search for: silk_smlaww

...+#define silk_SMULWW(a32, b32) ((opus_int32)(((opus_int64)(a32) * (b32)) >> 16)) #else #define silk_SMULWW(a32, b32) silk_MLA(silk_SMULWB((a32), (b32)), (a32), silk_RSHIFT_ROUND((b32), 16)) #endif /* a32 + ((b32 * c32) >> 16) */ #if OPUS_FAST_INT64 -#define silk_SMLAWW(a32, b32, c32) ((a32) + (((opus_int64)(b32) * (c32)) >> 16)) +#define silk_SMLAWW(a32, b32, c32) ((opus_int32)((a32) + (((opus_int64)(b32) * (c32)) >> 16))) #else #define silk_SMLAWW(a32, b32, c32) silk_MLA(silk_SMLAWB((a32), (b32), (c32)), (b32), silk_RSHIFT_ROUND((...

...t64 rd; + __asm__( + "#silk_SMULWW\n\t" + "smull %x0, %w1, %w2\n\t" + : "=&r"(rd) + : "%r"(a), "r"(b) + ); + rd >>= 16; + rd &= 0xFFFFFFFF; + return rd; +} +#define silk_SMULWW(a, b) (silk_SMULWW_arm64(a, b)) + +#undef silk_SMLAWW +static OPUS_INLINE opus_int32 silk_SMLAWW_arm64(opus_int32 a, opus_int32 b, + opus_int32 c) +{ + opus_int64 rd; + __asm__( + "#silk_SMLAWW\n\t" + "smull %x0, %w1, %w2\n\t" + : "=&r"(rd) + : "%r"(b), "r"(c) + ); + rd >>= 16...

--- celt/arch.h | 5 +++++ silk/macros.h | 4 +--- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/celt/arch.h b/celt/arch.h index 9f74ddd..670527b 100644 --- a/celt/arch.h +++ b/celt/arch.h @@ -78,6 +78,11 @@ static OPUS_INLINE void _celt_fatal(const char *str, const char *file, int line) #define UADD32(a,b) ((a)+(b)) #define USUB32(a,b) ((a)-(b)) +/* Set this if opus_int64

...int64)(a32) * (b32)) >> 16) #else #define silk_SMULWW(a32, b32) silk_MLA(silk_SMULWB((a32), (b32)), (a32), silk_RSHIFT_ROUND((b32), 16)) #endif /* a32 + ((b32 * c32) >> 16) */ -#if defined(__x86_64__) || defined(__LP64__) || defined(_WIN64) +#if OPUS_FAST_INT64 #define silk_SMLAWW(a32, b32, c32) ((a32) + (((opus_int64)(b32) * (c32)) >> 16)) #else #define silk_SMLAWW(a32, b32, c32) silk_MLA(silk_SMLAWB((a32), (b32), (c32)), (b32), silk_RSHIFT_ROUND((c32), 16)) -- 2.3.2 (Apple Git-55)

--- configure.ac | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/configure.ac b/configure.ac index f52d2c2..e1a6e9b 100644 --- a/configure.ac +++ b/configure.ac @@ -190,7 +190,7 @@ AC_ARG_ENABLE([rtcd], [enable_rtcd=yes]) AC_ARG_ENABLE([intrinsics], - [AS_HELP_STRING([--disable-intrinsics], [Disable intrinsics optimizations for ARM(float) X86(fixed)])],, +

This sequence of patches provides arm64 support for Opus. Tested on iOS, Android, and Ubuntu 14.04. The patch sequence was written on top of Viswanath Puttagunta's Ne10 patches, but all but the second ("Reorganize pitch_arm.h") should, I think, apply independently of it. It does depends on my previous intrinsics configury reorganization, however. Comments welcome. With this and

Here are my aarch64 patches rebased to the current tip of Opus master. They're largely the same as my previous patch set, with the addition of the final one (the Neon fixed-point implementation of xcorr_kernel). This replaces Viswanath's Neon fixed-point celt_pitch_xcorr, since xcorr_kernel is used in celt_fir and celt_iir as well. These have been tested for correctness under qemu

...#define silk_SMLAL(a64, b32, c32) (silk_ADD64((a64), ((opus_int64)(b32) * (opus_int64)(c32)))) + +/* (a32 * b32) >> 16 */ +#define silk_SMULWW(a32, b32) silk_MLA(silk_SMULWB((a32), (b32)), (a32), silk_RSHIFT_ROUND((b32), 16)) + +/* a32 + ((b32 * c32) >> 16) */ +#define silk_SMLAWW(a32, b32, c32) silk_MLA(silk_SMLAWB((a32), (b32), (c32)), (b32), silk_RSHIFT_ROUND((c32), 16)) + +/* add/subtract with output saturated */ +static inline opus_int32 silk_ADD_SAT32(opus_int32 a, opus_int32 b) +{ + int res; + __asm__( + "qadd %0, %1, %2;\n" + : "=&amp...