virtualenv/FFmpeg
1
0
Fork 0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2025-01-24 13:56:33 +02:00
Code Issues Releases Activity

swresample/x86/resample: extend resample_double to support avx and fma3

Browse Source 
benchmark:
sse2 10.670s
avx   8.763s
fma3  8.380s

Signed-off-by: Muhammad Faiz <mfcc64@gmail.com>
This commit is contained in:
Muhammad Faiz 2017-03-16 11:33:16 +07:00
parent 3d5c2169e4
commit de1308429a
2 changed files with 22 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
libswresample/x86/resample.asm
View File

@ -203,7 +203,7 @@ cglobal resample_common_%1, 1, 7, 2, ctx, phase_count, dst, frac, \
; horizontal sum & store ; horizontal sum & store
%if mmsize == 32 %if mmsize == 32
vextractf128 xm1, m0, 0x1 vextractf128 xm1, m0, 0x1
addps xm0, xm1 addp%4 xm0, xm1
%endif %endif
movhlps xm1, xm0 movhlps xm1, xm0
%ifidn %1, float %ifidn %1, float
@ -489,8 +489,8 @@ cglobal resample_linear_%1, 1, 7, 5, ctx, min_filter_length_x4, filter2, \
%if mmsize == 32 %if mmsize == 32
vextractf128 xm1, m0, 0x1 vextractf128 xm1, m0, 0x1
vextractf128 xm3, m2, 0x1 vextractf128 xm3, m2, 0x1
addps xm0, xm1 addp%4 xm0, xm1
addps xm2, xm3 addp%4 xm2, xm3
%endif %endif
cvtsi2s%4 xm1, fracd cvtsi2s%4 xm1, fracd
subp%4 xm2, xm0 subp%4 xm2, xm0
@ -608,3 +608,12 @@ RESAMPLE_FNS int16, 2, 1
INIT_XMM sse2 INIT_XMM sse2
RESAMPLE_FNS double, 8, 3, d, pdbl_1 RESAMPLE_FNS double, 8, 3, d, pdbl_1
%if HAVE_AVX_EXTERNAL
INIT_YMM avx
RESAMPLE_FNS double, 8, 3, d, pdbl_1
%endif
%if HAVE_FMA3_EXTERNAL
INIT_YMM fma3
RESAMPLE_FNS double, 8, 3, d, pdbl_1
%endif

10
libswresample/x86/resample_init.c
View File

@ -42,6 +42,8 @@ RESAMPLE_FUNCS(float, avx);
RESAMPLE_FUNCS(float, fma3); RESAMPLE_FUNCS(float, fma3);
RESAMPLE_FUNCS(float, fma4); RESAMPLE_FUNCS(float, fma4);
RESAMPLE_FUNCS(double, sse2); RESAMPLE_FUNCS(double, sse2);
RESAMPLE_FUNCS(double, avx);
RESAMPLE_FUNCS(double, fma3);
av_cold void swri_resample_dsp_x86_init(ResampleContext *c) av_cold void swri_resample_dsp_x86_init(ResampleContext *c)
{ {
@ -85,6 +87,14 @@ av_cold void swri_resample_dsp_x86_init(ResampleContext *c)
c->dsp.resample_linear = ff_resample_linear_double_sse2; c->dsp.resample_linear = ff_resample_linear_double_sse2;
c->dsp.resample_common = ff_resample_common_double_sse2; c->dsp.resample_common = ff_resample_common_double_sse2;
} }
if (EXTERNAL_AVX_FAST(mm_flags)) {
c->dsp.resample_linear = ff_resample_linear_double_avx;
c->dsp.resample_common = ff_resample_common_double_avx;
}
if (EXTERNAL_FMA3_FAST(mm_flags)) {
c->dsp.resample_linear = ff_resample_linear_double_fma3;
c->dsp.resample_common = ff_resample_common_double_fma3;
}
break; break;
} }
} }