search for: _y

...t.h index c2e67b7..71414b1 100644 --- a/usr/kinit/kinit.h +++ b/usr/kinit/kinit.h @@ -36,17 +36,17 @@ ssize_t freadfile(FILE *f, char **pptr); * "unnecessary" pointer comparison. * From the Linux kernel. */ -#define min(x,y) ({ \ - typeof(x) _x = (x); \ - typeof(y) _y = (y); \ - (void) (&_x == &_y); \ - _x < _y ? _x : _y; }) +#define min(x, y) ({ \ + typeof(x) _x = (x); \ + typeof(y) _y = (y); \ + (void) (&_x == &_y); \ + _x < _y ? _x : _y; }) -#define max(x,y) ({ \ - typeof(x) _x = (...

...h b/celt/arm/pitch_arm.h index fe76f8d..fa2dd17 100644 --- a/celt/arm/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_MA...

..._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) ||...

...], 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) { 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...

...l _f .align 16, 0x90 _f: # @f # BB#0: movl $-800, %eax # imm = 0xFFFFFFFFFFFFFCE0 movsd _DA, %xmm0 .align 16, 0x90 LBB0_1: # =>This Inner Loop Header: Depth=1 movsd _X+800(%eax), %xmm1 mulsd %xmm0, %xmm1 movsd _Y+800(%eax), %xmm2 subsd %xmm1, %xmm2 movsd %xmm2, _Y+800(%eax) addl $8, %eax jne LBB0_1 # BB#2: xorl %eax, %eax ret .data .globl _DA # @DA .align 8 _DA: .quad 4599075939470750515 # double 3.000000e-01 .comm _Y,800,3 # @Y .comm _X,800,3...

...[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) { > > 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); >> +...

Hi all, this patch series makes the necessary changes to make sure that the current ARM hypercall ABI can be used as-is on 64 bit ARM platforms: - it defines xen_ulong_t as uint64_t on ARM; - it introduces a new macro to handle guest pointers, called XEN_GUEST_HANDLE_PARAM (that has size 4 bytes on aarch and is going to have size 8 bytes on aarch64); - it replaces all the occurrences of

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

Hello, Is it possible somehow to get mouse coordinates without using the event mechanism ? I need to get the current mouse position to initialize some div position, but not at page load Tarek _______________________________________________ Rails-spinoffs mailing list Rails-spinoffs-1W37MKcQCpIf0INCOvqR/iCwEArCW2h5@public.gmane.org http://lists.rubyonrails.org/mailman/listinfo/rails-spinoffs

...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_neon(const opus_val16 *_x, const opus_val16 *_y, (const float32_t *)_y+i, (float32_t *)xcorr+i, len); } } +#else /* FIXED POINT */ + +/* + * Function: xcorr_kernel_neon_fixed + * --------------------------------- + * Computes 8 correlation values and stores them in sum[8] + */ +static void xcorr_kernel_neon_fixed(const int16_t...

...------------- 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_pitch_xcorr_float_neon(const opus_val16 *_x, const opus_val16 *_y, #endif #endif /* end !FIXED_POINT */ + +/*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)) +extern +# if defined(FIXED_POINT) +opus_val32 +# else +void +# endif +(*const CELT_P...

...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_neon(const opus_val16 *_x, const opus_val16 *_y, (const float32_t *)_y+i, (float32_t *)xcorr+i, len); } } +#else /* FIXED POINT */ + +/* + * Function: xcorr_kernel_neon_fixed + * --------------------------------- + * Computes 8 correlation values and stores them in sum[8] + */ +static void xcorr_kernel_neon_fixed(const int16_t...

...X_2, 0); + SUMM[0] = vmlaq_lane_f32(SUMM[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 *)xco...

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, I have the following LLVM IR. ----Snip--- %1 = getelementptr inbounds %struct._X, %struct._X* %0, i64 0, i32 3 %2 = load %struct._X*, %struct._X** %1, align 8, !tbaa !10 .... ..... ....... %3 = bitcast %struct._Y** %1 to i8** store i8* null, i8** %3, align 8, !tbaa !9 !9 = !{!7, !7, i64 0} !7 = !{!"omnipotent char", !8, i64 0} !8 = !{!"Simple C/C++ TBAA"} ----Snip---- Load inst above is trying to access a field of _X which is a self recursive pointer to same struct _X. Store puts a nu...

...t;- lmer(.D ~ offset(log(.Y)) + (1|pcid2) + educy + agri, male, poisson) ------------------------------------------------------------------------------------------- In Stata, I type: ------------------------------------------------------------------------------------------- xtpois _D educy agri, e(_Y) i(pcid2) ------------------------------------------------------------------------------------------- Results using R look like: ------------------------------------------------------------------------------------------- ... Random effects: Groups Name Variance Std.Dev. pc...

...AX_H +#define NBDKIT_MINMAX_H + +#include <config.h> + +#ifdef HAVE_AUTO_TYPE + +/* __auto_type is a GCC extension, added in GCC 4.9 in 2014, and to + * Clang in 2015. + */ + +#define MIN(x, y) ({ \ + __auto_type _x = (x); \ + __auto_type _y = (y); \ + _x < _y ? _x : _y; \ + }) +#define MAX(x, y) ({ \ + __auto_type _x = (x); \ + __auto_type _y = (y); \ + _x > _y ? _x : _y; \ + })...

...AX_H +#define NBDKIT_MINMAX_H + +#include <config.h> + +#ifdef HAVE_AUTO_TYPE + +/* __auto_type is a GCC extension, added in GCC 4.9 in 2014, and to + * Clang in 2015. + */ + +#define MIN(x, y) ({ \ + __auto_type _x = (x); \ + __auto_type _y = (y); \ + _x < _y ? _x : _y; \ + }) +#define MAX(x, y) ({ \ + __auto_type _x = (x); \ + __auto_type _y = (y); \ + _x > _y ? _x : _y; \ + })...

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,