search for: entcod

...bcelt/Makefile.am +++ b/libcelt/Makefile.am @@ -11,17 +11,17 @@ TESTS = match-test.sh noinst_SCRIPTS = match-test.sh -lib_LTLIBRARIES = libcelt.la +lib_LTLIBRARIES = libcelt at LIBCELT_SUFFIX@.la # Sources for compilation in the library -libcelt_la_SOURCES = bands.c celt.c cwrs.c ecintrin.h entcode.c \ +libcelt at LIBCELT_SUFFIX@_la_SOURCES = bands.c celt.c cwrs.c ecintrin.h entcode.c \ entdec.c entenc.c header.c kfft_single.c kiss_fft.c kiss_fftr.c laplace.c mdct.c \ modes.c pitch.c psy.c quant_bands.c rangedec.c rangeenc.c rate.c \ vq.c #noinst_HEADERS = -libcelt_la_LDFLAGS = -v...

...hout some porting effort, so there's no real reason to maintain the typedefs separately. Hopefully we'll replace these all again somedate with a common set of Opus typedefs, but for now this will do. This fixes an issue caused by commit 6c8acbf1, which moved the ec_ilog() prototype from entcode.h to ecintrin.h, where the ec_uint32 typedef was not yet available. Thanks to John Ridges for the report. --- libcelt/bands.c | 2 +- libcelt/bands.h | 2 +- libcelt/celt.c | 12 ++++++------ libcelt/cwrs.c | 2 +- libcelt/cwrs.h | 2 +- libcelt/eci...

Hi, Bjoern's solution of adding the line: #pragma intrinsic(_BitScanReverse) after the: # include<intrin.h> worked for me, so it solves my debug build problem. However, you still might want to change the location of ec_ilog's prototype in entcode.h for those platforms that don't have an intrinsic like that. Cheers, John Ridges

...elt/quant_pitch.h diff --git a/libcelt/Makefile.am b/libcelt/Makefile.am index d34c1dc..7c574cc 100644 --- a/libcelt/Makefile.am +++ b/libcelt/Makefile.am @@ -16,7 +16,7 @@ lib_LTLIBRARIES = libcelt.la # Sources for compilation in the library libcelt_la_SOURCES = bands.c celt.c cwrs.c ecintrin.h entcode.c \ entdec.c entenc.c header.c kfft_single.c kiss_fft.c kiss_fftr.c laplace.c mdct.c \ - modes.c pitch.c psy.c quant_bands.c quant_pitch.c rangedec.c rangeenc.c rate.c \ + modes.c pitch.c psy.c quant_bands.c rangedec.c rangeenc.c rate.c \ vq.c #noinst_HEADERS = @@ -26,8 +26,8 @@ libcelt_la_...

...MAY_HAVE_NEON_INTR)) extern # if defined(FIXED_POINT) opus_val32 diff --git a/celt/tests/test_unit_dft.c b/celt/tests/test_unit_dft.c index 9fbcdc4..e17e26f 100644 --- a/celt/tests/test_unit_dft.c +++ b/celt/tests/test_unit_dft.c @@ -45,8 +45,7 @@ #include "mathops.c" #include "entcode.c" -#if defined(OPUS_HAVE_RTCD) && \ - (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_MAY_HAVE_NEON_INTR)) +#if defined(OPUS_ARM_MAY_HAVE_NEON_INTR) || defined(OPUS_ARM_ASM) #include "arm/armcpu.c" #if !defined(FIXED_POINT) #if defined(HAVE_ARM_NE10) diff --git a/ce...

...lt;<(bits)))) /** Negate a 16-bit value */ #define NEG16(x) (-(x)) diff -Naupr opus-1.3.1-vanilla/celt/mathops.h opus-1.3.1/celt/mathops.h --- opus-1.3.1-vanilla/celt/mathops.h 2018-09-26 14:49:41 +0800 +++ opus-1.3.1/celt/mathops.h 2019-05-27 17:17:49 +0800 @@ -38,7 +38,7 @@ #include "entcode.h" #include "os_support.h" -#define PI 3.141592653f +#define PI 3.14159265358979f /* Multiplies two 16-bit fractional values. Bit-exactness of this macro is important */ #define FRAC_MUL16(a,b) ((16384+((opus_int32)(opus_int16)(a)*(opus_int16)(b)))>>15) diff -Naupr opus...

...ne10_twiddles_60[15], +}; +#endif /*end NE10_FFT_PARAMS48000_960*/ diff --git a/celt/tests/test_unit_dft.c b/celt/tests/test_unit_dft.c index 57db0e3..8996f17 100644 --- a/celt/tests/test_unit_dft.c +++ b/celt/tests/test_unit_dft.c @@ -45,6 +45,16 @@ #include "mathops.c" #include "entcode.c" +#if defined(OPUS_HAVE_RTCD) && \ + (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_NEON_INTR)) +#include "arm/armcpu.c" +#if defined(HAVE_ARM_NE10) +#include "arm/celt_ne10_fft.c" +#include "arm/arm_celt_ne10_fft_map.c" +#endif +#elif defined(OPU...

Hi All, Since I continue to base my work on top of Jonathan's patch, and my previous Ne10 fft/ifft/mdct_forward/backward patches, I thought it would be better to just post all new patches as a patch series. Please let me know if anyone disagrees with this approach. You can see wip branch of all latest patches at https://git.linaro.org/people/viswanath.puttagunta/opus.git Branch:

Hi All, As per Timothy's suggestion, disabling mdct_forward for fixed point. Only effects armv7,armv8: Extend fixed fft NE10 optimizations to mdct Rest of patches are same as in [1] For reference, latest wip code for opus is at [2] Still working with NE10 team at ARM to get corner cases of mdct_forward. Will update with another patch when issue in NE10 gets fixed. Regards, Vish [1]:

Hi All, Changes from RFC v2 [1] armv7,armv8: Extend fixed fft NE10 optimizations to mdct - Overflow issue fixed by Phil at ARM. Ne10 wip at [2]. Should be upstream soon. - So, re-enabled using fixed fft for mdct_forward which was disabled in RFCv2 armv7,armv8: Optimize fixed point fft using NE10 library - Thanks to Jonathan Lennox, fixed some build fixes on iOS and some copy-paste errors Rest

Hi Timothy, As I mentioned earlier [1], I now fixed compile issues with fixed point and resubmitting the patch. I also have new patch that does intrinsics optimizations for celt_pitch_xcorr targetting aarch64. You can find my latest work-in-progress branch at [2] For reference, you can use the Ne10 pre-built libraries at [3] Note that I am working with Phil at ARM to get my patch at [4]

Hello Timothy / Jean-Marc / opus-dev, This patch series is follow up on work I posted on [1]. In addition to what was posted on [1], this patch series mainly integrates Fixed point FFT implementations in NE10 library into opus. You can view my opus wip code at [2]. Note that while I found some issues both with the NE10 library(fixed fft) and with Linaro toolchain (armv8 intrinsics), the work

...lt/dump_modes/Makefile @@ -19,7 +19,8 @@ INCLUDES += -I$(NE10_INCDIR) -DHAVE_ARM_NE10 -DOPUS_ARM_PRESUME_NEON_INTR LIBDIR = -l:$(NE10_LIBDIR)/libNE10.so SOURCES += ../arm/celt_ne10_fft.c \ dump_modes_arm_ne10.c \ - ../arm/armcpu.c + ../arm/armcpu.c \ + ../entcode.c endif all: dump_modes diff --git a/celt/dump_modes/dump_modes_arch.h b/celt/dump_modes/dump_modes_arch.h index 1436926..59073ee 100644 --- a/celt/dump_modes/dump_modes_arch.h +++ b/celt/dump_modes/dump_modes_arch.h @@ -28,11 +28,17 @@ #ifndef DUMP_MODE_ARCH_H #define DUMP_MODE_ARCH_H +#i...

Hello opus-dev, I've been cooking up this patchset to integrate NE10 library into opus. Current patchset focuses on encode use case mainly effecting performance of clt_mdct_forward() and opus_fft() (for float only) Glad to report the following on Encode use case: (Measured on my Beaglebone Black Cortex-A8 board) - Performance improvement for encode use case ~= 12.34% (Based on time -p

..._C #define TEST_UNIT_DFT_C #include "stack_alloc.h" +#include "pitch.h" +#include "celt_lpc.c" +#include "pitch.c" #include "kiss_fft.h" #include "kiss_fft.c" +#include "mdct.c" #include "mathops.c" #include "entcode.c" +#if defined(OPUS_HAVE_RTCD) && \ + (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_NEON_INTR)) +#include "arm/armcpu.c" +#if defined(HAVE_ARM_NE10) +#include "arm/celt_ne10_fft.c" +#include "arm/celt_ne10_mdct.c" +#include "arm/celt_neon_int...

..._C #define TEST_UNIT_DFT_C #include "stack_alloc.h" +#include "pitch.h" +#include "celt_lpc.c" +#include "pitch.c" #include "kiss_fft.h" #include "kiss_fft.c" +#include "mdct.c" #include "mathops.c" #include "entcode.c" +#if defined(OPUS_HAVE_RTCD) && \ + (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_NEON_INTR)) +#include "arm/armcpu.c" +#if defined(HAVE_ARM_NE10) +#include "arm/celt_ne10_fft.c" +#include "arm/celt_ne10_mdct.c" +#endif +#include "arm/celt_...

...state_float32_60, +}; + +#endif /* end NE10_FFT_PARAMS48000_960 */ diff --git a/celt/tests/test_unit_dft.c b/celt/tests/test_unit_dft.c index 57db0e3..991ece3 100644 --- a/celt/tests/test_unit_dft.c +++ b/celt/tests/test_unit_dft.c @@ -45,6 +45,23 @@ #include "mathops.c" #include "entcode.c" +#if defined(OPUS_HAVE_RTCD) && \ + (defined(OPUS_ARM_ASM) || defined(OPUS_ARM_NEON_INTR)) +#include "arm/armcpu.c" +#if !defined(FIXED_POINT) +#if defined(HAVE_ARM_NE10) +#include "mdct.c" +#include "arm/celt_ne10_fft.c" +#include "arm/...

Changes from RFC PATCH v3 - Just rebased on tip - For all else, please see notes from RFC PATCH v3 at http://lists.xiph.org/pipermail/opus/2015-March/002902.html - latest wip opus tree/branch https://git.linaro.org/people/viswanath.puttagunta/Ne10.git branch: rfcv4_final_fft_ne10 Viswanath Puttagunta (1): armv7(float): Optimize encode usecase using NE10 library Makefile.am

Changes from RFC PATCH v1: - passing arch parameter explicitly - reduced stack usage by ~3.5K by using scaled NE10 fft version - moved all optimization array functions to arm_celt_map.c - Other cleanups pointed out by Timothy Phil, As you mentioned earlier, could you please address all compile and linker errors/warnings coming out of Ne10 library? You can find my working Ne10 repo at [1] You

Changes from RFC PATCH v2 - fixed compile issue when just compiling for --enable-intrinsics for ARMv7 without NE10 - Notes for NE10: - All compile/link warnings are now in upstream NE10 - Only patch pending upstream in NE10 is the one that needs to add -funsafe-math-optimizations for ARMv7 targets. - Phil Wang @ ARM is working on getting this fixed. - Note that even without