search for: cpu_arm

...am +++ b/Makefile.am @@ -38,6 +38,12 @@ CELT_SOURCES += $(CELT_SOURCES_SSE) endif endif +if OPUS_ARM_NEON_INTR +noinst_LTLIBRARIES = libarmneon.la +libarmneon_la_SOURCES = $(CELT_SOURCES_ARM_NEON_INTR) +libarmneon_la_CPPFLAGS = $(OPUS_ARM_NEON_INTR_CPPFLAGS) -I$(top_srcdir)/include +endif + if CPU_ARM CELT_SOURCES += $(CELT_SOURCES_ARM) SILK_SOURCES += $(SILK_SOURCES_ARM) @@ -59,6 +65,9 @@ include opus_headers.mk libopus_la_SOURCES = $(CELT_SOURCES) $(SILK_SOURCES) $(OPUS_SOURCES) libopus_la_LDFLAGS = -no-undefined -version-info @OPUS_LT_CURRENT@:@OPUS_LT_REVISION@:@OPUS_LT_AGE@ libopus_la_...

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,

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

--- Makefile.am | 4 ++-- configure.ac | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Makefile.am b/Makefile.am index 4d3a888..d256b45 100644 --- a/Makefile.am +++ b/Makefile.am @@ -47,7 +47,7 @@ if CPU_ARM CELT_SOURCES += $(CELT_SOURCES_ARM) SILK_SOURCES += $(SILK_SOURCES_ARM) -if OPUS_ARM_NEON_INTR +if HAVE_ARM_NEON_INTR CELT_SOURCES += $(CELT_SOURCES_ARM_NEON_INTR) endif @@ -294,7 +294,7 @@ SSE4_1_OBJ = $(CELT_SOURCES_SSE4_1:.c=.lo) \ $(SSE4_1_OBJ) $(OPT_UNIT_TEST_OBJ): CFLAGS += $(OPUS_X8...

--- Makefile.am | 4 ++-- configure.ac | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Makefile.am b/Makefile.am index 4d3a888..d256b45 100644 --- a/Makefile.am +++ b/Makefile.am @@ -47,7 +47,7 @@ if CPU_ARM CELT_SOURCES += $(CELT_SOURCES_ARM) SILK_SOURCES += $(SILK_SOURCES_ARM) -if OPUS_ARM_NEON_INTR +if HAVE_ARM_NEON_INTR CELT_SOURCES += $(CELT_SOURCES_ARM_NEON_INTR) endif @@ -294,7 +294,7 @@ SSE4_1_OBJ = $(CELT_SOURCES_SSE4_1:.c=.lo) \ $(SSE4_1_OBJ) $(OPT_UNIT_TEST_OBJ): CFLAGS += $(OPUS_X8...

...| 3 + configure.ac | 83 +++++++++++-- 10 files changed, 377 insertions(+), 19 deletions(-) create mode 100644 celt/arm/celt_neon_intr.c diff --git a/Makefile.am b/Makefile.am index e20f7b4..95323ca 100644 --- a/Makefile.am +++ b/Makefile.am @@ -41,6 +41,12 @@ endif if CPU_ARM CELT_SOURCES += $(CELT_SOURCES_ARM) SILK_SOURCES += $(SILK_SOURCES_ARM) + +if OPUS_ARM_NEON_INTR +CELT_SOURCES += $(CELT_SOURCES_ARM_NEON_INTR) +OPUS_ARM_NEON_INTR_CPPFLAGS = -mfpu=neon +endif + if OPUS_ARM_EXTERNAL_ASM nodist_libopus_la_SOURCES = $(CELT_SOURCES_ARM_ASM:.s=-gnu.S) BUILT_SOURCE...

...| 3 + configure.ac | 77 +++++++++++-- 10 files changed, 370 insertions(+), 19 deletions(-) create mode 100644 celt/arm/celt_neon_intr.c diff --git a/Makefile.am b/Makefile.am index e20f7b4..0687814 100644 --- a/Makefile.am +++ b/Makefile.am @@ -41,6 +41,11 @@ endif if CPU_ARM CELT_SOURCES += $(CELT_SOURCES_ARM) SILK_SOURCES += $(SILK_SOURCES_ARM) + +if OPUS_ARM_NEON_INTR +CELT_SOURCES += $(CELT_SOURCES_ARM_NEON_INTR) +endif + if OPUS_ARM_EXTERNAL_ASM nodist_libopus_la_SOURCES = $(CELT_SOURCES_ARM_ASM:.s=-gnu.S) BUILT_SOURCES = $(CELT_SOURCES_ARM_ASM:.s=-gnu.S) \ @@...

...| 3 + configure.ac | 83 +++++++++++-- 10 files changed, 390 insertions(+), 19 deletions(-) create mode 100644 celt/arm/celt_neon_intr.c diff --git a/Makefile.am b/Makefile.am index e20f7b4..be53754 100644 --- a/Makefile.am +++ b/Makefile.am @@ -41,6 +41,12 @@ endif if CPU_ARM CELT_SOURCES += $(CELT_SOURCES_ARM) SILK_SOURCES += $(SILK_SOURCES_ARM) + +if OPUS_ARM_NEON_INTR +CELT_SOURCES += $(CELT_SOURCES_ARM_NEON_INTR) +OPUS_ARM_NEON_INTR_CPPFLAGS = -mfpu=neon -O3 +endif + if OPUS_ARM_EXTERNAL_ASM nodist_libopus_la_SOURCES = $(CELT_SOURCES_ARM_ASM:.s=-gnu.S) BUILT_SO...

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

...| 83 +++++++++++-- > 10 files changed, 377 insertions(+), 19 deletions(-) > create mode 100644 celt/arm/celt_neon_intr.c > > diff --git a/Makefile.am b/Makefile.am > index e20f7b4..95323ca 100644 > --- a/Makefile.am > +++ b/Makefile.am > @@ -41,6 +41,12 @@ endif > if CPU_ARM > CELT_SOURCES += $(CELT_SOURCES_ARM) > SILK_SOURCES += $(SILK_SOURCES_ARM) > + > +if OPUS_ARM_NEON_INTR > +CELT_SOURCES += $(CELT_SOURCES_ARM_NEON_INTR) > +OPUS_ARM_NEON_INTR_CPPFLAGS = -mfpu=neon > +endif > + > if OPUS_ARM_EXTERNAL_ASM > nodist_libopus_la_SOURCES...

...elt/tests/test_unit_rotation.c | 5 ++- configure.ac | 93 +++++++++++++++++++---------------------- 12 files changed, 67 insertions(+), 67 deletions(-) diff --git a/Makefile.am b/Makefile.am index 3a75740..8bd7447 100644 --- a/Makefile.am +++ b/Makefile.am @@ -47,7 +47,7 @@ if CPU_ARM CELT_SOURCES += $(CELT_SOURCES_ARM) SILK_SOURCES += $(SILK_SOURCES_ARM) -if OPUS_ARM_NEON_INTR +if HAVE_ARM_NEON_INTR CELT_SOURCES += $(CELT_SOURCES_ARM_NEON_INTR) endif @@ -286,7 +286,7 @@ SSE4_1_OBJ = $(CELT_SOURCES_SSE4_1:.c=.lo) \ $(SSE4_1_OBJ) $(OPT_UNIT_TEST_OBJ): CFLAGS += $(OPUS_X8...

...pus_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) 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,...

...pus_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) 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,...

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 in-line with algorithm in celt_pitch_xcorr_arm.s Viswanath Puttagunta

...amp;OPUS_ARCHMASK])(_x, _y, \ > - xcorr, len, max_pitch)) > + xcorr, len, max_pitch, arch)) > +#endif > + And this. > diff --git a/configure.ac b/configure.ac > index 9b2f51f..09657b6 100644 > --- a/configure.ac > +++ b/configure.ac > @@ -198,12 +198,11 @@ cpu_arm=no > > AS_IF([test x"${enable_asm}" = x"yes"],[ > inline_optimization="No ASM for your platform, please send patches" > + OPUS_ARM_NEON_INTR_CPPFLAGS= > case $host_cpu in > arm*) > - dnl Currently we only have asm fo...

...gaard.com> --- configure.ac | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/configure.ac b/configure.ac index 0ba4a80..443362f 100644 --- a/configure.ac +++ b/configure.ac @@ -333,9 +333,9 @@ AS_IF([test x"${enable_asm}" = x"yes"],[ AM_CONDITIONAL([CPU_ARM], [test "$cpu_arm" = "yes"]) AM_CONDITIONAL([OPUS_ARM_INLINE_ASM], - [test x"${inline_optimization:0:3}" = x"ARM"]) + [test x"${inline_optimization%% *}" = x"ARM"]) AM_CONDITIONAL([OPUS_ARM_EXTERNAL_ASM], - [test x"${asm_op...

configure uses invalid shell syntax. (Ah, it's a bash extension.) Here's a portable fix. --- configure.ac.orig Thu Dec 5 00:26:45 2013 +++ configure.ac Sun Dec 15 17:32:25 2013 @@ -333,9 +333,9 @@ AS_IF([test x"${enable_asm}" = x"yes"],[ AM_CONDITIONAL([CPU_ARM], [test "$cpu_arm" = "yes"]) AM_CONDITIONAL([OPUS_ARM_INLINE_ASM], - [test x"${inline_optimization:0:3}" = x"ARM"]) + [expr x"${inline_optimization}" : x"ARM" >/dev/null]) AM_CONDITIONAL([OPUS_ARM_EXTERNAL_ASM], - [test x&quo...

...)"], >> + []) >> + ],[]) >> ;; >> esac >> -],[ >> - inline_optimization="disabled" >> - asm_optimization="disabled" >> -]) >> +],[]) >> >> AM_CONDITIONAL([CPU_ARM], [test "$cpu_arm" = "yes"]) >> AM_CONDITIONAL([OPUS_ARM_INLINE_ASM], >> @@ -349,6 +384,9 @@ AM_CONDITIONAL([OPUS_ARM_INLINE_ASM], >> AM_CONDITIONAL([OPUS_ARM_EXTERNAL_ASM], >> [test x"${asm_optimization%% *}" = x"ARM"]) >...

...pus_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 defined(OPUS_ARM_MAY_HAVE_NEON) +#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);...