Hi, On Sat, Dec 27, 2014 at 1:23 PM, Clément Bœsch <u...@pkh.me> wrote:
> On Sat, Dec 27, 2014 at 11:02:45AM -0500, Ronald S. Bultje wrote: > > --- > > libavcodec/x86/vp9dsp_init.c | 2 +- > > libavcodec/x86/vp9lpf.asm | 153 > ++++++++++++++++++++++++++++++------------- > > 2 files changed, 107 insertions(+), 48 deletions(-) > > > > diff --git a/libavcodec/x86/vp9dsp_init.c b/libavcodec/x86/vp9dsp_init.c > > index d89843e..6c58c6c 100644 > > --- a/libavcodec/x86/vp9dsp_init.c > > +++ b/libavcodec/x86/vp9dsp_init.c > > @@ -361,8 +361,8 @@ av_cold void ff_vp9dsp_init_x86(VP9DSPContext *dsp) > > dsp->loop_filter_mix2[1][0][0] = > ff_vp9_loop_filter_h_84_16_##opt; \ > > dsp->loop_filter_mix2[1][0][1] = > ff_vp9_loop_filter_v_84_16_##opt; \ > > dsp->loop_filter_mix2[1][1][0] = > ff_vp9_loop_filter_h_88_16_##opt; \ > > - dsp->loop_filter_mix2[1][1][1] = > ff_vp9_loop_filter_v_88_16_##opt; \ > > } \ > > + dsp->loop_filter_mix2[1][1][1] = ff_vp9_loop_filter_v_88_16_##opt; \ > > } while (0) > > > > #define init_ipred(sz, opt, t, e) \ > > diff --git a/libavcodec/x86/vp9lpf.asm b/libavcodec/x86/vp9lpf.asm > > index d00ba7f..2759031 100644 > > --- a/libavcodec/x86/vp9lpf.asm > > +++ b/libavcodec/x86/vp9lpf.asm > > @@ -50,6 +50,22 @@ mask_mix48: times 8 db 0x00 > > > > SECTION .text > > > > +%macro SCRATCH 3 > > +%if ARCH_X86_64 > > + SWAP %1, %2 > > +%else > > + mova [%3], m%1 > > +%endif > > +%endmacro > > + > > +%macro UNSCRATCH 3 > > +%if ARCH_X86_64 > > + SWAP %1, %2 > > +%else > > + mova m%1, [%3] > > +%endif > > +%endmacro > > + > > ; %1 = abs(%2-%3) > > %macro ABSSUB 4 ; dst, src1 (RO), src2 (RO), tmp > > %if ARCH_X86_64 > > @@ -84,12 +100,25 @@ SECTION .text > > por %1, %4 ; new&mask | old&~mask > > %endmacro > > > > -%macro FILTER_SUBx2_ADDx2 9-10 "" ; %1=dst %2=h/l %3=cache %4=stack_off > %5=sub1 %6=sub2 %7=add1 %8=add2 %9=rshift, [unpack] > > +%macro UNPACK 4 > > +%if ARCH_X86_64 > > + punpck%1bw %2, %3, %4 > > +%else > > + mova %2, %3 > > + punpck%1bw %2, %4 > > +%endif > > +%endmacro > > + > > +%macro FILTER_SUBx2_ADDx2 11 ; %1=dst %2=h/l %3=cache %4=stack_off > %5=sub1 %6=sub2 %7=add1 %8=add2 %9=rshift, [unpack] > > Please update the macro comment > Done (and split in two lines, it was getting really long). Ronald _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
