On Tue, Sep 3, 2024 at 5:42 PM Ramiro Polla <ramiro.po...@gmail.com> wrote:
> On Sun, Sep 1, 2024 at 3:09 PM Ramiro Polla <ramiro.po...@gmail.com> wrote:
> >
> > ---
> > libswscale/x86/input.asm | 15 +++++++++------
> > 1 file changed, 9 insertions(+), 6 deletions(-)
> >
> > diff --git a/libswscale/x86/input.asm b/libswscale/x86/input.asm
> > index 21cd8b37fd..516e4384b1 100644
> > --- a/libswscale/x86/input.asm
> > +++ b/libswscale/x86/input.asm
> > @@ -736,11 +736,11 @@ cglobal %2ToUV, 4, 5, %1, dstU, dstV, unused, src, w
> > packuswb m2, m3 ; (byte) { U0, ..., U15 }
> > packuswb m0, m1 ; (byte) { V0, ..., V15 }
> > %ifidn %2, nv12
> > - mova [dstUq+wq], m2
> > - mova [dstVq+wq], m0
> > + mov%1 [dstUq+wq], m2
> > + mov%1 [dstVq+wq], m0
> > %else ; nv21
> > - mova [dstVq+wq], m2
> > - mova [dstUq+wq], m0
> > + mov%1 [dstVq+wq], m2
> > + mov%1 [dstUq+wq], m0
> > %endif ; nv12/21
> > add wq, mmsize
> > jl .loop_%1
> > @@ -750,15 +750,18 @@ cglobal %2ToUV, 4, 5, %1, dstU, dstV, unused, src, w
> > ; %1 = nr. of XMM registers
> > ; %2 = nv12 or nv21
> > %macro NVXX_TO_UV_FN 2
> > -cglobal %2ToUV, 4, 5, %1, dstU, dstV, unused, src, w
> > +cglobal %2ToUV, 4, 5, %1, dstU, dstV, tmp, src, w
> > %if ARCH_X86_64
> > movsxd wq, dword r5m
> > %else ; x86-32
> > mov wq, r5m
> > %endif
> > + mov tmpq, srcq
> > + or tmpq, dstUq
> > + or tmpq, dstVq
> > add dstUq, wq
> > add dstVq, wq
> > - test srcq, 15
> > + test tmpq, 15
> > lea srcq, [srcq+wq*2]
> > pcmpeqb m5, m5 ; (byte) { 0xff } x 16
> > psrlw m5, 8 ; (word) { 0x00ff } x 8
> > --
> > 2.30.2
> >
>
> I'll apply this patchset in a few days if there are no comments.
Pushed.
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
