[x265] [PATCH Review only] asm: pixel_sub_ps routine for 4x2 block size

[chen]

>+;-----------------------------------------------------------------------------
>+; void pixel_sub_ps_c_4x2(int16_t *dest, intptr_t destride, pixel *src0, pixel *src1, intptr_t srcstride0, intptr_t srcstride1);
>+;-----------------------------------------------------------------------------
This function can define in pixel-a.asm
 
>+INIT_XMM sse2
pmovzxbw is sse4.1
 
>+cglobal pixel_sub_ps_4x2, 4, 6, 6, dest, deststride, src0, src1
>+
>+add         r1,     r1
>+mov         r4d,    r4m
>+mov         r5d,    r5m
r4 and r5 define as intptr_t, didn't need convert to dword

>+movd        m0,     [r2]
>+movd        m1,     [r3]
>+pmovzxbw    m2,     m0
>+pmovzxbw    m3,     m1
pmovzxbw    m0,     m0

>+movd        m0,     [r2 + r4]
>+movd        m1,     [r3 + r5]
>+pmovzxbw    m4,     m0
>+pmovzxbw    m5,     m1
>+
>+psubw       m4,     m5
>+psubw       m2,     m3
>+
>+movh    [r0],         m2
>+movh    [r0 + r1],    m4
>+
>+RET
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.videolan.org/pipermail/x265-devel/attachments/20131108/6f5ced3c/attachment.html>