search for: max_pitch

...arm.h +++ b/celt/arm/pitch_arm.h @@ -32,59 +32,89 @@ # if defined(FIXED_POINT) -#if defined(CPU_AARCH64) -#define OVERRIDE_PITCH_XCORR (1) -opus_val32 celt_pitch_xcorr_fixed_neon(const opus_val16 *_x, const opus_val16 *_y, - opus_val32 *xcorr, int len, int max_pitch); -#define celt_pitch_xcorr(_x, _y, xcorr, len, max_pitch, arch) \ - ((void)(arch), celt_pitch_xcorr_fixed_neon(_x, _y, xcorr, len, max_pitch)) - -#else /* End CPU_AARCH64. Begin CPU_ARM */ +#if defined(OPUS_ARM_MAY_HAVE_NEON) || defined(OPUS_ARM_MAY_HAVE_EDSP) +/* ARM assembly */ -# if define...

...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 > > -# if !defined(OPUS_HAVE_RTCD) > +# if (defined(OPUS_ARM_MAY_HAVE_NEON) || \ > + defined(OPUS_ARM_MAY_HAVE_MEDIA) || \ > + defined(OPUS_ARM_MAY_HAVE_EDSP)) && \ > + (!defined(OPUS_HAVE_RTCD) || \ > + defined(OPUS_ARM_PRESUME_NEON) || \ > +...

...vaddq_f32(SUMM[0], SUMM[1]); > + SUMM[2] = vaddq_f32(SUMM[2], SUMM[3]); > + SUMM[0] = vaddq_f32(SUMM[0], SUMM[2]); > + > + vst1q_f32(sum, SUMM[0]); > +} > + > +void celt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val16 *_y, > + opus_val32 *xcorr, int len, int max_pitch, int arch) { arch is unused. There's no reason to pass it here. If we're here, we know what the arch is. > + int i, j; > + > + celt_assert(max_pitch > 0); > + celt_assert((((unsigned char *)_x-(unsigned char *)NULL)&3)==0); > + > + for (i = 0; i < (max_pitch-3...

...32(SUMM[2], SUMM[3]); >> + SUMM[0] = vaddq_f32(SUMM[0], SUMM[2]); >> + >> + vst1q_f32(sum, SUMM[0]); >> +} >> + >> +void celt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val16 *_y, >> + opus_val32 *xcorr, int len, int max_pitch, int arch) { > > arch is unused. There's no reason to pass it here. If we're here, we > know what the arch is. > >> + int i, j; >> + >> + celt_assert(max_pitch > 0); >> + celt_assert((((unsigned char *)_x-(unsigned char *)NULL)&3)==0);...

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

...M[0], YY[0], XX_2, 0); + } + + SUMM[0] = vaddq_f32(SUMM[0], SUMM[1]); + SUMM[2] = vaddq_f32(SUMM[2], SUMM[3]); + SUMM[0] = vaddq_f32(SUMM[0], SUMM[2]); + + vst1q_f32(sum, SUMM[0]); +} + +void celt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val16 *_y, + opus_val32 *xcorr, int len, int max_pitch, int arch) { + int i, j; + + celt_assert(max_pitch > 0); + celt_assert((((unsigned char *)_x-(unsigned char *)NULL)&3)==0); + + for (i = 0; i < (max_pitch-3); i += 4) { + xcorr_kernel_neon_float((float *)_x, (float *)_y+i, + (float *)xcorr+i, len); + } + + /* In case max_pitch isn...

...(xi++); + YY_2 = vld1_dup_s16(yi++); + SUMM = vmlal_s16(SUMM, XX_2, YY_2); + len--; + } + vst1q_lane_s32(sum, SUMM, 0); +} + +opus_val32 celt_pitch_xcorr_fixed_neon(const opus_val16 *_x, const opus_val16 *_y, + opus_val32 *xcorr, int len, int max_pitch) { + int i; + celt_assert(max_pitch > 0); + celt_assert((((unsigned char *)_x-(unsigned char *)NULL)&3)==0); + int max_corr = 1; + + for (i = 0; i < (max_pitch-3); i += 4) { + xcorr_kernel_neon_fixed((const int16_t *)_x, (const int16_t *)_y+i, +...

...(xi++); + YY_2 = vld1_dup_s16(yi++); + SUMM = vmlal_s16(SUMM, XX_2, YY_2); + len--; + } + vst1q_lane_s32(sum, SUMM, 0); +} + +opus_val32 celt_pitch_xcorr_fixed_neon(const opus_val16 *_x, const opus_val16 *_y, + opus_val32 *xcorr, int len, int max_pitch) { + int i; + celt_assert(max_pitch > 0); + celt_assert((((unsigned char *)_x-(unsigned char *)NULL)&3)==0); + int max_corr = 1; + + for (i = 0; i < (max_pitch-3); i += 4) { + xcorr_kernel_neon_fixed((const int16_t *)_x, (const int16_t *)_y+i, +...

...RM_MAY_HAVE_NEON_INTR)) +extern +# if defined(FIXED_POINT) +opus_val32 +# else +void +# endif +(*const CELT_PITCH_XCORR_IMPL[OPUS_ARCHMASK+1])(const opus_val16 *, + const opus_val16 *, opus_val32 *, int, int); + +# define OVERRIDE_PITCH_XCORR +# define celt_pitch_xcorr(_x, _y, xcorr, len, max_pitch, arch) \ + ((*CELT_PITCH_XCORR_IMPL[(arch)&OPUS_ARCHMASK])(_x, _y, \ + xcorr, len, max_pitch)) +# endif + #endif diff --git a/celt/pitch.h b/celt/pitch.h index dde48c8..bbe790e 100644 --- a/celt/pitch.h +++ b/celt/pitch.h @@ -186,24 +186,6 @@ celt_pitch_xcorr_c(const opus_val16 *_x, co...

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

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,

...XX_2 = vld1_dup_f32(xi); + YY_2 = vld1_dup_f32(yi); + SUMM_2[0] = vmla_f32(SUMM_2[0], XX_2, YY_2); + } + + vst1_lane_f32(sum, SUMM_2[0], 0); +} + +void celt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val16 *_y, + opus_val32 *xcorr, int len, int max_pitch) { + int i; + celt_assert(max_pitch > 0); + celt_assert((((unsigned char *)_x-(unsigned char *)NULL)&3)==0); + + for (i = 0; i < (max_pitch-3); i += 4) { + xcorr_kernel_neon_float((float *)_x, (float *)_y+i, + (float *)xcorr+i, len); + } + + /...

...= vadd_f32(tv.val[0], tv.val[1]); + + vst1_lane_f32(&sumi, tv.val[0], 0); + for (i = 0; i < len; i++) + sumi += xi[i] * yi[i]; + *sum = sumi; +} + +void celt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val16 *_y, + opus_val32 *xcorr, int len, int max_pitch) { + int i; + celt_assert(max_pitch > 0); + celt_assert((((unsigned char *)_x-(unsigned char *)NULL)&3)==0); + + for (i = 0; i < (max_pitch-3); i += 4) { + xcorr_kernel_neon_float((float *)_x, (float *)_y+i, + (float *)xcorr+i, len); + } + + /...

...XX_2 = vld1_dup_f32(xi); + YY_2 = vld1_dup_f32(yi); + SUMM_2[0] = vmla_f32(SUMM_2[0], XX_2, YY_2); + } + + vst1_lane_f32(sum, SUMM_2[0], 0); +} + +void celt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val16 *_y, + opus_val32 *xcorr, int len, int max_pitch) { + int i; + celt_assert(max_pitch > 0); + celt_assert((((unsigned char *)_x-(unsigned char *)NULL)&3)==0); + + for (i = 0; i < (max_pitch-3); i += 4) { + xcorr_kernel_neon_float((float *)_x, (float *)_y+i, + (float *)xcorr+i, len); + } + + /...

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:

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

...2 = vld1_dup_f32(yi); > + SUMM_2[0] = vmla_f32(SUMM_2[0], XX_2, YY_2); > + } > + > + vst1_lane_f32(sum, SUMM_2[0], 0); > +} > + > +void celt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val16 *_y, > + opus_val32 *xcorr, int len, int max_pitch) { > + int i; > + celt_assert(max_pitch > 0); > + celt_assert((((unsigned char *)_x-(unsigned char *)NULL)&3)==0); > + > + for (i = 0; i < (max_pitch-3); i += 4) { > + xcorr_kernel_neon_float((float *)_x, (float *)_y+i, > + (f...

.../* 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 -# if !defined(OPUS_HAVE_RTCD) +# if (defined(OPUS_ARM_MAY_HAVE_NEON) || \ + defined(OPUS_ARM_MAY_HAVE_MEDIA) || \ + defined(OPUS_ARM_MAY_HAVE_EDSP)) && \ + (!defined(OPUS_HAVE_RTCD) || \ + defined(OPUS_ARM_PRESUME_NEON) || \ + (defined(OPUS_ARM_PRESUME_MEDIA) &&...

...rm/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 >> >> -# if !defined(OPUS_HAVE_RTCD) >> +# if (defined(OPUS_ARM_MAY_HAVE_NEON) || \ >> + defined(OPUS_ARM_MAY_HAVE_MEDIA) || \ >> + defined(OPUS_ARM_MAY_HAVE_EDSP)) && \ >> + (!defined(OPUS_HAVE_RTCD) || \ >> + defined(OPU...