search for: armopts

Hi, Thank you for your response. I pulled yesterday to commit da97db1ca1f92592af3534c9a2596da0e9a009ca, added a bunch of more defines to my compile options, and assembled & linked in armopts.s,celt_pitch_xcorr_arm.s. Performance jumped up from about 4.8 Mb/s to 5.3 Mb/s on the same device, so it is improvement. Not sure what other tweaks there would be to try, but if it could match the tremolo decoder, we could probably throw that out entirely which would be very nice. Thanks! Dan O...

Hello all. I have got problem with compiling theorarm. I followed instructions posted earlier on this list (http://permalink.gmane.org/gmane.comp.multimedia.ogg.theora.devel/3066) but still got messages about undefined symbol: oc_frag_recon_inter2_arm. I have fixed Makefile.am by adding arm/ARMbitwise2.s \ arm/ARMdecode.s \ arm/ARMfilter.s \ arm/ARMfrag.s \ arm/ARMidct.s \ arm/ARMint.h \

...LT_SOURCES_ARM_ASM:%.s=%-gnu.S): $(top_srcdir)/celt/arm/arm2gnu.pl # convert ARM asm to GNU as format %-gnu.S: $(top_srcdir)/%.s - $(top_srcdir)/celt/arm/arm2gnu.pl < $< > $@ + $(top_srcdir)/celt/arm/arm2gnu.pl @ARM2GNU_PARAMS@ < $< > $@ # For autoconf-modified sources (e.g., armopts.s) %-gnu.S: %.s $(top_srcdir)/celt/arm/arm2gnu.pl < $< > $@ diff --git a/celt/arm/arm2gnu.pl b/celt/arm/arm2gnu.pl index e313904..46e7d0a 100755 --- a/celt/arm/arm2gnu.pl +++ b/celt/arm/arm2gnu.pl @@ -26,6 +26,8 @@ my $bigend; # little/big endian my $nxstack; +my $apple = 0; +my $s...

Hi everyone, I have lately been evaluating the performance of various audio decoders, particularly for ARM devices (Cortex A8 / A9). The context is audio playback in a game engine, and thus decoding performance is of particular interest. Looking at Opus versus Vorbis on a Cortex A9 smartphone, the numbers look approximately like this: Vorbis (tremolo decoder) 9.3 Mb PCM/s Opus (libopus 1.1)

This avoids having to use the public symbol name when jumping here, on platforms where the public symbols have an underscore prefix. --- This avoids having to add heuristics for adding prefixes to symbols in jumps to local labels as well. --- celt/arm/celt_pitch_xcorr_arm.s | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/celt/arm/celt_pitch_xcorr_arm.s

...ate mode 100644 tests/test_unit_optimization.c diff --git a/.gitignore b/.gitignore index 33127c9..05d0582 100644 --- a/.gitignore +++ b/.gitignore @@ -49,6 +49,7 @@ tests/test_opus_api tests/test_opus_decode tests/test_opus_encode tests/test_opus_padding +tests/test_unit_optimization celt/arm/armopts.s celt/dump_modes/dump_modes celt/tests/test_unit_cwrs32 diff --git a/Makefile.am b/Makefile.am index 7a69114..2bfb923 100644 --- a/Makefile.am +++ b/Makefile.am @@ -84,9 +84,36 @@ pkginclude_HEADERS = include/opus.h include/opus_multistream.h include/opus_type noinst_HEADERS = $(OPUS_HEAD) $(SI...

...rm/pitch_arm.h \ +celt/arm/kiss_fft_neon.h \ celt/x86/pitch_sse.h \ celt/x86/x86cpu.h diff --git a/celt_sources.mk b/celt_sources.mk index 20b1b1b..b27bf3e 100644 --- a/celt_sources.mk +++ b/celt_sources.mk @@ -32,3 +32,6 @@ celt/arm/celt_pitch_xcorr_arm.s CELT_AM_SOURCES_ARM_ASM = \ celt/arm/armopts.s.in + +CELT_SOURCES_ARM_NEON = \ +celt/arm/kiss_fft_neon.c diff --git a/configure.ac b/configure.ac index 9b2f51f..488295f 100644 --- a/configure.ac +++ b/configure.ac @@ -193,6 +193,20 @@ AC_ARG_ENABLE([intrinsics], [AS_HELP_STRING([--enable-intrinsics], [Enable intrinsics optimizations (onl...

...s.mk b/celt_sources.mk index 20b1b1b..3d4deca 100644 --- a/celt_sources.mk +++ b/celt_sources.mk @@ -30,5 +30,8 @@ celt/arm/arm_celt_map.c CELT_SOURCES_ARM_ASM = \ celt/arm/celt_pitch_xcorr_arm.s +CELT_SOURCES_ARM_NEON_INTR = \ +celt/arm/celt_neon_intr.c + CELT_AM_SOURCES_ARM_ASM = \ celt/arm/armopts.s.in 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" +...

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,

...t;arm/celt_neon_intr.c" +#endif #include "arm/arm_celt_map.c" #endif diff --git a/celt_sources.mk b/celt_sources.mk index 20b1b1b..29ec937 100644 --- a/celt_sources.mk +++ b/celt_sources.mk @@ -32,3 +32,6 @@ celt/arm/celt_pitch_xcorr_arm.s CELT_AM_SOURCES_ARM_ASM = \ celt/arm/armopts.s.in + +CELT_SOURCES_ARM_NEON_INTR = \ +celt/arm/celt_neon_intr.c diff --git a/configure.ac b/configure.ac index 9b2f51f..1e6ab53 100644 --- a/configure.ac +++ b/configure.ac @@ -190,14 +190,14 @@ AC_ARG_ENABLE([rtcd], [enable_rtcd=yes]) AC_ARG_ENABLE([intrinsics], - [AS_HELP_STRING([--e...

...\ + || defined(OPUS_ARM_NEON_INTR)) #include "arm/arm_celt_map.c" #endif diff --git a/celt_sources.mk b/celt_sources.mk index 20b1b1b..29ec937 100644 --- a/celt_sources.mk +++ b/celt_sources.mk @@ -32,3 +32,6 @@ celt/arm/celt_pitch_xcorr_arm.s CELT_AM_SOURCES_ARM_ASM = \ celt/arm/armopts.s.in + +CELT_SOURCES_ARM_NEON_INTR = \ +celt/arm/celt_neon_intr.c diff --git a/configure.ac b/configure.ac index 9b2f51f..6ad4a70 100644 --- a/configure.ac +++ b/configure.ac @@ -190,14 +190,14 @@ AC_ARG_ENABLE([rtcd], [enable_rtcd=yes]) AC_ARG_ENABLE([intrinsics], - [AS_HELP_STRING([--e...

...\ + || defined(OPUS_ARM_NEON_INTR)) #include "arm/arm_celt_map.c" #endif diff --git a/celt_sources.mk b/celt_sources.mk index 20b1b1b..29ec937 100644 --- a/celt_sources.mk +++ b/celt_sources.mk @@ -32,3 +32,6 @@ celt/arm/celt_pitch_xcorr_arm.s CELT_AM_SOURCES_ARM_ASM = \ celt/arm/armopts.s.in + +CELT_SOURCES_ARM_NEON_INTR = \ +celt/arm/celt_neon_intr.c diff --git a/configure.ac b/configure.ac index 9b2f51f..1e6ab53 100644 --- a/configure.ac +++ b/configure.ac @@ -190,14 +190,14 @@ AC_ARG_ENABLE([rtcd], [enable_rtcd=yes]) AC_ARG_ENABLE([intrinsics], - [AS_HELP_STRING([--e...

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:

Hello, This patch introduces ARM NEON Intrinsics to optimize kf_bfly4 routine in celt part of libopus. Using NEON optimized kf_bfly4(_neon) routine helped improve performance of opus_fft_impl function by about 21.4%. The end use case was decoding a music opus ogg file. The end use case saw performance improvement of about 4.47%. This patch has 2 components i. Actual neon code to improve

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

..."arm/arm_celt_map.c" > #endif > > diff --git a/celt_sources.mk b/celt_sources.mk > index 20b1b1b..29ec937 100644 > --- a/celt_sources.mk > +++ b/celt_sources.mk > @@ -32,3 +32,6 @@ celt/arm/celt_pitch_xcorr_arm.s > > CELT_AM_SOURCES_ARM_ASM = \ > celt/arm/armopts.s.in > + > +CELT_SOURCES_ARM_NEON_INTR = \ > +celt/arm/celt_neon_intr.c > diff --git a/configure.ac b/configure.ac > index 9b2f51f..1e6ab53 100644 > --- a/configure.ac > +++ b/configure.ac > @@ -190,14 +190,14 @@ AC_ARG_ENABLE([rtcd], > [enable_rtcd=yes]) > >...

...io support not found -- not compiling player_example checking for PNG... no checking for library containing ftime... none required checking for getopt_long... no configure: creating ./config.status config.status: creating Makefile config.status: creating lib/Makefile config.status: creating lib/arm/armopts.s config.status: creating include/Makefile config.status: creating include/theora/Makefile config.status: creating examples/Makefile config.status: creating doc/Makefile config.status: creating doc/Doxyfile config.status: creating doc/spec/Makefile config.status: creating tests/Makefile config.stat...

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

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

Hi all, This is Linfeng Zhang from Google. I'll work on ARM NEON optimization in the next few months. I'm submitting 2 patches in the following couple of emails, which have the new created celt_fir_neon(). I revised celt_fir_c() to not pass in argument "mem" in Patch 1. If there are concerns to this change, please let me know. Many thanks to your comments. Linfeng Zhang