[x265] [PATCH 3 of 7] asm: intra_pred_ang4_5_sse2 improved ~2.5% 642.50 -> 627.50 with nits and tweaks

[dave]

please disregard this one.  The correct version has been sent
On 04/01/2015 11:52 AM, dtyx265 at gmail.com wrote:
> # HG changeset patch
> # User David T Yuen <dtyx265 at gmail.com>
> # Date 1427912500 25200
> # Node ID fc6b5f8bbcc8283e5b4fd88d41b8c313b002a198
> # Parent  fc902b84fc7f8dadf56431766adab8eda3520596
> asm: intra_pred_ang4_5_sse2 improved ~2.5% 642.50 -> 627.50 with nits and tweaks
>
> Changed r3 and r4 to r3d and r4d
> tweaked unpacking for performance
>
> diff -r fc902b84fc7f -r fc6b5f8bbcc8 source/common/x86/intrapred8.asm
> --- a/source/common/x86/intrapred8.asm	Wed Apr 01 06:01:22 2015 -0700
> +++ b/source/common/x86/intrapred8.asm	Wed Apr 01 11:21:40 2015 -0700
> @@ -1436,22 +1436,21 @@
>       jmp         mangle(private_prefix %+ _ %+ intra_pred_ang4_3 %+ SUFFIX %+ .do_filter4x4)
>   
>   cglobal intra_pred_ang4_5, 3,5,8
> -    xor         r4, r4
> -    inc         r4
> -    cmp         r3m, byte 31
> -    mov         r3, 9
> -    cmove       r3, r4
> +    xor         r4d, r4d
> +    inc         r4d
> +    cmp         r3d, byte 31
> +    mov         r3d, 9
> +    cmove       r3d, r4d
>   
>       movh        m0, [r2 + r3]    ; [8 7 6 5 4 3 2 1]
> -    mova        m1, m0
> -    psrldq      m1, 1           ; [x 8 7 6 5 4 3 2]
> -    punpcklbw   m0, m1          ; [x 8 8 7 7 6 6 5 5 4 4 3 3 2 2 1]
> -    mova        m1, m0
> -    psrldq      m1, 2           ; [x x x x x x x x 6 5 5 4 4 3 3 2]
> +    punpcklbw   m0, m0          ; [x 8 8 7 7 6 6 5 5 4 4 3 3 2 2 1]
> +    psrldq      m0, 1
> +    mova        m2, m0
> +    psrldq      m2, 2           ; [x x x x x x x x 6 5 5 4 4 3 3 2]
>       mova        m3, m0
>       psrldq      m3, 4           ; [x x x x x x x x 7 6 6 5 5 4 4 3]
> -    punpcklqdq  m0, m1
> -    punpcklqdq  m2, m1, m3
> +    punpcklqdq  m0, m2
> +    punpcklqdq  m2, m3
>   
>       lea         r3, [pw_ang_table + 10 * 16]
>       mova        m4, [r3 +  7 * 16]  ; [17]