search for: opus_arm_asm

...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.c b/celt/tests/test_unit_mathops.c index 5b44...

...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.c b/celt/tests/test_unit_mathops.c index 5b44...

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

...R = -l:$(NE10_LIBDIR)/libNE10.so SOURCES += ../arm/celt_ne10_fft.c \ dump_modes_arm_ne10.c \ diff --git a/celt/pitch.h b/celt/pitch.h index af745eb..dde48c8 100644 --- a/celt/pitch.h +++ b/celt/pitch.h @@ -46,8 +46,7 @@ #include "mips/pitch_mipsr1.h" #endif -#if ((defined(OPUS_ARM_ASM) && defined(FIXED_POINT)) \ - || defined(OPUS_ARM_NEON_INTR)) +#if (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_MAY_HAVE_NEON_INTR)) # include "arm/pitch_arm.h" #endif @@ -189,7 +188,7 @@ celt_pitch_xcorr_c(const opus_val16 *_x, const opus_val16 *_y, #if !defined(OVERRIDE_PITC...

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,

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:

...nd !FIXED_POINT */ #endif diff --git a/celt/cpu_support.h b/celt/cpu_support.h index 71efff1..1d62e2f 100644 --- a/celt/cpu_support.h +++ b/celt/cpu_support.h @@ -31,7 +31,8 @@ #include "opus_types.h" #include "opus_defines.h" -#if defined(OPUS_HAVE_RTCD) && defined(OPUS_ARM_ASM) +#if defined(OPUS_HAVE_RTCD) && \ + (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_NEON_INTR)) #include "arm/armcpu.h" /* We currently support 4 ARM variants: diff --git a/celt/pitch.h b/celt/pitch.h index 5c6e551..4368cc5 100644 --- a/celt/pitch.h +++ b/celt/pitch.h @@ -46,7 +4...

...nd !FIXED_POINT */ #endif diff --git a/celt/cpu_support.h b/celt/cpu_support.h index 71efff1..1d62e2f 100644 --- a/celt/cpu_support.h +++ b/celt/cpu_support.h @@ -31,7 +31,8 @@ #include "opus_types.h" #include "opus_defines.h" -#if defined(OPUS_HAVE_RTCD) && defined(OPUS_ARM_ASM) +#if defined(OPUS_HAVE_RTCD) && \ + (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_NEON_INTR)) #include "arm/armcpu.h" /* We currently support 4 ARM variants: diff --git a/celt/pitch.h b/celt/pitch.h index 5c6e551..4368cc5 100644 --- a/celt/pitch.h +++ b/celt/pitch.h @@ -46,7 +4...

...nd !FIXED_POINT */ #endif diff --git a/celt/cpu_support.h b/celt/cpu_support.h index 71efff1..1d62e2f 100644 --- a/celt/cpu_support.h +++ b/celt/cpu_support.h @@ -31,7 +31,8 @@ #include "opus_types.h" #include "opus_defines.h" -#if defined(OPUS_HAVE_RTCD) && defined(OPUS_ARM_ASM) +#if defined(OPUS_HAVE_RTCD) && \ + (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_NEON_INTR)) #include "arm/armcpu.h" /* We currently support 4 ARM variants: diff --git a/celt/pitch.h b/celt/pitch.h index 5c6e551..4368cc5 100644 --- a/celt/pitch.h +++ b/celt/pitch.h @@ -46,7 +4...

...float_neon(_x, _y, xcorr, \ + len, max_pitch, arch)) +#endif +#endif /*end of !FIXED_POINT*/ #endif diff --git a/celt/pitch.h b/celt/pitch.h index 027ebd9..752b54e 100644 --- a/celt/pitch.h +++ b/celt/pitch.h @@ -46,7 +46,7 @@ #include "mips/pitch_mipsr1.h" #endif -#if defined(OPUS_ARM_ASM) && defined(FIXED_POINT) +#if defined(OPUS_ARM_ASM) # include "arm/pitch_arm.h" #endif @@ -189,11 +189,22 @@ opus_val32 void # endif (*const CELT_PITCH_XCORR_IMPL[OPUS_ARCHMASK+1])(const opus_val16 *, - const opus_val16 *, opus_val32 *, int, int); + const opus_va...

From: Viswanath Puttagunta <viswanath.puttagunta at linaro.org> Hi, Optimizes celt_pitch_xcorr for floating point. Changes from RFCv1: - Rebased on top of commit aad281878: Fix celt_pitch_xcorr_c signature. which got rid of ugly code around CELT_PITCH_XCORR_IMPL passing of "arch" parameter. - Unified with --enable-intrinsics used by x86 - Modified algorithm to be more

...a/celt/cpu_support.h b/celt/cpu_support.h > index 71efff1..1d62e2f 100644 > --- a/celt/cpu_support.h > +++ b/celt/cpu_support.h > @@ -31,7 +31,8 @@ > #include "opus_types.h" > #include "opus_defines.h" > > -#if defined(OPUS_HAVE_RTCD) && defined(OPUS_ARM_ASM) > +#if defined(OPUS_HAVE_RTCD) && \ > + (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_NEON_INTR)) > #include "arm/armcpu.h" > > /* We currently support 4 ARM variants: > diff --git a/celt/pitch.h b/celt/pitch.h > index 5c6e551..4368cc5 100644 > --- a/celt/...

Hi, Optimizes celt_pitch_xcorr for floating point. Changes from RFCv1: - Rebased on top of commit aad281878: Fix celt_pitch_xcorr_c signature. which got rid of ugly code around CELT_PITCH_XCORR_IMPL passing of "arch" parameter. - Unified with --enable-intrinsics used by x86 - Modified algorithm to be more in-line with algorithm in celt_pitch_xcorr_arm.s Viswanath Puttagunta

..._64-unknown-linux-gnu --host arm-linux-gnueabihf --disable-assertions --disable-check-asm --enable-intrinsics CFLAGS=-O3 --disable-shared When configuring with floating-point and intrinsics enabled as above, the generated config.h only has OPUS_ARM_MAY_HAVE_NEON_INTR defined (to 1), with /* #undef OPUS_ARM_ASM */ /* #undef OPUS_ARM_INLINE_ASM */ /* #undef OPUS_ARM_INLINE_EDSP */ /* #undef OPUS_ARM_INLINE_MEDIA */ /* #undef 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 */ /*...

...NTR) > +OPUS_ARM_NEON_INTR_CPPFLAGS = -mfpu=neon -O3 I'll repeat: I don't think you should change the optimization level here. > + /* Just unroll the rest of the loop */ I saw you decided to keep this unrolled, but you didn't actually answer my question. > -#elif defined(OPUS_ARM_ASM) && defined(FIXED_POINT) > +#endif > + > +#if defined(OPUS_ARM_NEON_INTR) > +#include "arm/celt_neon_intr.c" > +#endif > + > +#if ((defined(OPUS_ARM_ASM) && defined(FIXED_POINT)) \ > + || defined(OPUS_ARM_NEON_INTR)) > #include "arm/arm_c...

Hello, I received feedback from engineers working on NE10 [1] that it would be better to use NE10 [1] for FFT optimizations for opus use cases. However, these FFT patches are currently in review and haven't been integrated into NE10 yet. While the FFT functions in NE10 are getting baked, I wanted to optimize the celt_pitch_xcorr (floating point only) and use it to introduce ARM NEON

...ok about what should be expected? What I really want to know is if Opus could potentially run faster than Vorbis for equivalent audio. I also must mention I am cross compiling with a different build system. I have attempted different sets of compilation defines. Latest run included the following: OPUS_ARM_ASM OPUS_ARM_MAY_HAVE_NEON OPUS_ARM_MAY_HAVE_MEDIA OPUS_ARM_INLINE_EDSP OPUS_ARM_INLINE_NEON OPUS_ARM_INLINE_ASM FIXED_POINT OPUS_BUILD HAVE_LRINT HAVE_LRINTF Thanks! Dan

...s could potentially run faster than Vorbis for equivalent audio. >> >> I also must mention I am cross compiling with a different build system. >>I >> have attempted different sets of compilation defines. Latest run >>included >> the following: >> >> OPUS_ARM_ASM >> OPUS_ARM_MAY_HAVE_NEON >> OPUS_ARM_MAY_HAVE_MEDIA >> OPUS_ARM_INLINE_EDSP >> OPUS_ARM_INLINE_NEON >> OPUS_ARM_INLINE_ASM >> FIXED_POINT >> OPUS_BUILD >> HAVE_LRINT >> HAVE_LRINTF >> >> Thanks! >> Dan >> >> ____...

...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(OPUS_ARM_PRESUME_NEON)) || \ >...