search for: celt_pitch_xcorr_edsp

....S:262:2: error: unknown directive .type xcorr_kernel_edsp, %function; xcorr_kernel_edsp: @ PROC ^ celt/arm/celt_pitch_xcorr_arm-gnu.S:343:2: error: unknown directive .size xcorr_kernel_edsp, .-xcorr_kernel_edsp @ ENDP ^ celt/arm/celt_pitch_xcorr_arm-gnu.S:345:2: error: unknown directive .type celt_pitch_xcorr_edsp, %function; celt_pitch_xcorr_edsp: @ PROC ^ celt/arm/celt_pitch_xcorr_arm-gnu.S:544:2: error: unknown directive .size celt_pitch_xcorr_edsp, .-celt_pitch_xcorr_edsp @ ENDP ^ celt/arm/celt_pitch_xcorr_arm-gnu.S:549:23: error: unexpected token in '.section' directive .section .note.GNU...

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

...itch); # endif -# if defined(OPUS_ARM_MAY_HAVE_MEDIA) -# define celt_pitch_xcorr_media MAY_HAVE_EDSP(celt_pitch_xcorr) -# endif +#if defined(OPUS_ARM_MAY_HAVE_MEDIA) +# define celt_pitch_xcorr_media MAY_HAVE_EDSP(celt_pitch_xcorr) +#endif # if defined(OPUS_ARM_MAY_HAVE_EDSP) 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) -# define OVERRIDE_PITCH_XCORR (1) +#if defined(OPUS_ARM_PRESUME_NEON) + +#define OVERRIDE_PITCH_XCORR (1) # define celt_pitch_xcorr(_x, _y, xcorr, len, max_...

...K+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..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)...

...sion 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); >> # endif >> >> -# if !defined(OPUS_HAVE_RTCD) >> +# if (defined(OPUS_ARM_MAY_HAVE_NEON) || \ >> + defined(OPUS_ARM_MAY_HAVE_MEDIA) || \ >> + defined(OPU...

...; + y++; + } + + vst1q_s32(sum, a); +} + +#else /* * Function: xcorr_kernel_neon_float * --------------------------------- diff --git a/celt/arm/pitch_arm.h b/celt/arm/pitch_arm.h index bd41774..545c115 100644 --- a/celt/arm/pitch_arm.h +++ b/celt/arm/pitch_arm.h @@ -56,7 +56,36 @@ opus_val32 celt_pitch_xcorr_edsp(const opus_val16 *_x, const opus_val16 *_y, # define OVERRIDE_PITCH_XCORR (1) # define celt_pitch_xcorr(_x, _y, xcorr, len, max_pitch, arch) \ ((void)(arch),PRESUME_NEON(celt_pitch_xcorr)(_x, _y, xcorr, len, max_pitch)) -# endif + +#endif + +# if defined(OPUS_ARM_MAY_HAVE_NEON_INTR) + +v...

...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, max_pitch)) > # endif > > -# endif > +#else /* Start !FIXED_POINT */ > +/* Float case */ > +#if defined(OPUS_ARM_NEON_INTR) > +void celt_pitch_xcorr_float_ne...

...t 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)(_x, _y, xcorr, len, max_pitch)) >> # endif >> >> -# endif >> +#else /* Start !FIXED_POINT */ >> +/* Float case */ >> +#if defined(OPUS_ARM_NEON_INTR) >>...

...+260,4 @@ void clt_mdct_backward_float_neon(const mdct_lookup *l, } RESTORE_STACK; } +#endif /* !defined(FIXED_POINT) */ diff --git a/celt/arm/pitch_arm.h b/celt/arm/pitch_arm.h index 8626ed7..344186b 100644 --- a/celt/arm/pitch_arm.h +++ b/celt/arm/pitch_arm.h @@ -57,7 +57,7 @@ opus_val32 celt_pitch_xcorr_edsp(const opus_val16 *_x, const opus_val16 *_y, #if defined(OPUS_ARM_MAY_HAVE_NEON_INTR) void celt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val16 *_y, opus_val32 *xcorr, int len, int max_pitch); -#if !defined(OPUS_HAVE_RTCD) || defined(OPUS_ARM_PRESUME...

...t_pitch_xcorr_fixed_neon(_x, _y, xcorr, len, max_pitch)) + +#else /* End CPU_AARCH64. Begin CPU_ARM */ + # if defined(OPUS_ARM_MAY_HAVE_NEON) opus_val32 celt_pitch_xcorr_neon(const opus_val16 *_x, const opus_val16 *_y, opus_val32 *xcorr, int len, int max_pitch); @@ -51,6 +60,7 @@ opus_val32 celt_pitch_xcorr_edsp(const opus_val16 *_x, const opus_val16 *_y, # define celt_pitch_xcorr(_x, _y, xcorr, len, max_pitch, arch) \ ((void)(arch),PRESUME_NEON(celt_pitch_xcorr)(_x, _y, xcorr, len, max_pitch)) # endif +#endif /* End CPU_ARM */ #else /* Start !FIXED_POINT */ /* Float case */ diff --git a/config...

...t_pitch_xcorr_fixed_neon(_x, _y, xcorr, len, max_pitch)) + +#else /* End CPU_AARCH64. Begin CPU_ARM */ + # if defined(OPUS_ARM_MAY_HAVE_NEON) opus_val32 celt_pitch_xcorr_neon(const opus_val16 *_x, const opus_val16 *_y, opus_val32 *xcorr, int len, int max_pitch); @@ -51,6 +60,7 @@ opus_val32 celt_pitch_xcorr_edsp(const opus_val16 *_x, const opus_val16 *_y, # define celt_pitch_xcorr(_x, _y, xcorr, len, max_pitch, arch) \ ((void)(arch),PRESUME_NEON(celt_pitch_xcorr)(_x, _y, xcorr, len, max_pitch)) # endif +#endif /* End CPU_ARM */ #else /* Start !FIXED_POINT */ /* Float case */ diff --git a/config...

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

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

...i++) { + float sum = 0; + float *yi = _y+i; + for (j = 0; j < len; j++) + sum += _x[i]*yi[i]; + xcorr[i] = sum; + } +} 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, max_pitch)) # endif -# endif +#else /* Start !FIXED_POINT */ +/* Float case */ +#if defined(OPUS_ARM_NEON_INTR) +void celt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val1...

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,

...xcorr_kernel_neon_float_process1((float *)_x, (float *)_y+i, + (float *)xcorr+i, len); + } +} diff --git a/celt/arm/pitch_arm.h b/celt/arm/pitch_arm.h index a07f8ac..125d1bc 100644 --- a/celt/arm/pitch_arm.h +++ b/celt/arm/pitch_arm.h @@ -52,6 +52,17 @@ 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, max_pitch)) # endif -# endif +#else /* Start !FIXED_POINT */ +/* Float case */ +#if defined(OPUS_ARM_NEON_INTR) +void celt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val1...

...xcorr3to1_kernel_neon_float((float *)_x, (float *)_y+i, + (float *)xcorr+i, len); + } +} diff --git a/celt/arm/pitch_arm.h b/celt/arm/pitch_arm.h index a07f8ac..125d1bc 100644 --- a/celt/arm/pitch_arm.h +++ b/celt/arm/pitch_arm.h @@ -52,6 +52,17 @@ 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, max_pitch)) # endif -# endif +#else /* Start !FIXED_POINT */ +/* Float case */ +#if defined(OPUS_ARM_NEON_INTR) +void celt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val1...

...xcorr_kernel_neon_float_process1((float *)_x, (float *)_y+i, + (float *)xcorr+i, len); + } +} diff --git a/celt/arm/pitch_arm.h b/celt/arm/pitch_arm.h index a07f8ac..125d1bc 100644 --- a/celt/arm/pitch_arm.h +++ b/celt/arm/pitch_arm.h @@ -52,6 +52,17 @@ 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, max_pitch)) # endif -# endif +#else /* Start !FIXED_POINT */ +/* Float case */ +#if defined(OPUS_ARM_NEON_INTR) +void celt_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val1...

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

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: