search for: silk_head

--- silk/arm/macros_arm64.h | 39 +++++++++++++++++++++++++++++++++++++++ silk/macros.h | 4 ++++ silk_headers.mk | 1 + 3 files changed, 44 insertions(+) create mode 100644 silk/arm/macros_arm64.h diff --git a/silk/arm/macros_arm64.h b/silk/arm/macros_arm64.h new file mode 100644 index 0000000..ed03041 --- /dev/null +++ b/silk/arm/macros_arm64.h @@ -0,0 +1,39 @@ +/****************************...

--- silk/SigProc_FIX.h | 4 +++ silk/arm/SigProc_FIX_arm64.h | 46 ++++++++++++++++++++++++++++++ silk/arm/macros_arm64.h | 66 ++++++++++++++++++++++++++++++++++++++++++++ silk/macros.h | 4 +++ silk_headers.mk | 2 ++ 5 files changed, 122 insertions(+) create mode 100644 silk/arm/SigProc_FIX_arm64.h create mode 100644 silk/arm/macros_arm64.h diff --git a/silk/SigProc_FIX.h b/silk/SigProc_FIX.h index b632994..0a6969d 100644 --- a/silk/SigProc_FIX.h +++ b/silk/SigProc_FIX.h @@ -603,6...

--- configure.ac | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/configure.ac b/configure.ac index 90a06c8..adcb969 100644 --- a/configure.ac +++ b/configure.ac @@ -503,6 +503,26 @@ AS_IF([test x"$enable_intrinsics" = x"yes"],[ [rtcd_support="$rtcd_support (NE10)"]) ]) + OPUS_CHECK_INTRINSICS( +

--- configure.ac | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/configure.ac b/configure.ac index f52d2c2..e1a6e9b 100644 --- a/configure.ac +++ b/configure.ac @@ -190,7 +190,7 @@ AC_ARG_ENABLE([rtcd], [enable_rtcd=yes]) AC_ARG_ENABLE([intrinsics], - [AS_HELP_STRING([--disable-intrinsics], [Disable intrinsics optimizations for ARM(float) X86(fixed)])],, +

...| 37 ++++++++-------------- silk/NSQ.h | 70 +++++++++++++++++++++++++++++++++++++++++ silk/arm/NSQ_neon.c | 64 +++++++++++++++++++++++++++++++++++++ silk/arm/NSQ_neon.h | 91 +++++++++++++++++++++++++++++++++++++++++++++++++++++ silk/x86/NSQ_sse.c | 2 +- silk/x86/main_sse.h | 3 +- silk_headers.mk | 2 ++ silk_sources.mk | 2 ++ 9 files changed, 250 insertions(+), 29 deletions(-) create mode 100644 silk/NSQ.h create mode 100644 silk/arm/NSQ_neon.c create mode 100644 silk/arm/NSQ_neon.h diff --git a/Makefile.am b/Makefile.am index a7e7465..d819f38 100644 --- a/Makefile.am...

...| 37 ++++++++-------------- silk/NSQ.h | 70 +++++++++++++++++++++++++++++++++++++++++ silk/arm/NSQ_neon.c | 64 +++++++++++++++++++++++++++++++++++++ silk/arm/NSQ_neon.h | 91 +++++++++++++++++++++++++++++++++++++++++++++++++++++ silk/x86/NSQ_sse.c | 2 +- silk/x86/main_sse.h | 3 +- silk_headers.mk | 2 ++ silk_sources.mk | 2 ++ 9 files changed, 248 insertions(+), 28 deletions(-) create mode 100644 silk/NSQ.h create mode 100644 silk/arm/NSQ_neon.c create mode 100644 silk/arm/NSQ_neon.h diff --git a/Makefile.am b/Makefile.am index d256b45..36762c2 100644 --- a/Makefile.am...

...++++++++++++++++++++ silk/arm/SigProc_FIX_arm64.h | 46 +++++++++++++++ silk/arm/macros_arm64.h | 66 +++++++++++++++++++++ silk/macros.h | 4 ++ silk/mips/NSQ_del_dec_mipsr1.h | 3 +- silk/x86/NSQ_sse.c | 2 +- silk/x86/main_sse.h | 3 +- silk_headers.mk | 4 ++ silk_sources.mk | 2 + 22 files changed, 685 insertions(+), 111 deletions(-) create mode 100644 celt/arm/fixed_arm64.h create mode 100644 silk/NSQ.h create mode 100644 silk/arm/NSQ_neon.c create mode 100644 silk/arm/NSQ_neon.h create mode 100644...

...| 8 +- silk/arm/LPC_analysis_filter_arm.h | 60 +++++++ silk/arm/LPC_analysis_filter_neon_intr.c | 176 +++++++++++++++++++++ silk/arm/arm_silk_map.c | 14 ++ .../test_unit_optimization_LPC_analysis_filter.c | 85 ++++++++++ silk_headers.mk | 1 + silk_sources.mk | 1 + tests/test_unit_optimization.c | 2 + 9 files changed, 348 insertions(+), 7 deletions(-) create mode 100644 silk/arm/LPC_analysis_filter_arm.h create mode 100644 sil...

...++++++++++++++++++++ silk/arm/SigProc_FIX_arm64.h | 46 +++++++++++++++ silk/arm/macros_arm64.h | 66 +++++++++++++++++++++ silk/macros.h | 4 ++ silk/mips/NSQ_del_dec_mipsr1.h | 3 +- silk/x86/NSQ_sse.c | 2 +- silk/x86/main_sse.h | 3 +- silk_headers.mk | 4 ++ silk_sources.mk | 2 + 23 files changed, 732 insertions(+), 97 deletions(-) create mode 100644 celt/arm/fixed_arm64.h create mode 100644 silk/NSQ.h create mode 100644 silk/arm/NSQ_neon.c create mode 100644 silk/arm/NSQ_neon.h create mode 100644 s...

...ned.c | 2 +- silk/main.h | 6 +- silk/stereo_LR_to_MS.c | 7 ++- silk/stereo_find_predictor.c | 5 +- .../test_unit_optimization_inner_prod_aligned.c | 63 +++++++++++++++++++++ silk_headers.mk | 1 + silk_sources.mk | 1 + tests/test_unit_optimization.c | 2 + 13 files changed, 222 insertions(+), 10 deletions(-) create mode 100644 silk/arm/inner_prod_aligned_arm.h create mode 100644 silk/...

...| 40 +++++------- silk/arm/NSQ_neon.c | 135 +++++++++++++++++++++++++++++++++++++++++ silk/arm/NSQ_neon.h | 109 +++++++++++++++++++++++++++++++++ silk/mips/NSQ_del_dec_mipsr1.h | 3 +- silk/x86/NSQ_sse.c | 2 +- silk/x86/main_sse.h | 3 +- silk_headers.mk | 2 + silk_sources.mk | 2 + 16 files changed, 521 insertions(+), 84 deletions(-) create mode 100644 silk/NSQ.h create mode 100644 silk/arm/NSQ_neon.c create mode 100644 silk/arm/NSQ_neon.h -- 2.5.4 (Apple Git-61)

...++++++ silk/arm/NSQ_neon.h | 101 ++++++++++++++++++++++++++++++++ silk/arm/macros_arm64.h | 39 +++++++++++++ silk/macros.h | 22 ++++--- silk/mips/NSQ_del_dec_mipsr1.h | 3 +- silk/x86/NSQ_sse.c | 2 +- silk/x86/main_sse.h | 3 +- silk_headers.mk | 3 + silk_sources.mk | 2 + 22 files changed, 655 insertions(+), 115 deletions(-) create mode 100644 celt/arm/fixed_arm64.h create mode 100644 silk/NSQ.h create mode 100644 silk/arm/NSQ_neon.c create mode 100644 silk/arm/NSQ_neon.h create mode 100644 s...

Hi all, I'm sending patch "Optimize silk_warped_autocorrelation_FIX() for ARM NEON" in an separate email. It is based on Tim’s aarch64v8 branch https://git.xiph.org/?p=users/tterribe/opus.git;a=shortlog;h=refs/heads/aarch64v8 Thanks for your comments. Linfeng

I rebased my previous 3 patches to the current master with minor changes. Patches 1 to 3 replace all my previous submitted patches. Patches 4 and 5 are new. Thanks, Linfeng Zhang

...OPUS_LT_CURRENT@:@OPUS_LT_REVISION@:@OPUS_LT_AGE@ libopus_la_LIBADD = $(LIBM) +if ARMv7_NEON_INTRINSICS_FLOAT +libopus_la_LIBADD += ./libneon.la +endif + pkginclude_HEADERS = include/opus.h include/opus_multistream.h include/opus_types.h include/opus_defines.h noinst_HEADERS = $(OPUS_HEAD) $(SILK_HEAD) $(CELT_HEAD) @@ -97,6 +107,9 @@ celt_tests_test_unit_cwrs32_LDADD = $(LIBM) celt_tests_test_unit_dft_SOURCES = celt/tests/test_unit_dft.c celt_tests_test_unit_dft_LDADD = $(LIBM) +if ARMv7_NEON_INTRINSICS_FLOAT +celt_tests_test_unit_dft_LDADD += ./libneon.la +endif celt_tests_test_unit_entr...

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

...ts.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) $(SILK_HEAD) $(CELT_HEAD) if EXTRA_PROGRAMS -noinst_PROGRAMS = opus_demo repacketizer_demo opus_compare tests/test_opus_api tests/test_opus_encode tests/test_opus_decode tests/test_opus_padding celt/tests/test_unit_cwrs32 celt/tests/test_unit_dft celt/tests/test_unit_entropy celt/tests/test_unit_laplace cel...

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