mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-23 12:43:46 +02:00
82c71913e4
This adds a hand-optimized assembly version for get_cabac much like the existing one, but it works if the table offsets are RIP-relative. Compared to the non-RIP-relative version this adds 2 lea instructions and it needs one extra register. There is a surprisingly large performance improvement over the c version (more so than the generated assembly seems to suggest) just in get_cabac, I measured roughly 40% faster for get_cabac on a K8. However, overall the difference is not that big, I measured roughly 5% on a test clip on a K8 and a Core2. Hopefully it still compiles on x86 32bit... Now that only one table is used, there's some chance even darwin as compiles this (apparently the label arithmetic used previously doesn't work if it involves symbols defined in a different file, thanks to Ronald S. Bultje for helping me with this). Signed-off-by: Michael Niedermayer <michaelni@gmx.at> |
||
|---|---|---|
| .. | ||
| ac3dsp_mmx.c | ||
| ac3dsp.asm | ||
| cabac.h | ||
| cavsdsp_mmx.c | ||
| dct32_sse.asm | ||
| deinterlace.asm | ||
| diracdsp_mmx.c | ||
| diracdsp_mmx.h | ||
| diracdsp_yasm.asm | ||
| dnxhd_mmx.c | ||
| dsputil_mmx_avg_template.c | ||
| dsputil_mmx_qns_template.c | ||
| dsputil_mmx_rnd_template.c | ||
| dsputil_mmx.c | ||
| dsputil_mmx.h | ||
| dsputil_yasm.asm | ||
| dsputilenc_mmx.c | ||
| dsputilenc_yasm.asm | ||
| dwt_yasm.asm | ||
| dwt.c | ||
| dwt.h | ||
| fdct_mmx.c | ||
| fft_3dn2.c | ||
| fft_3dn.c | ||
| fft_mmx.asm | ||
| fft_sse.c | ||
| fft.c | ||
| fft.h | ||
| fmtconvert_mmx.c | ||
| fmtconvert.asm | ||
| 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_10bit.asm | ||
| h264_qpel_mmx.c | ||
| h264_weight_10bit.asm | ||
| h264_weight.asm | ||
| h264dsp_mmx.c | ||
| idct_mmx_xvid.c | ||
| idct_mmx.c | ||
| idct_sse2_xvid.c | ||
| idct_xvid.h | ||
| imdct36_sse.asm | ||
| lpc_mmx.c | ||
| Makefile | ||
| mathops.h | ||
| mlpdsp.c | ||
| motion_est_mmx.c | ||
| mpegaudiodec_mmx.c | ||
| mpegvideo_mmx_template.c | ||
| mpegvideo_mmx.c | ||
| pngdsp-init.c | ||
| pngdsp.asm | ||
| proresdsp-init.c | ||
| proresdsp.asm | ||
| rv34dsp_init.c | ||
| rv34dsp.asm | ||
| rv40dsp_init.c | ||
| rv40dsp.asm | ||
| sbrdsp_init.c | ||
| sbrdsp.asm | ||
| simple_idct_mmx.c | ||
| snowdsp_mmx.c | ||
| v210-init.c | ||
| v210.asm | ||
| vc1dsp_mmx.c | ||
| vc1dsp_yasm.asm | ||
| vp3dsp.asm | ||
| vp8dsp-init.c | ||
| vp8dsp.asm | ||
| vp56_arith.h | ||
| vp56dsp_init.c | ||
| vp56dsp.asm | ||
| w64xmmtest.c | ||