notice, this list of conditions and the following disclaimer in the
 documentation and/or other materials provided with the distribution.
 - Neither the name of Internet Society, IETF or IETF Trust, nor the
 names of specific contributors, may be used to endorse or promote
 products derived from this software without specific prior written
 permission.
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
 LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 POSSIBILITY OF SUCH DAMAGE.
 ***********************************************************************/
 
-/*                                                                      *
- * silk_biquad_alt.c                                              *
- *                                                                      *
- * Second order ARMA filter                                             *
- * Can handle slowly varying filter coefficients                        *
- *                                                                      */
+#ifndef SILK_BIQUAD_ALT_ARM_H
+# define SILK_BIQUAD_ALT_ARM_H
 
-#ifdef HAVE_CONFIG_H
-#include "config.h"
-#endif
+# include "celt/arm/armcpu.h"
 
-#include "SigProc_FIX.h"
-
-/* Second order ARMA filter, alternative implementation */
-void silk_biquad_alt(
+# if defined(OPUS_ARM_MAY_HAVE_NEON_INTR)
+void silk_biquad_alt_stride2_neon(
     const opus_int16            *in,                /* I     input signal                                               */
     const opus_int32            *B_Q28,             /* I     MA coefficients [3]                                        */
     const opus_int32            *A_Q28,             /* I     AR coefficients [2]                                        */
-    opus_int32                  *S,                 /* I/O   State vector [2]                                           */
+    opus_int32                  *S,                 /* I/O   State vector [4]                                           */
     opus_int16                  *out,               /* O     output signal                                              */
-    const opus_int32            len,                /* I     signal length (must be even)                               */
-    opus_int                    stride              /* I     Operate on interleaved signal if > 1                       */
-)
-{
-    /* DIRECT FORM II TRANSPOSED (uses 2 element state vector) */
-    opus_int   k;
-    opus_int32 inval, A0_U_Q28, A0_L_Q28, A1_U_Q28, A1_L_Q28, out32_Q14;
+    const opus_int32            len                 /* I     signal length (must be even)                               */
+);
 
-    /* Negate A_Q28 values and split in two parts */
-    A0_L_Q28 = ( -A_Q28[ 0 ] ) & 0x00003FFF;        /* lower part */
-    A0_U_Q28 = silk_RSHIFT( -A_Q28[ 0 ], 14 );      /* upper part */
-    A1_L_Q28 = ( -A_Q28[ 1 ] ) & 0x00003FFF;        /* lower part */
-    A1_U_Q28 = silk_RSHIFT( -A_Q28[ 1 ], 14 );      /* upper part */
+#  if !defined(OPUS_HAVE_RTCD) && defined(OPUS_ARM_PRESUME_NEON)
+#   define OVERRIDE_silk_biquad_alt_stride2                   (1)
+#   define silk_biquad_alt_stride2(in, B_Q28, A_Q28, S, out, len, arch) ((void)(arch), PRESUME_NEON(silk_biquad_alt_stride2)(in, B_Q28, A_Q28, S, out, len))
+#  endif
+# endif
 
-    for( k = 0; k < len; k++ ) {
-        /* S[ 0 ], S[ 1 ]: Q12 */
-        inval = in[ k * stride ];
-        out32_Q14 = silk_LSHIFT( silk_SMLAWB( S[ 0 ], B_Q28[ 0 ], inval ), 2 );
+# if !defined(OVERRIDE_silk_biquad_alt_stride2)
+/*Is run-time CPU detection enabled on this platform?*/
+#  if defined(OPUS_HAVE_RTCD) && (defined(OPUS_ARM_MAY_HAVE_NEON_INTR) && !defined(OPUS_ARM_PRESUME_NEON_INTR))
+extern void (*const SILK_BIQUAD_ALT_STRIDE2_IMPL[OPUS_ARCHMASK+1])(
+        const opus_int16            *in,                /* I     input signal                                               */
+        const opus_int32            *B_Q28,             /* I     MA coefficients [3]                                        */
+        const opus_int32            *A_Q28,             /* I     AR coefficients [2]                                        */
+        opus_int32                  *S,                 /* I/O   State vector [4]                                           */
+        opus_int16                  *out,               /* O     output signal                                              */
+        const opus_int32            len                 /* I     signal length (must be even)                               */
+    );
+#   define OVERRIDE_silk_biquad_alt_stride2                  (1)
+#   define silk_biquad_alt_stride2(in, B_Q28, A_Q28, S, out, len, arch) ((*SILK_BIQUAD_ALT_STRIDE2_IMPL[(arch)&OPUS_ARCHMASK])(in, B_Q28, A_Q28, S, out, len))
+#  elif defined(OPUS_ARM_PRESUME_NEON_INTR)
+#   define OVERRIDE_silk_biquad_alt_stride2                  (1)
+#   define silk_biquad_alt_stride2(in, B_Q28, A_Q28, S, out, len, arch) ((void)(arch), silk_biquad_alt_stride2_neon(in, B_Q28, A_Q28, S, out, len))
+#  endif
+# endif
 
-        S[ 0 ] = S[1] + silk_RSHIFT_ROUND( silk_SMULWB( out32_Q14, A0_L_Q28 ), 14 );
-        S[ 0 ] = silk_SMLAWB( S[ 0 ], out32_Q14, A0_U_Q28 );
-        S[ 0 ] = silk_SMLAWB( S[ 0 ], B_Q28[ 1 ], inval);
-
-        S[ 1 ] = silk_RSHIFT_ROUND( silk_SMULWB( out32_Q14, A1_L_Q28 ), 14 );
-        S[ 1 ] = silk_SMLAWB( S[ 1 ], out32_Q14, A1_U_Q28 );
-        S[ 1 ] = silk_SMLAWB( S[ 1 ], B_Q28[ 2 ], inval );
-
-        /* Scale back to Q0 and saturate */
-        out[ k * stride ] = (opus_int16)silk_SAT16( silk_RSHIFT( out32_Q14 + (1<<14) - 1, 14 ) );
-    }
-}
+#endif /* end SILK_BIQUAD_ALT_ARM_H */