[FFmpeg-devel] [PATCH] x86/hevc_res_add: refactor ff_hevc_transform_add{16, 32}_8

[Hendrik Leppkes]

On Thu, Aug 21, 2014 at 12:42 AM, James Almer <jamrial at gmail.com> wrote:
> * Reduced xmm register count to 7 (As such they are now enabled for x86_32).
> * Removed four movdqa (affects the sse2 version only).
> * pxor is now used to clear m0 only once.
>
> ~5% faster.
>
> Signed-off-by: James Almer <jamrial at gmail.com>
> ---

Good job, faster and 32-bit compat!

>  libavcodec/x86/hevc_res_add.asm | 122 ++++++++++++++++------------------------
>  libavcodec/x86/hevcdsp_init.c   |  10 ++--
>  2 files changed, 51 insertions(+), 81 deletions(-)
>
> diff --git a/libavcodec/x86/hevc_res_add.asm b/libavcodec/x86/hevc_res_add.asm
> index feea50c..7238fb3 100644
> --- a/libavcodec/x86/hevc_res_add.asm
> +++ b/libavcodec/x86/hevc_res_add.asm
> @@ -88,71 +88,41 @@ cglobal hevc_transform_add4_8, 3, 4, 6
>      movhps       [r0+r3  ], m1
>  %endmacro
>
> -%macro TR_ADD_INIT_SSE_8 0
> -    pxor              m0, m0
> -
> -    mova              m4, [r1]
> -    mova              m1, [r1+16]
> -    psubw             m2, m0, m1
> -    psubw             m5, m0, m4
> -    packuswb          m4, m1
> -    packuswb          m5, m2
> -
> -    mova              m6, [r1+32]
> -    mova              m1, [r1+48]
> -    psubw             m2, m0, m1
> -    psubw             m7, m0, m6
> -    packuswb          m6, m1
> -    packuswb          m7, m2
> -
> -    mova              m8, [r1+64]
> -    mova              m1, [r1+80]
> -    psubw             m2, m0, m1
> -    psubw             m9, m0, m8
> -    packuswb          m8, m1
> -    packuswb          m9, m2
> -
> -    mova             m10, [r1+96]
> -    mova              m1, [r1+112]
> -    psubw             m2, m0, m1
> -    psubw            m11, m0, m10
> -    packuswb         m10, m1
> -    packuswb         m11, m2
> -%endmacro
> -
> -
> -%macro TR_ADD_SSE_16_8 0
> -    TR_ADD_INIT_SSE_8
> -
> -    paddusb           m0, m4, [r0     ]
> -    paddusb           m1, m6, [r0+r2  ]
> -    paddusb           m2, m8, [r0+r2*2]
> -    paddusb           m3, m10,[r0+r3  ]
> -    psubusb           m0, m5
> -    psubusb           m1, m7
> -    psubusb           m2, m9
> -    psubusb           m3, m11
> -    mova       [r0     ], m0
> -    mova       [r0+r2  ], m1
> -    mova       [r0+2*r2], m2
> -    mova       [r0+r3  ], m3
> -%endmacro
> -
> -%macro TR_ADD_SSE_32_8 0
> -    TR_ADD_INIT_SSE_8
> -
> -    paddusb           m0, m4, [r0      ]
> -    paddusb           m1, m6, [r0+16   ]
> -    paddusb           m2, m8, [r0+r2   ]
> -    paddusb           m3, m10,[r0+r2+16]
> -    psubusb           m0, m5
> -    psubusb           m1, m7
> -    psubusb           m2, m9
> -    psubusb           m3, m11
> -    mova      [r0      ], m0
> -    mova      [r0+16   ], m1
> -    mova      [r0+r2   ], m2
> -    mova      [r0+r2+16], m3
> +%macro TR_ADD_SSE_16_32_8 3
> +    mova              m2, [r1+%1   ]
> +    mova              m6, [r1+%1+16]
> +%if cpuflag(avx)
> +    psubw             m1, m0, m2
> +    psubw             m5, m0, m6
> +%else
> +    mova              m1, m0
> +    mova              m5, m0
> +    psubw             m1, m2
> +    psubw             m5, m6
> +%endif

I was wondering about these blocks - doesn't the x264asm layer
automatically add the mova's when you just use the 3-arg form on sse2?
Or is there a speed benefit grouping the mov's?

- Hendrik