search for: opus_arm_may_have_edsp

Jonathan Lennox wrote: > -# 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(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?*/ &gt...

...-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(OPUS_ARM_PRESUME_EDSP))) 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 */ diff --git a/celt/arm/pitch_arm.h b/celt/arm/pitch_arm.h index eaf61c9...

...te: >> -# 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(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 enable...

...loating-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 */ /* #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 def...

...+ b/celt/arm/arm_celt_map.c @@ -94,9 +94,14 @@ void (*const CLT_MDCT_BACKWARD_IMPL[OPUS_ARCHMASK+1])(const mdct_lookup *l, clt_mdct_backward_neon, /* Neon with NE10 */ }; -#endif +#endif /* HAVE_ARM_NE10 */ # if defined(FIXED_POINT) + +#if defined(OPUS_ARM_MAY_HAVE_NEON) || defined(OPUS_ARM_MAY_HAVE_EDSP) + +#if !defined(OPUS_ARM_PRESUME_NEON) && (!defined(OPUS_ARM_PRESUME_EDSP) || defined(OPUS_ARM_MAY_HAVE_NEON)) + opus_val32 (*const CELT_PITCH_XCORR_IMPL[OPUS_ARCHMASK+1])(const opus_val16 *, const opus_val16 *, opus_val32 *, int , int) = { celt_pitch_xcorr_c, /* ARM...

...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 */ > /* #undef OPUS_ARM_PRESUME_EDSP */ > /* #undef OPUS_ARM_PRESUME_MEDIA */ > /* #undef OPUS_ARM_PRESUME_NEON */ > /* #undef OPUS_ARM_PRESUME_NEON_IN...

...], + [ + OPUS_ARM_NEON_INTR_CFLAGS="$ARM_NEON_INTR_CFLAGS" + AC_SUBST([OPUS_ARM_NEON_INTR_CFLAGS]) + dnl Don't see why defining these is necessary to check features at runtime + AC_DEFINE([OPUS_ARM_MAY_HAVE_EDSP], 1, [Define if compiler support EDSP Instructions]) + AC_DEFINE([OPUS_ARM_MAY_HAVE_MEDIA], 1, [Define if compiler support MEDIA Instructions]) + AC_DEFINE([OPUS_ARM_MAY_HAVE_NEON], 1, [Define if compiler support NEON instructions]) + ] +...

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

...loating-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 */ /* #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 def...

...loating-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 */ /* #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 def...

...nfig.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 */ >> /* #undef OPUS_ARM_PRESUME_EDSP */ >> /* #undef OPUS_ARM_PRESUME_MEDIA */ >> /* #undef OPUS_ARM_PRESUME_NEON */ >> /* #un...

..._process4 VEOR q0, q0, q0 ; xcorr_kernel_neon only modifies r4, r5, r12, and q0...q3. ; So we don't save/restore any other registers. - BL xcorr_kernel_neon + BL xcorr_kernel_neon_start SUBS r6, r6, #4 VST1.32 {q0}, [r2]! ; _y += 4 @@ -257,6 +258,7 @@ IF OPUS_ARM_MAY_HAVE_EDSP ; This will get used on ARMv7 devices without NEON, so it has been optimized ; to take advantage of dual-issuing where possible. xcorr_kernel_edsp PROC +xcorr_kernel_edsp_start ; input: ; r3 = int len ; r4 = opus_val16 *_x (must be 32-bit aligned) @@ -416,7 +418,7...

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

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

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,

...quot; != x""], + [rtcd_support="ARM (ARMv7_Neon_Intrinsics)"],[]) + enable_intrinsics="$enable_intrinsics ARMv7_Neon_Intrinsics" + dnl Don't see why defining these is necessary to check features at runtime + AC_DEFINE([OPUS_ARM_MAY_HAVE_EDSP], 1, [Define if compiler support EDSP Instructions]) + AC_DEFINE([OPUS_ARM_MAY_HAVE_MEDIA], 1, [Define if compiler support MEDIA Instructions]) + AC_DEFINE([OPUS_ARM_MAY_HAVE_NEON], 1, [Define if compiler support NEON instructions]) + ], + [ + AC_MSG...

...quot; != x""], + [rtcd_support="ARM (ARMv7_Neon_Intrinsics)"],[]) + enable_intrinsics="$enable_intrinsics ARMv7_Neon_Intrinsics" + dnl Don't see why defining these is necessary to check features at runtime + AC_DEFINE([OPUS_ARM_MAY_HAVE_EDSP], 1, [Define if compiler support EDSP Instructions]) + AC_DEFINE([OPUS_ARM_MAY_HAVE_MEDIA], 1, [Define if compiler support MEDIA Instructions]) + AC_DEFINE([OPUS_ARM_MAY_HAVE_NEON], 1, [Define if compiler support NEON instructions]) + ], + [ + AC_MSG...

...quot; != x""], + [rtcd_support="ARM (ARMv7_Neon_Intrinsics)"],[]) + enable_intrinsics="$enable_intrinsics ARMv7_Neon_Intrinsics" + dnl Don't see why defining these is necessary to check features at runtime + AC_DEFINE([OPUS_ARM_MAY_HAVE_EDSP], 1, [Define if compiler support EDSP Instructions]) + AC_DEFINE([OPUS_ARM_MAY_HAVE_MEDIA], 1, [Define if compiler support MEDIA Instructions]) + AC_DEFINE([OPUS_ARM_MAY_HAVE_NEON], 1, [Define if compiler support NEON instructions]) + ], + [ + AC_MSG...

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: