search for: opus_have_rtcd

...fined(OPUS_ARM_PRESUME_EDSP))) > opus_val32 (*const CELT_PITCH_XCORR_IMPL[OPUS_ARCHMASK+1])(const opus_val16 *, > const 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...

...fined(OPUS_ARM_MAY_HAVE_MEDIA) +# define celt_pitch_xcorr_media MAY_HAVE_EDSP(celt_pitch_xcorr) +#endif # if defined(OPUS_ARM_MAY_HAVE_EDSP) opus_val32 celt_pitch_xcorr_edsp(const opus_val16 *_x, const opus_val16 *_y, opus_val32 *xcorr, int len, int max_pitch); # endif -# if !defined(OPUS_HAVE_RTCD) -# define OVERRIDE_PITCH_XCORR (1) +#if defined(OPUS_ARM_PRESUME_NEON) + +#define OVERRIDE_PITCH_XCORR (1) # define celt_pitch_xcorr(_x, _y, xcorr, len, max_pitch, arch) \ - ((void)(arch),PRESUME_NEON(celt_pitch_xcorr)(_x, _y, xcorr, len, max_pitch)) -# endif -#endif /* End CPU_ARM */ + (...

...| 5 ++++- celt/arm/pitch_arm.h | 19 ++++++++++++++----- 2 files changed, 18 insertions(+), 6 deletions(-) diff --git a/celt/arm/arm_celt_map.c b/celt/arm/arm_celt_map.c index ee6c244..f195315 100644 --- a/celt/arm/arm_celt_map.c +++ b/celt/arm/arm_celt_map.c @@ -35,7 +35,10 @@ #if defined(OPUS_HAVE_RTCD) -# if defined(FIXED_POINT) +# if 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) && !defined(O...

...a/celt/tests/test_unit_dft.c b/celt/tests/test_unit_dft.c index bcee440..484dc57 100644 --- a/celt/tests/test_unit_dft.c +++ b/celt/tests/test_unit_dft.c @@ -47,8 +47,7 @@ #if defined(OPUS_X86_MAY_HAVE_SSE2) || defined(OPUS_X86_MAY_HAVE_SSE4_1) # include "x86/x86cpu.c" -#elif defined(OPUS_HAVE_RTCD) && \ - (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_MAY_HAVE_NEON_INTR)) +#elif defined(OPUS_ARM_ASM) || defined(OPUS_ARM_MAY_HAVE_NEON_INTR) # include "arm/armcpu.c" # include "celt_lpc.c" # include "pitch.c" diff --git a/celt/tests/test_unit_mathops...

...a/celt/tests/test_unit_dft.c b/celt/tests/test_unit_dft.c index bcee440..484dc57 100644 --- a/celt/tests/test_unit_dft.c +++ b/celt/tests/test_unit_dft.c @@ -47,8 +47,7 @@ #if defined(OPUS_X86_MAY_HAVE_SSE2) || defined(OPUS_X86_MAY_HAVE_SSE4_1) # include "x86/x86cpu.c" -#elif defined(OPUS_HAVE_RTCD) && \ - (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_MAY_HAVE_NEON_INTR)) +#elif defined(OPUS_ARM_ASM) || defined(OPUS_ARM_MAY_HAVE_NEON_INTR) # include "arm/armcpu.c" # include "celt_lpc.c" # include "pitch.c" diff --git a/celt/tests/test_unit_mathops...

...) >> opus_val32 (*const CELT_PITCH_XCORR_IMPL[OPUS_ARCHMASK+1])(const opus_val16 *, >> const 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)...

Fixes build failure on platforms with MAY_HAVE_SSE4_1 (but not PRESUME_SSE4_1) with --enable-intrinsics. --- silk/fixed/main_FIX.h | 11 +++++++++++ silk/x86/x86_silk_map.c | 2 ++ 2 files changed, 13 insertions(+) diff --git a/silk/fixed/main_FIX.h b/silk/fixed/main_FIX.h index ffeb4f3..375b5eb 100644 --- a/silk/fixed/main_FIX.h +++ b/silk/fixed/main_FIX.h @@ -97,6 +97,17 @@ void

Fixes build failure on platforms with MAY_HAVE_SSE4_1 (but not PRESUME_SSE4_1) with --enable-intrinsics. --- silk/fixed/main_FIX.h | 11 +++++++++++ silk/x86/x86_silk_map.c | 2 ++ 2 files changed, 13 insertions(+) diff --git a/silk/fixed/main_FIX.h b/silk/fixed/main_FIX.h index ffeb4f3..375b5eb 100644 --- a/silk/fixed/main_FIX.h +++ b/silk/fixed/main_FIX.h @@ -97,6 +97,17 @@ void

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

...t_neon(const kiss_fft_state *st, const kiss_fft_cpx *fin, kiss_fft_cpx *fout); + +void opus_ifft_float_neon(const kiss_fft_state *st, + const kiss_fft_cpx *fin, + kiss_fft_cpx *fout); + #if !defined(OPUS_HAVE_RTCD) #define OVERRIDE_OPUS_FFT (1) @@ -58,6 +63,9 @@ void opus_fft_float_neon(const kiss_fft_state *st, #define opus_fft(_st, _fin, _fout, arch) \ ((void)(arch), opus_fft_float_neon(_st, _fin, _fout)) +#define opus_ifft(_st, _fin, _fout, arch) \ + ((void)(arch), opus_ifft_float_neon(_st, _f...

...t_neon(const kiss_fft_state *st, const kiss_fft_cpx *fin, kiss_fft_cpx *fout); + +void opus_ifft_float_neon(const kiss_fft_state *st, + const kiss_fft_cpx *fin, + kiss_fft_cpx *fout); + #if !defined(OPUS_HAVE_RTCD) #define OVERRIDE_OPUS_FFT (1) @@ -58,6 +63,9 @@ void opus_fft_float_neon(const kiss_fft_state *st, #define opus_fft(_st, _fin, _fout, arch) \ ((void)(arch), opus_fft_float_neon(_st, _fin, _fout)) +#define opus_ifft(_st, _fin, _fout, arch) \ + ((void)(arch), opus_ifft_float_neon(_st, _f...

...{ celt_pitch_xcorr_c, /* ARMv4 */ @@ -113,7 +113,7 @@ void (*const CLT_MDCT_BACKWARD_IMPL[OPUS_ARCHMASK+1])(const mdct_lookup *l, }; #endif /* HAVE_ARM_NE10 */ -# endif /* OPUS_ARM_NEON_INTR */ +# endif /* OPUS_ARM_MAY_HAVE_NEON_INTR */ # endif /* FIXED_POINT */ #endif /* OPUS_HAVE_RTCD */ diff --git a/celt/arm/celt_ne10_fft.c b/celt/arm/celt_ne10_fft.c index d354502..1901024 100644 --- a/celt/arm/celt_ne10_fft.c +++ b/celt/arm/celt_ne10_fft.c @@ -44,6 +44,7 @@ #include "os_support.h" #include "stack_alloc.h" +#if !defined(FIXED_POINT) #ifdef CUSTOM_MODES...

Hello All, I extended the libNE10 optimizations for float towards mdct_backwards/opus_ifft. I am able to get about 14.26% improvement for Decode use case now on my Beaglebone Black. Please see [1] for measurements. Questions 1. Since this patch needs to go in after Encode [2] patch) should I submit this as patch series? 2. Since Jonathan Lennox posted intrinsics cleanup [3] patch, should

Hi, Optimizes celt_pitch_xcorr for ARM NEON floating point. Changes from RFCv3: - celt_neon_intr.c - removed warnings due to not having constant pointers - Put simpler loop to take care of corner cases. Unrolling using intrinsics was not really mapping well to what was done in celt_pitch_xcorr_arm.s - Makefile.am Removed explicit -O3 optimization - test_unit_mathops.c,

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

..., xcorr, len, max_pitch)) # endif -# endif +#else /* Start !FIXED_POINT */ +/* Float case */ +#if defined(OPUS_ARM_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) +#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)) +#endif +#endif +#endif /* end !FIXED_POINT */ #endif diff --git a/celt/cpu_support.h b/celt/cpu_support.h index 71...

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 version performance degradation is ~30%. Detection NEON under i...

..., xcorr, len, max_pitch)) # endif -# endif +#else /* Start !FIXED_POINT */ +/* Float case */ +#if defined(OPUS_ARM_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) +#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)) +#endif +#endif +#endif /* end !FIXED_POINT */ #endif diff --git a/celt/cpu_support.h b/celt/cpu_support.h index 71...

..., xcorr, len, max_pitch)) # endif -# endif +#else /* Start !FIXED_POINT */ +/* Float case */ +#if defined(OPUS_ARM_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) +#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)) +#endif +#endif +#endif /* end !FIXED_POINT */ #endif diff --git a/celt/cpu_support.h b/celt/cpu_support.h index 71...

Hi, Optimizes celt_pitch_xcorr for floating point. Changes from RFCv2: - Changes recommended by Timothy for celt_neon_intr.c everything except, left the unrolled loop still unrolled - configure.ac - use AC_LINK_IFELSE instead of AC_COMPILE_IFELSE - Moved compile flags into Makefile.am - OPUS_ARM_NEON_INR --> typo --> OPUS_ARM_NEON_INTR Viswanath Puttagunta (1): armv7: