[x265] [PATCH] asm:intra_pred_ang4_2 improved by ~4% 134.99 -> 129.95

[Steve Borho]

On 03/31, dtyx265 at gmail.com wrote:
> # HG changeset patch
> # User David T Yuen <dtyx265 at gmail.com>
> # Date 1427823883 25200
> # Node ID 89bc6238d4a2e3f117f0127e406c6dfbf093868b
> # Parent  36d70728acc2d9d6103af7530493176c08298ded
> asm:intra_pred_ang4_2 improved by ~4% 134.99 -> 129.95
> 
> Reduced xmm registers to 1

I've queued this one; it might be good to re-send the latest versions of
the rest of them

> diff -r 36d70728acc2 -r 89bc6238d4a2 source/common/x86/intrapred8.asm
> --- a/source/common/x86/intrapred8.asm	Fri Mar 27 13:16:28 2015 -0500
> +++ b/source/common/x86/intrapred8.asm	Tue Mar 31 10:44:43 2015 -0700
> @@ -1320,7 +1320,7 @@
>  ; void intraPredAng4(pixel* dst, intptr_t dstStride, pixel* src, int dirMode, int bFilter)
>  ;-----------------------------------------------------------------------------------------
>  INIT_XMM sse2
> -cglobal intra_pred_ang4_2, 3,5,3
> +cglobal intra_pred_ang4_2, 3,5,1
>      lea         r4, [r2 + 2]
>      add         r2, 10
>      cmp         r3m, byte 34
> @@ -1328,14 +1328,12 @@
>  
>      movh        m0, [r2]
>      movd        [r0], m0
> -    mova        m1, m0
> -    psrldq      m1, 1
> -    movd        [r0 + r1], m1
> -    mova        m2, m0
> -    psrldq      m2, 2
> -    movd        [r0 + r1 * 2], m2
> +    psrldq      m0, 1
> +    movd        [r0 + r1], m0
> +    psrldq      m0, 1
> +    movd        [r0 + r1 * 2], m0
>      lea         r1, [r1 * 3]
> -    psrldq      m0, 3
> +    psrldq      m0, 1
>      movd        [r0 + r1], m0
>      RET
>  
> _______________________________________________
> x265-devel mailing list
> x265-devel at videolan.org
> https://mailman.videolan.org/listinfo/x265-devel

-- 
Steve Borho