[x265] [PATCH] asm: 10bpp code for pixel_add_ps_6x8

[Murugan Vairavel]

Ignore this patch. I will resend it



On Mon, Dec 9, 2013 at 2:44 PM, chen <chenm003 at 163.com> wrote:

> >diff -r 5bb46ef28bc5 -r 02b888130ed4 source/common/x86/pixeladd8.asm
> >--- a/source/common/x86/pixeladd8.asm Mon Dec 09 10:59:45 2013 +0800
> >+++ b/source/common/x86/pixeladd8.asm Mon Dec 09 12:13:29 2013 +0530
> >@@ -364,6 +364,75 @@
>
> > ; void pixel_add_ps_%1x%2(pixel *dest, intptr_t destride, pixel *src0, int16_t *scr1, intptr_t srcStride0, intptr_t srcStride1)
>
> > ;-----------------------------------------------------------------------------
> > %macro PIXEL_ADD_PS_W6_H4 2
> >+%if HIGH_BIT_DEPTH
> >+INIT_XMM sse2
>
> >+cglobal pixel_add_ps_%1x%2, 6, 7, 6, dest, destride, src0, scr1, srcStride0, srcStride1
> >+    mov     r6d,    %2/4
> >+    add      r1,    r1
> >+    add      r4,    r4
> >+    add      r5,    r5
> >+    pxor     m4,    m4
> >+    mova     m5,    [pw_pixel_max]
> >+.loop
> >+    movu        m0,    [r2]
> >+    movu        m1,    [r3]
> >+    mova        m2,    m0
> >+    mova        m3,    m1
> >+    punpckhqdq  m2,    m2
> >+    punpckhqdq  m3,    m3
> punpckhqdq m2, m0, m0
> write like this will more performance on AVX, of course, you don't need
> it, see below
>
> >+    paddw       m0,    m1
> >+    paddw       m2,    m3
> the latest paddw can process 8 pixels, so you don't need m2m3
>
> >+    CLIPW       m0,    m4,    m5
> >+    CLIPW       m2,    m4,    m5
> >+
> >+    movh        [r0],         m0
> >+    movd        [r0 + 8],     m2
> SSE4: pextrd [r0+8],m0,2
> SSE2: pshufd m0, 2 + movd
>
>
>
> _______________________________________________
> x265-devel mailing list
> x265-devel at videolan.org
> https://mailman.videolan.org/listinfo/x265-devel
>
>


-- 
With Regards,

Murugan. V
+919659287478
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.videolan.org/pipermail/x265-devel/attachments/20131209/3dc5243f/attachment.html>