search for: opus_arm_may_have_neon_intr

...18e6cf 100644 --- a/celt/arm/arm_celt_map.c +++ b/celt/arm/arm_celt_map.c @@ -44,7 +44,7 @@ opus_val32 (*const CELT_PITCH_XCORR_IMPL[OPUS_ARCHMASK+1])(const opus_val16 *, MAY_HAVE_NEON(celt_pitch_xcorr) /* NEON */ }; # else /* !FIXED_POINT */ -# if defined(OPUS_ARM_NEON_INTR) +# if defined(OPUS_ARM_MAY_HAVE_NEON_INTR) void (*const CELT_PITCH_XCORR_IMPL[OPUS_ARCHMASK+1])(const opus_val16 *, const opus_val16 *, opus_val32 *, int, int) = { 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_N...

....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 5b446b7..fd3319d 100644 --- a/celt/tests/tes...

....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 5b446b7..fd3319d 100644 --- a/celt/tests/tes...

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

...al32 *, int , int) = { celt_pitch_xcorr_c, /* 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_...

..._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)) || \ > + (defined(OPUS_ARM_MAY_HAVE_MEDIA) && !d...

Hi, ./configure --build x86_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 */ /* #und...

..., > > ./configure --build x86_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 */ &gt...

...f195315..5794e44 100644 --- a/celt/arm/arm_celt_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_kerne...

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

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

--- 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)])],, -

...sics optimizations for ARM(float) X86(fixed)])],, + [AS_HELP_STRING([--disable-intrinsics], [Disable intrinsics optimizations])],, [enable_intrinsics=yes]) rtcd_support=no @@ -483,11 +483,11 @@ AS_IF([test x"$enable_intrinsics" = x"yes"],[ AS_IF([test x"$OPUS_ARM_MAY_HAVE_NEON_INTR" = x"1"], [ - AC_DEFINE([OPUS_ARM_MAY_HAVE_NEON_INTR], 1, [Compiler supports ARMv7 Neon Intrinsics]) + AC_DEFINE([OPUS_ARM_MAY_HAVE_NEON_INTR], 1, [Compiler supports ARMv7/Aarch64 Neon Intrinsics]) intrinsics_support="$intrinsics_support (Neon_In...

...) +# define celt_fir(x, num, y, N, ord, arch) \ + ((void)(arch),PRESUME_NEON(celt_fir)(x, num, y, N, ord, arch)) +# endif + +#if !defined(OVERRIDE_CELT_FIR) +/*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))) +extern void (*const CELT_FIR_IMPL[OPUS_ARCHMASK+1])(const opus_val16 *, + const opus_val16 *, opus_val16 *, int, int, int); + +# define OVERRIDE_CELT_FIR +# define celt_fir(x, num, y, N, ord, arch) \ + ((*CELT_FIR_IMPL[(arch)&OP...

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

Hi all, This is Linfeng Zhang from Google. I'll work on ARM NEON optimization in the next few months. I'm submitting 2 patches in the following couple of emails, which have the new created celt_fir_neon(). I revised celt_fir_c() to not pass in argument "mem" in Patch 1. If there are concerns to this change, please let me know. Many thanks to your comments. Linfeng Zhang

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

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

...sics optimizations for ARM(float) X86(fixed)])],, + [AS_HELP_STRING([--disable-intrinsics], [Disable intrinsics optimizations])],, [enable_intrinsics=yes]) rtcd_support=no @@ -483,11 +483,11 @@ AS_IF([test x"$enable_intrinsics" = x"yes"],[ AS_IF([test x"$OPUS_ARM_MAY_HAVE_NEON_INTR" = x"1"], [ - AC_DEFINE([OPUS_ARM_MAY_HAVE_NEON_INTR], 1, [Compiler supports ARMv7 Neon Intrinsics]) + AC_DEFINE([OPUS_ARM_MAY_HAVE_NEON_INTR], 1, [Compiler supports ARMv7/Aarch64 Neon Intrinsics]) intrinsics_support="$intrinsics_support (Neon_In...