mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-11-21 10:55:51 +02:00
34454c761f
The 32bits targets have been compiled with -mfpmath=sse for proper reference. sbr_sum_square C /32bits: 82c (unrolled)/102c C /64bits: 69c (unrolled)/82c SSE/32bits: 42c SSE/64bits: 31c Use of SSE4.1 dpps to perform the final sum is slower. Not unrolling to perform 8 operations in a loop yields 10 more cycles. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com> |
||
---|---|---|
.. | ||
ac3dsp_mmx.c | ||
ac3dsp.asm | ||
cabac.h | ||
cavsdsp_mmx.c | ||
dct32_sse.asm | ||
deinterlace.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 | ||
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 | ||
vc1dsp_mmx.c | ||
vc1dsp_yasm.asm | ||
vp3dsp.asm | ||
vp8dsp-init.c | ||
vp8dsp.asm | ||
vp56_arith.h | ||
vp56dsp_init.c | ||
vp56dsp.asm | ||
w64xmmtest.c |