search for: opus_arm_presume_neon_intr

...opus_val16 *, opus_val32 *, int , int) = { Maybe I'm missing something, but... > -/*Is run-time CPU detection enabled on this platform?*/ > -# if defined(OPUS_HAVE_RTCD) && (defined(OPUS_ARM_ASM) \ > - || (defined(OPUS_ARM_MAY_HAVE_NEON_INTR) \ > - && !defined(OPUS_ARM_PRESUME_NEON_INTR))) > +# if defined(OPUS_HAVE_RTCD) && \ > + (defined(FIXED_POINT) && \ > + ((defined(OPUS_ARM_MAY_HAVE_NEON) && !defined(OPUS_ARM_PRESUME_NEON)) || \ > + (defined(OPUS_ARM_MAY_HAVE_MEDIA) && !defined(OPUS_ARM_PRESUME_MEDIA)) || \ > + (defined(OPUS...

...pitch_xcorr_edsp(const opus_val16 *_x, const opus_val16 *_y, #if defined(OPUS_ARM_MAY_HAVE_NEON_INTR) void celt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val16 *_y, opus_val32 *xcorr, int len, int max_pitch); -#if !defined(OPUS_HAVE_RTCD) || defined(OPUS_ARM_PRESUME_NEON_INTR) +#if defined(OPUS_ARM_PRESUME_NEON_INTR) #define OVERRIDE_PITCH_XCORR (1) # define celt_pitch_xcorr(_x, _y, xcorr, len, max_pitch, arch) \ ((void)(arch),celt_pitch_xcorr_float_neon(_x, _y, xcorr, len, max_pitch)) diff --git a/celt/dump_modes/Makefile b/celt/dump_modes/Makefile index 10c367...

...N_INTR], 1, [Compiler supports ARMv7/Aarch64 Neon Intrinsics]) - intrinsics_support="$intrinsics_support (Neon_Intrinsics)" + intrinsics_support="$intrinsics_support (NEON)" - AS_IF([test x"enable_rtcd" != x"" && test x"$OPUS_ARM_PRESUME_NEON_INTR" != x"1"], - [rtcd_support="$rtcd_support (Neon_Intrinsics)"]) + AS_IF([test x"$enable_rtcd" != x"" && test x"$OPUS_ARM_PRESUME_NEON_INTR" != x"1"], + [AS_IF([test x"$rtcd_support" = "no&quo...

...map.c +++ b/celt/arm/arm_celt_map.c @@ -58,6 +58,23 @@ void (*const CELT_PITCH_XCORR_IMPL[OPUS_ARCHMASK+1])(const opus_val16 *, # endif # endif /* FIXED_POINT */ +#if defined(FIXED_POINT) && defined(OPUS_HAVE_RTCD) && \ + defined(OPUS_ARM_MAY_HAVE_NEON_INTR) && !defined(OPUS_ARM_PRESUME_NEON_INTR) + +void (*const XCORR_KERNEL_IMPL[OPUS_ARCHMASK + 1])( + const opus_val16 *x, + const opus_val16 *y, + opus_val32 sum[4], + int len +) = { + xcorr_kernel_c, /* ARMv4 */ + xcorr_kernel_c, /* EDSP */ + xcorr_kernel_c...

As promised, here's a re-send of all my Aarch64 patches, following comments by John Ridges. Note that they actually affect more than just Aarch64 -- other than the ones specifically guarded by AARCH64_NEON defines, the Neon intrinsics all also apply on armv7; and the OPUS_FAST_INT64 patches apply on any 64-bit machine. The patches should largely be independent and independently useful, other

...d functions are called directly under iOS. Regards, Victor -----Original Message----- From: Jonathan Lennox Sent: Thursday, August 30, 2018 11:59 AM To: Victor Cherepanov Cc: opus at xiph.org Subject: Re: [opus] NEON detection under iOs On iOS, configure should define OPUS_ARM_PRESUME_NEON and OPUS_ARM_PRESUME_NEON_INTR if you’re building for armv7, and OPUS_ARM_PRESUME_NEON_INTR for arm64 (since every Apple armv7 CPU has supported Neon, and of course arm64 supports it though the assembler syntax is different). This should be slightly faster than using RTCD, since the Neon functions can be direct calls instea...

Hi, Thank you for a great work. Opus codec works great under many platforms. I have found a small performance issue under iOS platform. If the macro OPUS_HAVE_RTCD is not set, then encoder doesn't use some _neon functions at low bitrates (up to 64k). If the macro is set, then the compiler hits the error at opus/celt/arm/armcpu.c:153 (a function for detection missed). Being compared to Android

.../* ARMv4 */ @@ -104,8 +109,23 @@ opus_val32 (*const CELT_PITCH_XCORR_IMPL[OPUS_ARCHMASK+1])(const opus_val16 *, MAY_HAVE_MEDIA(celt_pitch_xcorr), /* Media */ MAY_HAVE_NEON(celt_pitch_xcorr) /* NEON */ }; + +#endif + +#elif defined(OPUS_ARM_MAY_HAVE_NEON_INTR) && !defined(OPUS_ARM_PRESUME_NEON_INTR) + +opus_val32 (*const CELT_PITCH_XCORR_IMPL[OPUS_ARCHMASK+1])(const opus_val16 *, + const opus_val16 *, opus_val32 *, int, int) = { + celt_pitch_xcorr_c, /* ARMv4 */ + celt_pitch_xcorr_c, /* EDSP */ + celt_pitch_xcorr_c, /* Media */ + celt_pitch_xcorr_...

...s ARMv7 Neon Intrinsics]) + AC_DEFINE([OPUS_ARM_MAY_HAVE_NEON_INTR], 1, [Compiler supports ARMv7/Aarch64 Neon Intrinsics]) intrinsics_support="$intrinsics_support (Neon_Intrinsics)" AS_IF([test x"enable_rtcd" != x"" && test x"$OPUS_ARM_PRESUME_NEON_INTR" != x"1"], - [rtcd_support="$rtcd_support (ARMv7_Neon_Intrinsics)"]) + [rtcd_support="$rtcd_support (Neon_Intrinsics)"]) AS_IF([test x"$OPUS_ARM_PRESUME_NEON_INTR" = x"1"], [AC_DEFINE([OPUS_ARM_PRE...

--- configure.ac | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/configure.ac b/configure.ac index f267ef7..606511b 100644 --- a/configure.ac +++ b/configure.ac @@ -190,8 +190,8 @@ AC_ARG_ENABLE([rtcd], [enable_rtcd=yes]) AC_ARG_ENABLE([intrinsics], - [AS_HELP_STRING([--enable-intrinsics], [Enable intrinsics optimizations for ARM(float) X86(fixed)])],, -

...s ARMv7 Neon Intrinsics]) + AC_DEFINE([OPUS_ARM_MAY_HAVE_NEON_INTR], 1, [Compiler supports ARMv7/Aarch64 Neon Intrinsics]) intrinsics_support="$intrinsics_support (Neon_Intrinsics)" AS_IF([test x"enable_rtcd" != x"" && test x"$OPUS_ARM_PRESUME_NEON_INTR" != x"1"], - [rtcd_support="$rtcd_support (ARMv7_Neon_Intrinsics)"]) + [rtcd_support="$rtcd_support (Neon_Intrinsics)"]) AS_IF([test x"$OPUS_ARM_PRESUME_NEON_INTR" = x"1"], [AC_DEFINE([OPUS_ARM_PRE...

...ef OPUS_ARM_INLINE_NEON */ /* #undef OPUS_ARM_MAY_HAVE_EDSP */ /* #undef OPUS_ARM_MAY_HAVE_MEDIA */ /* #undef OPUS_ARM_MAY_HAVE_NEON */ /* #undef OPUS_ARM_PRESUME_AARCH64_NEON_INTR */ /* #undef OPUS_ARM_PRESUME_EDSP */ /* #undef OPUS_ARM_PRESUME_MEDIA */ /* #undef OPUS_ARM_PRESUME_NEON */ /* #undef OPUS_ARM_PRESUME_NEON_INTR */ So MAY_HAVE_NEON will be defined to MEDIA version, which will eventually fall down to C functions in the jump table: # define MAY_HAVE_NEON(name) MAY_HAVE_MEDIA(name) Therefore all NEON intrinsics optimizations in their jump tables won't get called for floating-point. Am I missing some o...

Should call celt_inner_prod(). --- celt/bands.c | 7 ++++--- celt/bands.h | 2 +- celt/celt_encoder.c | 6 +++--- celt/pitch.c | 2 +- src/opus_multistream_encoder.c | 2 +- 5 files changed, 10 insertions(+), 9 deletions(-) diff --git a/celt/bands.c b/celt/bands.c index bbe8a4c..1ab24aa 100644 --- a/celt/bands.c +++ b/celt/bands.c

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

...elt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val16 *_y, #endif /* end !FIXED_POINT */ -/*Is run-time CPU detection enabled on this platform?*/ -# if defined(OPUS_HAVE_RTCD) && (defined(OPUS_ARM_ASM) \ - || (defined(OPUS_ARM_MAY_HAVE_NEON_INTR) \ - && !defined(OPUS_ARM_PRESUME_NEON_INTR))) +# if defined(OPUS_HAVE_RTCD) && \ + (defined(FIXED_POINT) && \ + ((defined(OPUS_ARM_MAY_HAVE_NEON) && !defined(OPUS_ARM_PRESUME_NEON)) || \ + (defined(OPUS_ARM_MAY_HAVE_MEDIA) && !defined(OPUS_ARM_PRESUME_MEDIA)) || \ + (defined(OPUS_ARM_MAY_HAVE_EDSP) &...

...t , int) = { > > Maybe I'm missing something, but... > >> -/*Is run-time CPU detection enabled on this platform?*/ >> -# if defined(OPUS_HAVE_RTCD) && (defined(OPUS_ARM_ASM) \ >> - || (defined(OPUS_ARM_MAY_HAVE_NEON_INTR) \ >> - && !defined(OPUS_ARM_PRESUME_NEON_INTR))) >> +# if defined(OPUS_HAVE_RTCD) && \ >> + (defined(FIXED_POINT) && \ >> + ((defined(OPUS_ARM_MAY_HAVE_NEON) && !defined(OPUS_ARM_PRESUME_NEON)) || \ >> + (defined(OPUS_ARM_MAY_HAVE_MEDIA) && !defined(OPUS_ARM_PRESUME_MEDIA)) || \ >&g...

On iOS, configure should define OPUS_ARM_PRESUME_NEON and OPUS_ARM_PRESUME_NEON_INTR if you’re building for armv7, and OPUS_ARM_PRESUME_NEON_INTR for arm64 (since every Apple armv7 CPU has supported Neon, and of course arm64 supports it though the assembler syntax is different). This should be slightly faster than using RTCD, since the Neon functions can be direct calls instead of...

Following Tim's comments, here are my reworked patches for the Neon intrinsic function patches of of my Aarch64 patchset, i.e. replacing patches 5-8 of the v2 series. Patches 1-4 and 9-18 of the old series still apply unmodified. The one new (as opposed to changed) patch is the first one in this series, to add named constants for the ARM architecture variants. There are also some minor code

...f OPUS_ARM_MAY_HAVE_EDSP */ > /* #undef OPUS_ARM_MAY_HAVE_MEDIA */ > /* #undef OPUS_ARM_MAY_HAVE_NEON */ > /* #undef OPUS_ARM_PRESUME_AARCH64_NEON_INTR */ > /* #undef OPUS_ARM_PRESUME_EDSP */ > /* #undef OPUS_ARM_PRESUME_MEDIA */ > /* #undef OPUS_ARM_PRESUME_NEON */ > /* #undef OPUS_ARM_PRESUME_NEON_INTR */ > > So MAY_HAVE_NEON will be defined to MEDIA version, which will eventually > fall down to C functions in the jump table: > # define MAY_HAVE_NEON(name) MAY_HAVE_MEDIA(name) > > Therefore all NEON intrinsics optimizations in their jump tables won't get > called for flo...

...= x"yes"],[ [[ static float32x4_t A0, A1, SUMM; SUMM = vmlaq_f32(SUMM, A0, A1); + return (int)vgetq_lane_f32(SUMM, 0); ]] ) AS_IF([test x"$OPUS_ARM_MAY_HAVE_NEON_INTR" = x"1" && test x"$OPUS_ARM_PRESUME_NEON_INTR" != x"1"], @@ -521,10 +522,13 @@ AS_IF([test x"$enable_intrinsics" = x"yes"],[ [OPUS_X86_MAY_HAVE_SSE], [OPUS_X86_PRESUME_SSE], [[#include <xmmintrin.h> + #include <time.h> ]], [[ -...