search for: pitch_arm

..._IMPL[OPUS_ARCHMASK+1])(const opus_val16 *, > const opus_val16 *, opus_val32 *, int, int); Shouldn't the first case have a corresponding update in the #else clause for the !defined(FIXED_POINT) case? > celt_pitch_xcorr_c, /* ARMv4 */ > diff --git a/celt/arm/pitch_arm.h b/celt/arm/pitch_arm.h > index eaf61c9..bd41774 100644 > --- a/celt/arm/pitch_arm.h > +++ b/celt/arm/pitch_arm.h > @@ -46,7 +46,13 @@ opus_val32 celt_pitch_xcorr_edsp(const opus_val16 *_x, const opus_val16 *_y, > opus_val32 *xcorr, int len, int max_pitch); > # endif &gt...

--- celt/arm/arm_celt_map.c | 24 +++++++++++- celt/arm/pitch_arm.h | 97 +++++++++++++++++++++++++++++++++---------------- 2 files changed, 88 insertions(+), 33 deletions(-) diff --git a/celt/arm/arm_celt_map.c b/celt/arm/arm_celt_map.c index 0c9acff..cc6b706 100644 --- a/celt/arm/arm_celt_map.c +++ b/celt/arm/arm_celt_map.c @@ -94,9 +94,14 @@ void (*const C...

--- celt/arm/pitch_arm.h | 19 +++++++++++++++++++ celt/pitch.h | 19 ------------------- 2 files changed, 19 insertions(+), 19 deletions(-) diff --git a/celt/arm/pitch_arm.h b/celt/arm/pitch_arm.h index d5c9408..fe76f8d 100644 --- a/celt/arm/pitch_arm.h +++ b/celt/arm/pitch_arm.h @@ -75,4 +75,23 @@ void celt_pi...

--- celt/arm/arm_celt_map.c | 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 define...

Used for celt_pitch_xcorr on aarch64, and celt_fir and celt_iir on both armv7 and aarch64. --- celt/arm/arm_celt_map.c | 17 +++++++++++++ celt/arm/celt_neon_intr.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++- celt/arm/pitch_arm.h | 31 +++++++++++++++++++++++- 3 files changed, 107 insertions(+), 2 deletions(-) diff --git a/celt/arm/arm_celt_map.c b/celt/arm/arm_celt_map.c index 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[OP...

...) case? Hm, yes, you?re right ? there are cases where we?ll end up emitting a (useless and unused, but harmless) CELT_PITCH_XCORR_IMPL object unnecessarily. I?ll submit an updated version of the patch. > >> celt_pitch_xcorr_c, /* ARMv4 */ >> diff --git a/celt/arm/pitch_arm.h b/celt/arm/pitch_arm.h >> index eaf61c9..bd41774 100644 >> --- a/celt/arm/pitch_arm.h >> +++ b/celt/arm/pitch_arm.h >> @@ -46,7 +46,13 @@ opus_val32 celt_pitch_xcorr_edsp(const opus_val16 *_x, const opus_val16 *_y, >> opus_val32 *xcorr, int len, int max_pitch);...

.../subtract. Add Aarch64 intrinsic for SIG2WORD16. Makefile.am | 9 +-- celt/arch.h | 9 ++- celt/arm/arm_celt_map.c | 22 ++++++- celt/arm/celt_neon_intr.c | 61 ++++++++++++++++++- celt/arm/fixed_arm64.h | 35 +++++++++++ celt/arm/pitch_arm.h | 62 +++++++++++++++++++- celt/fixed_generic.h | 16 +++++ celt/pitch.h | 20 ------- celt_headers.mk | 1 + configure.ac | 41 +++++++++---- silk/NSQ.c | 55 +++++------------ silk/NSQ.h...

...c optimizations to work on aarch64 target. Signed-off-by: Viswanath Puttagunta <viswanath.puttagunta at linaro.org> --- Makefile.am | 4 +- celt/arm/arm_celt_map.c | 4 +- celt/arm/celt_ne10_fft.c | 2 + celt/arm/celt_ne10_mdct.c | 3 ++ celt/arm/pitch_arm.h | 2 +- celt/dump_modes/Makefile | 2 +- celt/pitch.h | 5 +-- celt/tests/test_unit_dft.c | 3 +- celt/tests/test_unit_mathops.c | 7 ++-- celt/tests/test_unit_mdct.c | 4 +- celt/tests/test_unit_rotation.c | 5 ++- configure.ac...

...e ARM neon intrinsics Makefile.am | 23 +++++++++++ celt/_kiss_fft_guts.h | 4 +- celt/arch.h | 4 +- celt/arm/arm_celt_map.c | 15 +++++++- celt/arm/celt_neon_intr.c | 81 +++++++++++++++++++++++++++++++++++++++ celt/arm/pitch_arm.h | 15 +++++++- celt/pitch.h | 17 ++++++-- celt/tests/test_unit_mathops.c | 2 +- celt/tests/test_unit_rotation.c | 2 +- celt_sources.mk | 3 ++ configure.ac | 56 ++++++++++++++++++++++----- silk/SigProc_FIX.h...

...x86_celt_map.c" is included Viswanath Puttagunta (1): armv7: celt_pitch_xcorr: Introduce ARM neon intrinsics Makefile.am | 12 ++ celt/arm/arm_celt_map.c | 15 ++- celt/arm/celt_neon_intr.c | 249 +++++++++++++++++++++++++++++++++++++++ celt/arm/pitch_arm.h | 13 +- celt/cpu_support.h | 3 +- celt/pitch.h | 6 +- celt/tests/test_unit_mathops.c | 6 +- celt/tests/test_unit_rotation.c | 6 +- celt_sources.mk | 3 + configure.ac | 83 +++++++++++-- 10 file...

...algorithm in celt_pitch_xcorr_arm.s Viswanath Puttagunta (1): armv7: celt_pitch_xcorr: Introduce ARM neon intrinsics Makefile.am | 11 ++ celt/arm/arm_celt_map.c | 15 ++- celt/arm/celt_neon_intr.c | 242 +++++++++++++++++++++++++++++++++++++++ celt/arm/pitch_arm.h | 13 ++- celt/cpu_support.h | 3 +- celt/pitch.h | 6 +- celt/tests/test_unit_mathops.c | 10 +- celt/tests/test_unit_rotation.c | 9 +- celt_sources.mk | 3 + configure.ac | 77 +++++++++++-- 10 fil...

...s neon intrinsics. --- Makefile.am | 23 +++++++++++ celt/_kiss_fft_guts.h | 4 +- celt/arch.h | 4 +- celt/arm/arm_celt_map.c | 15 +++++++- celt/arm/celt_neon_intr.c | 81 +++++++++++++++++++++++++++++++++++++++ celt/arm/pitch_arm.h | 15 +++++++- celt/pitch.h | 17 ++++++-- celt/tests/test_unit_mathops.c | 2 +- celt/tests/test_unit_rotation.c | 2 +- celt_sources.mk | 3 ++ configure.ac | 56 ++++++++++++++++++++++----- silk/SigProc_FIX.h...

...ARMv7 as well, turning this on only for aarch64 at the moment since there is a fixed point asm implementation for ARMv7 neon. Signed-off-by: Viswanath Puttagunta <viswanath.puttagunta at linaro.org> --- celt/arm/celt_neon_intr.c | 268 ++++++++++++++++++++++++++++++++++++++++++++++ celt/arm/pitch_arm.h | 10 ++ configure.ac | 6 ++ 3 files changed, 284 insertions(+) diff --git a/celt/arm/celt_neon_intr.c b/celt/arm/celt_neon_intr.c index 47dce15..be978a0 100644 --- a/celt/arm/celt_neon_intr.c +++ b/celt/arm/celt_neon_intr.c @@ -249,4 +249,272 @@ void celt_pitch_xcorr_float...

...sion */ > + for (; i < max_pitch; i++) { > + float sum = 0; > + float *yi = _y+i; > + for (j = 0; j < len; j++) > + sum += _x[i]*yi[i]; > + xcorr[i] = sum; > + } This loop can still be largely vectorized. Any reason not to do so? > +} > diff --git a/celt/arm/pitch_arm.h b/celt/arm/pitch_arm.h > index a07f8ac..f5adc48 100644 > --- a/celt/arm/pitch_arm.h > +++ b/celt/arm/pitch_arm.h > @@ -52,6 +52,19 @@ opus_val32 celt_pitch_xcorr_edsp(const opus_val16 *_x, const opus_val16 *_y, > ((void)(arch),PRESUME_NEON(celt_pitch_xcorr)(_x, _y, xcorr, len,...

...d-point implementation of xcorr_kernel. Makefile.am | 9 +-- celt/arch.h | 2 + celt/arm/arm_celt_map.c | 22 ++++++- celt/arm/celt_neon_intr.c | 61 ++++++++++++++++++- celt/arm/fixed_arm64.h | 75 ++++++++++++++++++++++++ celt/arm/pitch_arm.h | 62 +++++++++++++++++++- celt/pitch.h | 20 ------- celt_headers.mk | 1 + configure.ac | 23 +++++++- silk/NSQ.c | 55 +++++------------ silk/NSQ.h | 97 ++++++++++++++++++++++++++++++ s...

...ARMv7 as well, turning this on only for aarch64 at the moment since there is a fixed point asm implementation for ARMv7 neon. Signed-off-by: Viswanath Puttagunta <viswanath.puttagunta at linaro.org> --- celt/arm/celt_neon_intr.c | 268 ++++++++++++++++++++++++++++++++++++++++++++++ celt/arm/pitch_arm.h | 10 ++ configure.ac | 6 ++ 3 files changed, 284 insertions(+) diff --git a/celt/arm/celt_neon_intr.c b/celt/arm/celt_neon_intr.c index 47dce15..be978a0 100644 --- a/celt/arm/celt_neon_intr.c +++ b/celt/arm/celt_neon_intr.c @@ -249,4 +249,272 @@ void celt_pitch_xcorr_float...

...--> typo --> OPUS_ARM_NEON_INTR Viswanath Puttagunta (1): armv7: celt_pitch_xcorr: Introduce ARM neon intrinsics Makefile.am | 12 ++ celt/arm/arm_celt_map.c | 15 ++- celt/arm/celt_neon_intr.c | 256 +++++++++++++++++++++++++++++++++++++++ celt/arm/pitch_arm.h | 13 +- celt/cpu_support.h | 3 +- celt/pitch.h | 6 +- celt/tests/test_unit_mathops.c | 9 +- celt/tests/test_unit_rotation.c | 9 +- celt_sources.mk | 3 + configure.ac | 83 +++++++++++-- 10 file...

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 my previous patch set, I believe it should be safe to turn --enable-intrinsics on by default in Opus's configure script. Jonathan...

...sum += _x[i]*yi[i]; >> + xcorr[i] = sum; >> + } > > This loop can still be largely vectorized. Any reason not to do so? Should have put TBD in the comments..I will try to get this done in the re-spin. > >> +} >> diff --git a/celt/arm/pitch_arm.h b/celt/arm/pitch_arm.h >> index a07f8ac..f5adc48 100644 >> --- a/celt/arm/pitch_arm.h >> +++ b/celt/arm/pitch_arm.h >> @@ -52,6 +52,19 @@ opus_val32 celt_pitch_xcorr_edsp(const opus_val16 *_x, const opus_val16 *_y, >> ((void)(arch),PRESUME_NEON(celt_pitch_xcorr)(...

...e checks are also supported to make sure this optimization is only enabled when the compiler supports neon intrinsics. --- Makefile.am | 12 ++ celt/arm/arm_celt_map.c | 15 ++- celt/arm/celt_neon_intr.c | 249 +++++++++++++++++++++++++++++++++++++++ celt/arm/pitch_arm.h | 13 +- celt/cpu_support.h | 3 +- celt/pitch.h | 6 +- celt/tests/test_unit_mathops.c | 6 +- celt/tests/test_unit_rotation.c | 6 +- celt_sources.mk | 3 + configure.ac | 83 +++++++++++-- 10 file...