mirror of https://git.ffmpeg.org/ffmpeg.git
f0a2b6249b
checkasm --bench, 10k runs, for *_add_${bpc}_${sub_idct}_${opt}, shows
that it's about 1.65x as fast as the AVX version for the full IDCT, and
similar speedups for the sub-IDCTs:
nop: 24.6
vp9_inv_dct_dct_16x16_add_8_1_c: 6444.8
vp9_inv_dct_dct_16x16_add_8_1_sse2: 638.6
vp9_inv_dct_dct_16x16_add_8_1_ssse3: 484.4
vp9_inv_dct_dct_16x16_add_8_1_avx: 661.2
vp9_inv_dct_dct_16x16_add_8_1_avx2: 311.5
vp9_inv_dct_dct_16x16_add_8_2_c: 6665.7
vp9_inv_dct_dct_16x16_add_8_2_sse2: 646.9
vp9_inv_dct_dct_16x16_add_8_2_ssse3: 455.2
vp9_inv_dct_dct_16x16_add_8_2_avx: 521.9
vp9_inv_dct_dct_16x16_add_8_2_avx2: 304.3
vp9_inv_dct_dct_16x16_add_8_4_c: 7022.7
vp9_inv_dct_dct_16x16_add_8_4_sse2: 647.4
vp9_inv_dct_dct_16x16_add_8_4_ssse3: 467.1
vp9_inv_dct_dct_16x16_add_8_4_avx: 446.1
vp9_inv_dct_dct_16x16_add_8_4_avx2: 297.0
vp9_inv_dct_dct_16x16_add_8_8_c: 6800.4
vp9_inv_dct_dct_16x16_add_8_8_sse2: 598.6
vp9_inv_dct_dct_16x16_add_8_8_ssse3: 465.7
vp9_inv_dct_dct_16x16_add_8_8_avx: 440.9
vp9_inv_dct_dct_16x16_add_8_8_avx2: 290.2
vp9_inv_dct_dct_16x16_add_8_16_c: 6626.6
vp9_inv_dct_dct_16x16_add_8_16_sse2: 599.5
vp9_inv_dct_dct_16x16_add_8_16_ssse3: 475.0
vp9_inv_dct_dct_16x16_add_8_16_avx: 469.9
vp9_inv_dct_dct_16x16_add_8_16_avx2: 286.4
|
||
|---|---|---|
| .. | ||
| aarch64 | ||
| arm | ||
| avr32 | ||
| bfin | ||
| mips | ||
| ppc | ||
| sh4 | ||
| tests | ||
| tomi | ||
| x86 | ||
| .gitignore | ||
| Makefile | ||
| adler32.c | ||
| adler32.h | ||
| aes.c | ||
| aes.h | ||
| aes_ctr.c | ||
| aes_ctr.h | ||
| aes_internal.h | ||
| atomic.c | ||
| atomic.h | ||
| atomic_gcc.h | ||
| atomic_suncc.h | ||
| atomic_win32.h | ||
| attributes.h | ||
| audio_fifo.c | ||
| audio_fifo.h | ||
| avassert.h | ||
| avstring.c | ||
| avstring.h | ||
| avutil.h | ||
| avutilres.rc | ||
| base64.c | ||
| base64.h | ||
| blowfish.c | ||
| blowfish.h | ||
| bprint.c | ||
| bprint.h | ||
| bswap.h | ||
| buffer.c | ||
| buffer.h | ||
| buffer_internal.h | ||
| camellia.c | ||
| camellia.h | ||
| cast5.c | ||
| cast5.h | ||
| channel_layout.c | ||
| channel_layout.h | ||
| color_utils.c | ||
| color_utils.h | ||
| colorspace.h | ||
| common.h | ||
| cpu.c | ||
| cpu.h | ||
| cpu_internal.h | ||
| crc.c | ||
| crc.h | ||
| des.c | ||
| des.h | ||
| dict.c | ||
| dict.h | ||
| display.c | ||
| display.h | ||
| downmix_info.c | ||
| downmix_info.h | ||
| dynarray.h | ||
| error.c | ||
| error.h | ||
| eval.c | ||
| eval.h | ||
| ffmath.h | ||
| fifo.c | ||
| fifo.h | ||
| file.c | ||
| file.h | ||
| file_open.c | ||
| fixed_dsp.c | ||
| fixed_dsp.h | ||
| float_dsp.c | ||
| float_dsp.h | ||
| frame.c | ||
| frame.h | ||
| hash.c | ||
| hash.h | ||
| hmac.c | ||
| hmac.h | ||
| hwcontext.c | ||
| hwcontext.h | ||
| hwcontext_cuda.c | ||
| hwcontext_cuda.h | ||
| hwcontext_dxva2.c | ||
| hwcontext_dxva2.h | ||
| hwcontext_internal.h | ||
| hwcontext_vaapi.c | ||
| hwcontext_vaapi.h | ||
| hwcontext_vdpau.c | ||
| hwcontext_vdpau.h | ||
| imgutils.c | ||
| imgutils.h | ||
| integer.c | ||
| integer.h | ||
| internal.h | ||
| intfloat.h | ||
| intmath.c | ||
| intmath.h | ||
| intreadwrite.h | ||
| lfg.c | ||
| lfg.h | ||
| libavutil.v | ||
| libm.h | ||
| lls.c | ||
| lls.h | ||
| log.c | ||
| log.h | ||
| log2_tab.c | ||
| lzo.c | ||
| lzo.h | ||
| macros.h | ||
| mastering_display_metadata.c | ||
| mastering_display_metadata.h | ||
| mathematics.c | ||
| mathematics.h | ||
| md5.c | ||
| md5.h | ||
| mem.c | ||
| mem.h | ||
| mem_internal.h | ||
| motion_vector.h | ||
| murmur3.c | ||
| murmur3.h | ||
| opencl.c | ||
| opencl.h | ||
| opencl_internal.c | ||
| opencl_internal.h | ||
| opt.c | ||
| opt.h | ||
| parseutils.c | ||
| parseutils.h | ||
| pca.c | ||
| pca.h | ||
| pixdesc.c | ||
| pixdesc.h | ||
| pixelutils.c | ||
| pixelutils.h | ||
| pixfmt.h | ||
| qsort.h | ||
| random_seed.c | ||
| random_seed.h | ||
| rational.c | ||
| rational.h | ||
| rc4.c | ||
| rc4.h | ||
| replaygain.h | ||
| reverse.c | ||
| ripemd.c | ||
| ripemd.h | ||
| samplefmt.c | ||
| samplefmt.h | ||
| sha.c | ||
| sha.h | ||
| sha512.c | ||
| sha512.h | ||
| softfloat.h | ||
| softfloat_tables.h | ||
| stereo3d.c | ||
| stereo3d.h | ||
| tablegen.h | ||
| tea.c | ||
| tea.h | ||
| thread.h | ||
| threadmessage.c | ||
| threadmessage.h | ||
| time.c | ||
| time.h | ||
| time_internal.h | ||
| timecode.c | ||
| timecode.h | ||
| timer.h | ||
| timestamp.h | ||
| tree.c | ||
| tree.h | ||
| twofish.c | ||
| twofish.h | ||
| utils.c | ||
| version.h | ||
| wchar_filename.h | ||
| xga_font_data.c | ||
| xga_font_data.h | ||
| xtea.c | ||
| xtea.h | ||