[x265] [PATCH] asm: intrapred dc32 sse2 high bit

[dave]

oops, forgot to remove old comment, will resubmit...

On 03/03/2015 09:40 AM, dtyx265 at gmail.com wrote:
> # HG changeset patch
> # User David T Yuen <dtyx265 at gmail.com>
> # Date 1425404383 28800
> # Node ID 1699595e179d7c131ab24a9af48683a8da2a4d79
> # Parent  4641827f98c935603f608425de8c76785aef1114
> asm: intrapred dc32 sse2 high bit
>
> This replaces c code for systems using ssse3 to sse2 processors
> The code is backported from intrapred dc32 sse4 high bit
>
> ./test/TestBench --testbench intrapred | grep 32x32
> intra_dc_32x32[f=0]	2.80x 	 3082.50  	 8635.37
>
> diff -r 4641827f98c9 -r 1699595e179d source/common/x86/asm-primitives.cpp
> --- a/source/common/x86/asm-primitives.cpp	Mon Mar 02 14:46:46 2015 -0800
> +++ b/source/common/x86/asm-primitives.cpp	Tue Mar 03 09:39:43 2015 -0800
> @@ -871,6 +871,7 @@
>           p.cu[BLOCK_4x4].intra_pred[DC_IDX] = x265_intra_pred_dc4_sse2;
>           p.cu[BLOCK_8x8].intra_pred[DC_IDX] = x265_intra_pred_dc8_sse2;
>           p.cu[BLOCK_16x16].intra_pred[DC_IDX] = x265_intra_pred_dc16_sse2;
> +        p.cu[BLOCK_32x32].intra_pred[DC_IDX] = x265_intra_pred_dc32_sse2;
>   
>           p.cu[BLOCK_4x4].sse_ss = x265_pixel_ssd_ss_4x4_mmx2;
>           ALL_LUMA_CU(sse_ss, pixel_ssd_ss, sse2);
> diff -r 4641827f98c9 -r 1699595e179d source/common/x86/intrapred16.asm
> --- a/source/common/x86/intrapred16.asm	Mon Mar 02 14:46:46 2015 -0800
> +++ b/source/common/x86/intrapred16.asm	Tue Mar 03 09:39:43 2015 -0800
> @@ -386,6 +386,69 @@
>   .end:
>       RET
>   
> +;-------------------------------------------------------------------------------------------
> +; void intra_pred_dc(pixel* above, pixel* left, pixel* dst, intptr_t dstStride, int filter)
> +;-------------------------------------------------------------------------------------------
> +INIT_XMM sse2
> +cglobal intra_pred_dc32, 3, 4, 6
> +    lea             r3,                  [r2 + 130]     ;130 = 32*sizeof(pixel)*2 + 1*sizeof(pixel)
> +    add             r2,                  2
> +    add             r1,                  r1
> +    movu            m0,                  [r3]
> +    movu            m1,                  [r3 + 16]
> +    movu            m2,                  [r3 + 32]
> +    movu            m3,                  [r3 + 48]
> +    paddw           m0,                  m1
> +    paddw           m2,                  m3
> +    paddw           m0,                  m2
> +    movu            m1,                  [r2]
> +    movu            m3,                  [r2 + 16]
> +    movu            m4,                  [r2 + 32]
> +    movu            m5,                  [r2 + 48]
> +    paddw           m1,                  m3
> +    paddw           m4,                  m5
> +    paddw           m1,                  m4
> +    paddw           m0,                  m1
> +    movhlps         m1,                  m0
> +    paddw           m0,                  m1
> +    pshuflw         m1,                  m0, 0x6E
> +    paddw           m0,                  m1
> +    pmaddwd         m0,                  [pw_1]
> +
> +    paddd           m0,                  [pd_32]     ; sum = sum + 32
> +    psrld           m0,                  6           ; sum = sum / 64
> +    pshuflw         m0,                  m0, 0
> +    pshufd          m0,                  m0, 0
> +
> +    lea             r2,                 [r1 * 3]
> +;     mov             r3d,                4
> +.loop:
> +    ; store DC 32x32
> +%assign x 1
> +%rep 8
> +    movu            [r0 +  0],          m0
> +    movu            [r0 + 16],          m0
> +    movu            [r0 + 32],          m0
> +    movu            [r0 + 48],          m0
> +    movu            [r0 + r1 +  0],     m0
> +    movu            [r0 + r1 + 16],     m0
> +    movu            [r0 + r1 + 32],     m0
> +    movu            [r0 + r1 + 48],     m0
> +    movu            [r0 + r1 * 2 +  0], m0
> +    movu            [r0 + r1 * 2 + 16], m0
> +    movu            [r0 + r1 * 2 + 32], m0
> +    movu            [r0 + r1 * 2 + 48], m0
> +    movu            [r0 + r2 +  0],     m0
> +    movu            [r0 + r2 + 16],     m0
> +    movu            [r0 + r2 + 32],     m0
> +    movu            [r0 + r2 + 48],     m0
> +    %if x < 8
> +    lea             r0, [r0 + r1 * 4]
> +    %endif
> +%assign x x + 1
> +%endrep
> +    RET
> +
>   ;-----------------------------------------------------------------------------------
>   ; void intra_pred_dc(pixel* dst, intptr_t dstStride, pixel* above, int, int filter)
>   ;-----------------------------------------------------------------------------------
> @@ -668,7 +731,7 @@
>   ;-------------------------------------------------------------------------------------------
>   INIT_XMM sse4
>   cglobal intra_pred_dc32, 3, 5, 6
> -    lea             r3,                  [r2 + 130]
> +    lea             r3,                  [r2 + 130]     ;130 = 32*sizeof(pixel)*2 + 1*sizeof(pixel)
>       add             r2,                  2
>       add             r1,                  r1
>       movu            m0,                  [r3]