|
|
|
|
OBJS += x86/constants.o \
|
|
|
|
|
|
|
|
|
|
# subsystems
|
|
|
|
|
OBJS-$(CONFIG_AC3DSP) += x86/ac3dsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_AUDIODSP) += x86/audiodsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_BLOCKDSP) += x86/blockdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_BSWAPDSP) += x86/bswapdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_DCT) += x86/dct_init.o
|
|
|
|
|
OBJS-$(CONFIG_DIRAC_DECODER) += x86/diracdsp_init.o \
|
|
|
|
|
x86/dirac_dwt_init.o
|
|
|
|
|
OBJS-$(CONFIG_FDCTDSP) += x86/fdctdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_FFT) += x86/fft_init.o
|
|
|
|
|
OBJS-$(CONFIG_FLACDSP) += x86/flacdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_FMTCONVERT) += x86/fmtconvert_init.o
|
|
|
|
|
OBJS-$(CONFIG_H263DSP) += x86/h263dsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_H264CHROMA) += x86/h264chroma_init.o
|
|
|
|
|
OBJS-$(CONFIG_H264DSP) += x86/h264dsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_H264PRED) += x86/h264_intrapred_init.o
|
|
|
|
|
OBJS-$(CONFIG_H264QPEL) += x86/h264_qpel.o
|
|
|
|
|
OBJS-$(CONFIG_HPELDSP) += x86/hpeldsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_LLAUDDSP) += x86/lossless_audiodsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_LLVIDDSP) += x86/lossless_videodsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_LLVIDENCDSP) += x86/lossless_videoencdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_HUFFYUVDSP) += x86/huffyuvdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_HUFFYUVENCDSP) += x86/huffyuvencdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_IDCTDSP) += x86/idctdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_LPC) += x86/lpc.o
|
|
|
|
|
OBJS-$(CONFIG_MDCT15) += x86/mdct15_init.o
|
|
|
|
|
OBJS-$(CONFIG_ME_CMP) += x86/me_cmp_init.o
|
|
|
|
|
OBJS-$(CONFIG_MPEGAUDIODSP) += x86/mpegaudiodsp.o
|
|
|
|
|
OBJS-$(CONFIG_MPEGVIDEO) += x86/mpegvideo.o \
|
|
|
|
|
x86/mpegvideodsp.o
|
|
|
|
|
OBJS-$(CONFIG_MPEGVIDEOENC) += x86/mpegvideoenc.o \
|
|
|
|
|
x86/mpegvideoencdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_PIXBLOCKDSP) += x86/pixblockdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_QPELDSP) += x86/qpeldsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_RV34DSP) += x86/rv34dsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_VC1DSP) += x86/vc1dsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_VIDEODSP) += x86/videodsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_VP3DSP) += x86/vp3dsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_VP8DSP) += x86/vp8dsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_XMM_CLOBBER_TEST) += x86/w64xmmtest.o
|
|
|
|
|
|
|
|
|
|
# decoders/encoders
|
|
|
|
|
OBJS-$(CONFIG_AAC_DECODER) += x86/aacpsdsp_init.o \
|
|
|
|
|
x86/sbrdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_AAC_ENCODER) += x86/aacencdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_ADPCM_G722_DECODER) += x86/g722dsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_ADPCM_G722_ENCODER) += x86/g722dsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_ALAC_DECODER) += x86/alacdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_APNG_DECODER) += x86/pngdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_CAVS_DECODER) += x86/cavsdsp.o
|
|
|
|
|
OBJS-$(CONFIG_CFHD_DECODER) += x86/cfhddsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_DCA_DECODER) += x86/dcadsp_init.o x86/synth_filter_init.o
|
|
|
|
|
OBJS-$(CONFIG_DNXHD_ENCODER) += x86/dnxhdenc_init.o
|
|
|
|
|
OBJS-$(CONFIG_EXR_DECODER) += x86/exrdsp_init.o
|
x86/opusdsp: implement FMA3 accelerated postfilter and deemphasis
58893 decicycles in deemphasis_c, 130548 runs, 524 skips
9475 decicycles in deemphasis_fma3, 130686 runs, 386 skips -> 6.21x speedup
24866 decicycles in postfilter_c, 65386 runs, 150 skips
5268 decicycles in postfilter_fma3, 65505 runs, 31 skips -> 4.72x speedup
Total decoder speedup: ~14%
Deemphasis SIMD based on the following unrolling:
const float c1 = CELT_EMPH_COEFF, c2 = c1*c1, c3 = c2*c1, c4 = c3*c1;
float state = coeff;
for (int i = 0; i < len; i += 4) {
y[0] = x[0] + c1*state;
y[1] = x[1] + c2*state + c1*x[0];
y[2] = x[2] + c3*state + c1*x[1] + c2*x[0];
y[3] = x[3] + c4*state + c1*x[2] + c2*x[1] + c3*x[0];
state = y[3];
y += 4;
x += 4;
}
6 years ago
|
|
|
OBJS-$(CONFIG_OPUS_DECODER) += x86/opusdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_OPUS_ENCODER) += x86/celt_pvq_init.o
|
|
|
|
|
OBJS-$(CONFIG_HEVC_DECODER) += x86/hevcdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_JPEG2000_DECODER) += x86/jpeg2000dsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_LSCR_DECODER) += x86/pngdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_MLP_DECODER) += x86/mlpdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_MPEG4_DECODER) += x86/xvididct_init.o
|
|
|
|
|
OBJS-$(CONFIG_PNG_DECODER) += x86/pngdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_PRORES_DECODER) += x86/proresdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_PRORES_LGPL_DECODER) += x86/proresdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_RV40_DECODER) += x86/rv40dsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_SBC_ENCODER) += x86/sbcdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_SVQ1_ENCODER) += x86/svq1enc_init.o
|
|
|
|
|
OBJS-$(CONFIG_TAK_DECODER) += x86/takdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_TRUEHD_DECODER) += x86/mlpdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_TTA_DECODER) += x86/ttadsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_TTA_ENCODER) += x86/ttaencdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_UTVIDEO_DECODER) += x86/utvideodsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_V210_DECODER) += x86/v210-init.o
|
|
|
|
|
OBJS-$(CONFIG_V210_ENCODER) += x86/v210enc_init.o
|
|
|
|
|
OBJS-$(CONFIG_VORBIS_DECODER) += x86/vorbisdsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_VP3_DECODER) += x86/hpeldsp_vp3_init.o
|
|
|
|
|
OBJS-$(CONFIG_VP6_DECODER) += x86/vp6dsp_init.o
|
|
|
|
|
OBJS-$(CONFIG_VP9_DECODER) += x86/vp9dsp_init.o \
|
|
|
|
|
x86/vp9dsp_init_10bpp.o \
|
|
|
|
|
x86/vp9dsp_init_12bpp.o \
|
|
|
|
|
x86/vp9dsp_init_16bpp.o
|
|
|
|
|
OBJS-$(CONFIG_WEBP_DECODER) += x86/vp8dsp_init.o
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# GCC inline assembly optimizations
|
|
|
|
|
# subsystems
|
|
|
|
|
MMX-OBJS-$(CONFIG_FDCTDSP) += x86/fdct.o
|
|
|
|
|
MMX-OBJS-$(CONFIG_VC1DSP) += x86/vc1dsp_mmx.o
|
|
|
|
|
|
|
|
|
|
# decoders/encoders
|
|
|
|
|
MMX-OBJS-$(CONFIG_SNOW_DECODER) += x86/snowdsp.o
|
|
|
|
|
MMX-OBJS-$(CONFIG_SNOW_ENCODER) += x86/snowdsp.o
|
|
|
|
|
|
|
|
|
|
# subsystems
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_AC3DSP) += x86/ac3dsp.o \
|
|
|
|
|
x86/ac3dsp_downmix.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_AUDIODSP) += x86/audiodsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_BLOCKDSP) += x86/blockdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_BSWAPDSP) += x86/bswapdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_DCT) += x86/dct32.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_FFT) += x86/fft.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_FMTCONVERT) += x86/fmtconvert.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_H263DSP) += x86/h263_loopfilter.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_H264CHROMA) += x86/h264_chromamc.o \
|
|
|
|
|
x86/h264_chromamc_10bit.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_H264DSP) += x86/h264_deblock.o \
|
|
|
|
|
x86/h264_deblock_10bit.o \
|
|
|
|
|
x86/h264_idct.o \
|
|
|
|
|
x86/h264_idct_10bit.o \
|
|
|
|
|
x86/h264_weight.o \
|
|
|
|
|
x86/h264_weight_10bit.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_H264PRED) += x86/h264_intrapred.o \
|
|
|
|
|
x86/h264_intrapred_10bit.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_H264QPEL) += x86/h264_qpel_8bit.o \
|
|
|
|
|
x86/h264_qpel_10bit.o \
|
|
|
|
|
x86/fpel.o \
|
|
|
|
|
x86/qpel.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_HPELDSP) += x86/fpel.o \
|
|
|
|
|
x86/hpeldsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_HUFFYUVDSP) += x86/huffyuvdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_HUFFYUVENCDSP) += x86/huffyuvencdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_IDCTDSP) += x86/idctdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_LLAUDDSP) += x86/lossless_audiodsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_LLVIDDSP) += x86/lossless_videodsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_LLVIDENCDSP) += x86/lossless_videoencdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_MDCT15) += x86/mdct15.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_ME_CMP) += x86/me_cmp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_MPEGAUDIODSP) += x86/imdct36.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_MPEGVIDEOENC) += x86/mpegvideoencdsp.o
|
x86/opusdsp: implement FMA3 accelerated postfilter and deemphasis
58893 decicycles in deemphasis_c, 130548 runs, 524 skips
9475 decicycles in deemphasis_fma3, 130686 runs, 386 skips -> 6.21x speedup
24866 decicycles in postfilter_c, 65386 runs, 150 skips
5268 decicycles in postfilter_fma3, 65505 runs, 31 skips -> 4.72x speedup
Total decoder speedup: ~14%
Deemphasis SIMD based on the following unrolling:
const float c1 = CELT_EMPH_COEFF, c2 = c1*c1, c3 = c2*c1, c4 = c3*c1;
float state = coeff;
for (int i = 0; i < len; i += 4) {
y[0] = x[0] + c1*state;
y[1] = x[1] + c2*state + c1*x[0];
y[2] = x[2] + c3*state + c1*x[1] + c2*x[0];
y[3] = x[3] + c4*state + c1*x[2] + c2*x[1] + c3*x[0];
state = y[3];
y += 4;
x += 4;
}
6 years ago
|
|
|
X86ASM-OBJS-$(CONFIG_OPUS_DECODER) += x86/opusdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_OPUS_ENCODER) += x86/celt_pvq_search.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_PIXBLOCKDSP) += x86/pixblockdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_QPELDSP) += x86/qpeldsp.o \
|
|
|
|
|
x86/fpel.o \
|
|
|
|
|
x86/qpel.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_RV34DSP) += x86/rv34dsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_VC1DSP) += x86/vc1dsp_loopfilter.o \
|
|
|
|
|
x86/vc1dsp_mc.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_IDCTDSP) += x86/simple_idct10.o \
|
|
|
|
|
x86/simple_idct.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_VIDEODSP) += x86/videodsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_VP3DSP) += x86/vp3dsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_VP8DSP) += x86/vp8dsp.o \
|
|
|
|
|
x86/vp8dsp_loopfilter.o
|
|
|
|
|
|
|
|
|
|
# decoders/encoders
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_AAC_DECODER) += x86/aacpsdsp.o \
|
|
|
|
|
x86/sbrdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_AAC_ENCODER) += x86/aacencdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_ADPCM_G722_DECODER) += x86/g722dsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_ADPCM_G722_ENCODER) += x86/g722dsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_ALAC_DECODER) += x86/alacdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_APNG_DECODER) += x86/pngdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_CAVS_DECODER) += x86/cavsidct.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_CFHD_DECODER) += x86/cfhddsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_DCA_DECODER) += x86/dcadsp.o x86/synth_filter.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_DIRAC_DECODER) += x86/diracdsp.o \
|
|
|
|
|
x86/dirac_dwt.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_DNXHD_ENCODER) += x86/dnxhdenc.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_EXR_DECODER) += x86/exrdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_FLAC_DECODER) += x86/flacdsp.o
|
|
|
|
|
ifdef CONFIG_GPL
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_FLAC_ENCODER) += x86/flac_dsp_gpl.o
|
|
|
|
|
endif
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_HEVC_DECODER) += x86/hevc_add_res.o \
|
|
|
|
|
x86/hevc_deblock.o \
|
|
|
|
|
x86/hevc_idct.o \
|
|
|
|
|
x86/hevc_mc.o \
|
|
|
|
|
x86/hevc_sao.o \
|
|
|
|
|
x86/hevc_sao_10bit.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_JPEG2000_DECODER) += x86/jpeg2000dsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_LSCR_DECODER) += x86/pngdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_MLP_DECODER) += x86/mlpdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_MPEG4_DECODER) += x86/xvididct.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_PNG_DECODER) += x86/pngdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_PRORES_DECODER) += x86/proresdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_PRORES_LGPL_DECODER) += x86/proresdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_RV40_DECODER) += x86/rv40dsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_SBC_ENCODER) += x86/sbcdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_SVQ1_ENCODER) += x86/svq1enc.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_TAK_DECODER) += x86/takdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_TRUEHD_DECODER) += x86/mlpdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_TTA_DECODER) += x86/ttadsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_TTA_ENCODER) += x86/ttaencdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_UTVIDEO_DECODER) += x86/utvideodsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_V210_ENCODER) += x86/v210enc.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_V210_DECODER) += x86/v210.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_VORBIS_DECODER) += x86/vorbisdsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_VP3_DECODER) += x86/hpeldsp_vp3.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_VP6_DECODER) += x86/vp6dsp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_VP9_DECODER) += x86/vp9intrapred.o \
|
|
|
|
|
x86/vp9intrapred_16bpp.o \
|
|
|
|
|
x86/vp9itxfm.o \
|
|
|
|
|
x86/vp9itxfm_16bpp.o \
|
|
|
|
|
x86/vp9lpf.o \
|
|
|
|
|
x86/vp9lpf_16bpp.o \
|
|
|
|
|
x86/vp9mc.o \
|
|
|
|
|
x86/vp9mc_16bpp.o
|
|
|
|
|
X86ASM-OBJS-$(CONFIG_WEBP_DECODER) += x86/vp8dsp.o
|
