search for: celt_sig

...lt/bands.c b/celt/bands.c index bbe8a4c..1ab24aa 100644 --- a/celt/bands.c +++ b/celt/bands.c @@ -92,10 +92,11 @@ static int bitexact_log2tan(int isin,int icos) #ifdef FIXED_POINT /* Compute the amplitude (sqrt energy) in each of the bands */ -void compute_band_energies(const CELTMode *m, const celt_sig *X, celt_ener *bandE, int end, int C, int LM) +void compute_band_energies(const CELTMode *m, const celt_sig *X, celt_ener *bandE, int end, int C, int LM, int arch) { int i, c, N; const opus_int16 *eBands = m->eBands; + (void)arch; N = m->shortMdctSize<<LM; c=0; do {...

I realize this is ancient history, but I am trying to compile Ver 8.1 (from the download page) using Fixed Point and am getting compile errors as follows: argument of type "celt_sig *" is incompatible with parameter of type "celt_int16 *" libcelt81_orig_DSP/libcelt celt.c line 321 1304524612394 19769 argument of type "celt_sig *" is incompatible with parameter of type "celt_int16 *" libcelt81_orig_DSP/libcelt celt....

..., _shift, _stride, _arch) #endif /* OPUS_HAVE_RTCD */ #endif /* !defined(FIXED_POINT) && defined(HAVE_ARM_NE10) */ diff --git a/celt/celt_decoder.c b/celt/celt_decoder.c index 4304a3e..304f334 100644 --- a/celt/celt_decoder.c +++ b/celt/celt_decoder.c @@ -278,8 +278,9 @@ void deemphasis(celt_sig *in[], opus_val16 *pcm, int N, int C, int downsample, c static #endif void celt_synthesis(const CELTMode *mode, celt_norm *X, celt_sig * out_syn[], - opus_val16 *oldBandE, int start, int effEnd, int C, int CC, int isTransient, - int LM, int downsample, int silence) +...

..., _shift, _stride, _arch) #endif /* OPUS_HAVE_RTCD */ #endif /* !defined(FIXED_POINT) && defined(HAVE_ARM_NE10) */ diff --git a/celt/celt_decoder.c b/celt/celt_decoder.c index 4304a3e..304f334 100644 --- a/celt/celt_decoder.c +++ b/celt/celt_decoder.c @@ -278,8 +278,9 @@ void deemphasis(celt_sig *in[], opus_val16 *pcm, int N, int C, int downsample, c static #endif void celt_synthesis(const CELTMode *mode, celt_norm *X, celt_sig * out_syn[], - opus_val16 *oldBandE, int start, int effEnd, int C, int CC, int isTransient, - int LM, int downsample, int silence) +...

Hello All, I extended the libNE10 optimizations for float towards mdct_backwards/opus_ifft. I am able to get about 14.26% improvement for Decode use case now on my Beaglebone Black. Please see [1] for measurements. Questions 1. Since this patch needs to go in after Encode [2] patch) should I submit this as patch series? 2. Since Jonathan Lennox posted intrinsics cleanup [3] patch, should

...C int opus_custom_encoder_init(CELTEncoder *st, const CELTMod st->force_intra = 0; st->complexity = 5; st->lsb_depth=24; + st->arch = opus_select_arch(); opus_custom_encoder_ctl(st, OPUS_RESET_STATE); @@ -1014,7 +1017,7 @@ static int run_prefilter(CELTEncoder *st, celt_sig *in, celt_sig *prefilter_mem, VARDECL(opus_val16, pitch_buf); ALLOC(pitch_buf, (COMBFILTER_MAXPERIOD+N)>>1, opus_val16); - pitch_downsample(pre, pitch_buf, COMBFILTER_MAXPERIOD+N, CC); + pitch_downsample(pre, pitch_buf, COMBFILTER_MAXPERIOD+N, CC, st->arch);...

...ibcelt/celt.c | 24 +++++++++++++++++------- 1 files changed, 17 insertions(+), 7 deletions(-) diff --git a/libcelt/celt.c b/libcelt/celt.c index 31d35f8..287c720 100644 --- a/libcelt/celt.c +++ b/libcelt/celt.c @@ -1137,6 +1137,7 @@ int celt_encode_with_ec_float(CELTEncoder * restrict st, const celt_sig * pcm, i ec_enc_icdf(enc, prefilter_tapset, tapset_icdf, 2); else prefilter_tapset = 0; + fprintf(stderr,"pitch_index: %4i gain %0.2f tapset: %i\n",pitch_index,gain1,prefilter_tapset); gain1 = QCONST16(0.09375f,15)*(qg+1); p...

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 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]

...celt_encoder.c +++ b/celt/celt_encoder.c @@ -414,7 +414,8 @@ int patch_transient_decision(opus_val16 *newE, opus_val16 *oldE, int nbEBands, /** Apply window and compute the MDCT for all sub-frames and all channels in a frame */ static void compute_mdcts(const CELTMode *mode, int shortBlocks, celt_sig * OPUS_RESTRICT in, - celt_sig * OPUS_RESTRICT out, int C, int CC, int LM, int upsample) + celt_sig * OPUS_RESTRICT out, int C, int CC, int LM, int upsample, + int arch) { const int overlap = mode->overlap; int N...

...celt_encoder.c +++ b/celt/celt_encoder.c @@ -414,7 +414,8 @@ int patch_transient_decision(opus_val16 *newE, opus_val16 *oldE, int nbEBands, /** Apply window and compute the MDCT for all sub-frames and all channels in a frame */ static void compute_mdcts(const CELTMode *mode, int shortBlocks, celt_sig * OPUS_RESTRICT in, - celt_sig * OPUS_RESTRICT out, int C, int CC, int LM, int upsample) + celt_sig * OPUS_RESTRICT out, int C, int CC, int LM, int upsample, + int arch) { const int overlap = mode->overlap; int N...

...celt_encoder.c +++ b/celt/celt_encoder.c @@ -414,7 +414,8 @@ int patch_transient_decision(opus_val16 *newE, opus_val16 *oldE, int nbEBands, /** Apply window and compute the MDCT for all sub-frames and all channels in a frame */ static void compute_mdcts(const CELTMode *mode, int shortBlocks, celt_sig * OPUS_RESTRICT in, - celt_sig * OPUS_RESTRICT out, int C, int CC, int LM, int upsample) + celt_sig * OPUS_RESTRICT out, int C, int CC, int LM, int upsample, + int arch) { const int overlap = mode->overlap; int N...

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

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

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

...11, g12); + comb_filter_const(y+i, x+i, T1, N-i, g10, g11, g12, arch); } #endif /* OVERRIDE_comb_filter */ diff --git a/celt/celt.h b/celt/celt.h index b196751..a423b95 100644 --- a/celt/celt.h +++ b/celt/celt.h @@ -201,7 +201,17 @@ void celt_preemphasis(const opus_val16 * OPUS_RESTRICT pcmp, celt_sig * OPUS_RES void comb_filter(opus_val32 *y, opus_val32 *x, int T0, int T1, int N, opus_val16 g0, opus_val16 g1, int tapset0, int tapset1, - const opus_val16 *window, int overlap); + const opus_val16 *window, int overlap, int arch); + +#ifdef NON_STATIC_COMB_FILTER_CONST_C +void c...

...11, g12); + comb_filter_const(y+i, x+i, T1, N-i, g10, g11, g12, arch); } #endif /* OVERRIDE_comb_filter */ diff --git a/celt/celt.h b/celt/celt.h index b196751..a423b95 100644 --- a/celt/celt.h +++ b/celt/celt.h @@ -201,7 +201,17 @@ void celt_preemphasis(const opus_val16 * OPUS_RESTRICT pcmp, celt_sig * OPUS_RES void comb_filter(opus_val32 *y, opus_val32 *x, int T0, int T1, int N, opus_val16 g0, opus_val16 g1, int tapset0, int tapset1, - const opus_val16 *window, int overlap); + const opus_val16 *window, int overlap, int arch); + +#ifdef NON_STATIC_COMB_FILTER_CONST_C +void c...