mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2024-12-29 02:42:21 +00:00
3e892b2bcd
In some cases, 2 or 3 calls are performed to functions for unusual widths. Instead, perform 2 calls for different widths to split the workload. The 8+16 and 4+8 widths for respectively 8 and more than 8 bits can't be processed that way without modifications: some calls use unaligned buffers, and having branches to handle this was resulting in no micro-benchmark benefit. For block_w == 12 (around 1% of the pixels of the sequence): Before: 12758 decicycles in epel_uni, 4093 runs, 3 skips 19389 decicycles in qpel_uni, 8187 runs, 5 skips 22699 decicycles in epel_bi, 32743 runs, 25 skips 34736 decicycles in qpel_bi, 32733 runs, 35 skips After: 11929 decicycles in epel_uni, 4096 runs, 0 skips 18131 decicycles in qpel_uni, 8184 runs, 8 skips 20065 decicycles in epel_bi, 32750 runs, 18 skips 31458 decicycles in qpel_bi, 32753 runs, 15 skips Signed-off-by: Michael Niedermayer <michaelni@gmx.at> |
||
|---|---|---|
| .. | ||
| ac3dsp_init.c | ||
| ac3dsp.asm | ||
| audiodsp_init.c | ||
| audiodsp.asm | ||
| blockdsp_init.c | ||
| blockdsp.asm | ||
| bswapdsp_init.c | ||
| bswapdsp.asm | ||
| cabac.h | ||
| cavsdsp.c | ||
| constants.c | ||
| constants.h | ||
| dcadsp_init.c | ||
| dcadsp.asm | ||
| dct32.asm | ||
| dct_init.c | ||
| dct-test.c | ||
| deinterlace.asm | ||
| dirac_dwt.c | ||
| dirac_dwt.h | ||
| diracdsp_mmx.c | ||
| diracdsp_mmx.h | ||
| diracdsp_yasm.asm | ||
| dnxhdenc_init.c | ||
| dnxhdenc.asm | ||
| dwt_yasm.asm | ||
| fdct.c | ||
| fdct.h | ||
| fdctdsp_init.c | ||
| fft_init.c | ||
| fft.asm | ||
| fft.h | ||
| flac_dsp_gpl.asm | ||
| flacdsp_init.c | ||
| flacdsp.asm | ||
| fmtconvert_init.c | ||
| fmtconvert.asm | ||
| fpel.asm | ||
| fpel.h | ||
| h263_loopfilter.asm | ||
| h263dsp_init.c | ||
| h264_chromamc_10bit.asm | ||
| h264_chromamc.asm | ||
| h264_deblock_10bit.asm | ||
| h264_deblock.asm | ||
| h264_i386.h | ||
| h264_idct_10bit.asm | ||
| h264_idct.asm | ||
| h264_intrapred_10bit.asm | ||
| h264_intrapred_init.c | ||
| h264_intrapred.asm | ||
| h264_qpel_8bit.asm | ||
| h264_qpel_10bit.asm | ||
| h264_qpel.c | ||
| h264_weight_10bit.asm | ||
| h264_weight.asm | ||
| h264chroma_init.c | ||
| h264dsp_init.c | ||
| hevc_deblock.asm | ||
| hevc_idct.asm | ||
| hevc_mc.asm | ||
| hevc_res_add.asm | ||
| hevcdsp_init.c | ||
| hevcdsp.h | ||
| hpeldsp_init.c | ||
| hpeldsp_rnd_template.c | ||
| hpeldsp.asm | ||
| hpeldsp.h | ||
| huffyuvdsp_init.c | ||
| huffyuvdsp.asm | ||
| huffyuvencdsp_mmx.c | ||
| idct_mmx_xvid.c | ||
| idct_sse2_xvid.c | ||
| idct_xvid.h | ||
| idctdsp_init.c | ||
| idctdsp_mmx.c | ||
| idctdsp.asm | ||
| idctdsp.h | ||
| imdct36.asm | ||
| inline_asm.h | ||
| lossless_audiodsp_init.c | ||
| lossless_audiodsp.asm | ||
| lossless_videodsp_init.c | ||
| lossless_videodsp.asm | ||
| lpc.c | ||
| Makefile | ||
| mathops.h | ||
| me_cmp_init.c | ||
| me_cmp.asm | ||
| mlpdsp.c | ||
| mpegaudiodsp.c | ||
| mpegvideo.c | ||
| mpegvideodsp.c | ||
| mpegvideoenc_qns_template.c | ||
| mpegvideoenc_template.c | ||
| mpegvideoenc.c | ||
| mpegvideoencdsp_init.c | ||
| mpegvideoencdsp.asm | ||
| pixblockdsp_init.c | ||
| pixblockdsp.asm | ||
| pngdsp_init.c | ||
| pngdsp.asm | ||
| proresdsp_init.c | ||
| proresdsp.asm | ||
| qpel.asm | ||
| qpeldsp_init.c | ||
| qpeldsp.asm | ||
| rnd_template.c | ||
| rv34dsp_init.c | ||
| rv34dsp.asm | ||
| rv40dsp_init.c | ||
| rv40dsp.asm | ||
| sbrdsp_init.c | ||
| sbrdsp.asm | ||
| simple_idct.c | ||
| simple_idct.h | ||
| snowdsp.c | ||
| svq1enc_init.c | ||
| svq1enc.asm | ||
| ttadsp_init.c | ||
| ttadsp.asm | ||
| v210-init.c | ||
| v210.asm | ||
| vc1dsp_init.c | ||
| vc1dsp_mmx.c | ||
| vc1dsp.asm | ||
| vc1dsp.h | ||
| videodsp_init.c | ||
| videodsp.asm | ||
| vorbisdsp_init.c | ||
| vorbisdsp.asm | ||
| vp3dsp_init.c | ||
| vp3dsp.asm | ||
| vp6dsp_init.c | ||
| vp6dsp.asm | ||
| vp8dsp_init.c | ||
| vp8dsp_loopfilter.asm | ||
| vp8dsp.asm | ||
| vp9dsp_init.c | ||
| vp9intrapred.asm | ||
| vp9itxfm.asm | ||
| vp9lpf.asm | ||
| vp9mc.asm | ||
| vp56_arith.h | ||
| w64xmmtest.c | ||
| xvididct_init.c | ||