Re: [FFmpeg-devel] [PATCH 2/2] swscale/x86/input: add AVX2 optimized uyvytoyuv422

From: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
To: ffmpeg-devel@ffmpeg.org
Subject: Re: [FFmpeg-devel] [PATCH 2/2] swscale/x86/input: add AVX2 optimized uyvytoyuv422
Date: Wed, 5 Jun 2024 23:00:57 +0200
Message-ID: <GV1P250MB07377FCA744EFA8DC8E501F58FF92@GV1P250MB0737.EURP250.PROD.OUTLOOK.COM> (raw)
In-Reply-To: <20240605202853.3135-2-jamrial@gmail.com>

James Almer:
> uyvytoyuv422_c: 23991.8
> uyvytoyuv422_sse2: 2817.8
> uyvytoyuv422_avx: 2819.3

Why don't you nuke the avx version in a follow-up patch?

> uyvytoyuv422_avx2: 1972.3
> 
> Signed-off-by: James Almer <jamrial@gmail.com>
> ---
>  libswscale/x86/rgb2rgb.c     |  6 ++++++
>  libswscale/x86/rgb_2_rgb.asm | 32 ++++++++++++++++++++++++--------
>  2 files changed, 30 insertions(+), 8 deletions(-)
> 
> diff --git a/libswscale/x86/rgb2rgb.c b/libswscale/x86/rgb2rgb.c
> index b325e5dbd5..21ccfafe51 100644
> --- a/libswscale/x86/rgb2rgb.c
> +++ b/libswscale/x86/rgb2rgb.c
> @@ -136,6 +136,9 @@ void ff_uyvytoyuv422_sse2(uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
>  void ff_uyvytoyuv422_avx(uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
>                           const uint8_t *src, int width, int height,
>                           int lumStride, int chromStride, int srcStride);
> +void ff_uyvytoyuv422_avx2(uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
> +                          const uint8_t *src, int width, int height,
> +                          int lumStride, int chromStride, int srcStride);
>  #endif
>  
>  av_cold void rgb2rgb_init_x86(void)
> @@ -177,5 +180,8 @@ av_cold void rgb2rgb_init_x86(void)
>      if (EXTERNAL_AVX(cpu_flags)) {
>          uyvytoyuv422 = ff_uyvytoyuv422_avx;
>      }
> +    if (EXTERNAL_AVX2_FAST(cpu_flags)) {
> +        uyvytoyuv422 = ff_uyvytoyuv422_avx2;
> +    }
>  #endif
>  }
> diff --git a/libswscale/x86/rgb_2_rgb.asm b/libswscale/x86/rgb_2_rgb.asm
> index 76ca1eec03..0bf1278718 100644
> --- a/libswscale/x86/rgb_2_rgb.asm
> +++ b/libswscale/x86/rgb_2_rgb.asm
> @@ -34,13 +34,16 @@ pb_shuffle3210: db 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
>  
>  SECTION .text
>  
> -%macro RSHIFT_COPY 3
> +%macro RSHIFT_COPY 5
>  ; %1 dst ; %2 src ; %3 shift
> -%if cpuflag(avx)
> -    psrldq  %1, %2, %3
> +%if mmsize == 32
> +    vperm2i128 %1, %2, %3, %5
> +    RSHIFT         %1, %4
> +%elif cpuflag(avx)
> +    psrldq  %1, %2, %4
>  %else
>      mova           %1, %2
> -    RSHIFT         %1, %3
> +    RSHIFT         %1, %4
>  %endif
>  %endmacro
>  
> @@ -233,26 +236,37 @@ cglobal uyvytoyuv422, 9, 14, 8, ydst, udst, vdst, src, w, h, lum_stride, chrom_s
>      jge .end_line
>  
>      .loop_simd:
> +%if mmsize == 32
> +        movu   xm2, [srcq + wtwoq         ]
> +        movu   xm3, [srcq + wtwoq + 16    ]
> +        movu   xm4, [srcq + wtwoq + 16 * 2]
> +        movu   xm5, [srcq + wtwoq + 16 * 3]
> +        vinserti128 m2, m2, [srcq + wtwoq + 16 * 4], 1
> +        vinserti128 m3, m3, [srcq + wtwoq + 16 * 5], 1
> +        vinserti128 m4, m4, [srcq + wtwoq + 16 * 6], 1
> +        vinserti128 m5, m5, [srcq + wtwoq + 16 * 7], 1
> +%else
>          movu    m2, [srcq + wtwoq             ]
>          movu    m3, [srcq + wtwoq + mmsize    ]
>          movu    m4, [srcq + wtwoq + mmsize * 2]
>          movu    m5, [srcq + wtwoq + mmsize * 3]
> +%endif
>  
>          ; extract y part 1
> -        RSHIFT_COPY    m6, m2, 1 ; UYVY UYVY -> YVYU YVY...
> +        RSHIFT_COPY    m6, m2, m4, 1, 0x20 ; UYVY UYVY -> YVYU YVY...
>          pand           m6, m1; YxYx YxYx...
>  
> -        RSHIFT_COPY    m7, m3, 1 ; UYVY UYVY -> YVYU YVY...
> +        RSHIFT_COPY    m7, m3, m5, 1, 0x20 ; UYVY UYVY -> YVYU YVY...
>          pand           m7, m1 ; YxYx YxYx...
>  
>          packuswb       m6, m7 ; YYYY YYYY...
>          movu [ydstq + wq], m6
>  
>          ; extract y part 2
> -        RSHIFT_COPY    m6, m4, 1 ; UYVY UYVY -> YVYU YVY...
> +        RSHIFT_COPY    m6, m4, m2, 1, 0x13 ; UYVY UYVY -> YVYU YVY...
>          pand           m6, m1; YxYx YxYx...
>  
> -        RSHIFT_COPY    m7, m5, 1 ; UYVY UYVY -> YVYU YVY...
> +        RSHIFT_COPY    m7, m5, m3, 1, 0x13 ; UYVY UYVY -> YVYU YVY...
>          pand           m7, m1 ; YxYx YxYx...
>  
>          packuswb                m6, m7 ; YYYY YYYY...
> @@ -309,4 +323,6 @@ UYVY_TO_YUV422
>  
>  INIT_XMM avx
>  UYVY_TO_YUV422
> +INIT_YMM avx2
> +UYVY_TO_YUV422
>  %endif

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".