[FFmpeg-devel] [PATCH] NEON: put_pixels_clamped

[Måns Rullgård]

David Conrad <lessen42 at gmail.com> writes:

> Hi,
>
> Apparently this is used for some wmv3 files in addition to the signed
> variant.
> < 1% faster decode.
>
>
> commit 38cac0d21d8308e077bb762d712ab7c19e8c826d
> Author: David Conrad <davedc at Kozue.local>
> Date:   Thu Apr 16 14:30:29 2009 -0400
>
>     NEON: put_pixels_clamped
>
> diff --git a/libavcodec/arm/dsputil_neon.c b/libavcodec/arm/dsputil_neon.c
> index 37425a3..9b95130 100644
> --- a/libavcodec/arm/dsputil_neon.c
> +++ b/libavcodec/arm/dsputil_neon.c
> @@ -42,6 +42,7 @@ void ff_put_pixels8_xy2_no_rnd_neon(uint8_t *, const uint8_t *, int, int);
>  void ff_avg_pixels16_neon(uint8_t *, const uint8_t *, int, int);
>
>  void ff_add_pixels_clamped_neon(const DCTELEM *, uint8_t *, int);
> +void ff_put_pixels_clamped_neon(const DCTELEM *, uint8_t *, int);
>  void ff_put_signed_pixels_clamped_neon(const DCTELEM *, uint8_t *, int);
>
>  void ff_put_h264_qpel16_mc00_neon(uint8_t *, uint8_t *, int);
> @@ -180,6 +181,7 @@ void ff_dsputil_init_neon(DSPContext *c, AVCodecContext *avctx)
>      c->avg_pixels_tab[0][0] = ff_avg_pixels16_neon;
>
>      c->add_pixels_clamped = ff_add_pixels_clamped_neon;
> +    c->put_pixels_clamped = ff_put_pixels_clamped_neon;
>      c->put_signed_pixels_clamped = ff_put_signed_pixels_clamped_neon;
>
>      c->put_h264_chroma_pixels_tab[0] = ff_put_h264_chroma_mc8_neon;
> diff --git a/libavcodec/arm/dsputil_neon_s.S b/libavcodec/arm/dsputil_neon_s.S
> index f16293d..159ee64 100644
> --- a/libavcodec/arm/dsputil_neon_s.S
> +++ b/libavcodec/arm/dsputil_neon_s.S
> @@ -273,6 +273,30 @@ function ff_put_h264_qpel8_mc00_neon, export=1
>          pixfunc2 put_ pixels8_y2,   _no_rnd, vhadd.u8
>          pixfunc2 put_ pixels8_xy2,  _no_rnd, vshrn.u16, 1
>
> +function ff_put_pixels_clamped_neon, export=1
> +        vld1.64         {d16-d19}, [r0,:128]!
> +        vqmovn.u16      d0, q8
> +        vld1.64         {d20-d23}, [r0,:128]!
> +        vqmovn.u16      d1, q9
> +        vqmovn.u16      d2, q10
> +        vld1.64         {d24-d27}, [r0,:128]!
> +        vqmovn.u16      d3, q11
> +        vqmovn.u16      d4, q12
> +        vld1.64         {d28-d31}, [r0,:128]!
> +        vqmovn.u16      d5, q13
> +        vqmovn.u16      d6, q14
> +        vst1.64         {d0},      [r1,:64], r2
> +        vqmovn.u16      d7, q15
> +        vst1.64         {d1},      [r1,:64], r2
> +        vst1.64         {d2},      [r1,:64], r2
> +        vst1.64         {d3},      [r1,:64], r2
> +        vst1.64         {d4},      [r1,:64], r2
> +        vst1.64         {d5},      [r1,:64], r2
> +        vst1.64         {d6},      [r1,:64], r2
> +        vst1.64         {d7},      [r1,:64], r2
> +        bx              lr
> +        .endfunc

Shouldn't those be vqmovun.s16?  I'd also try to interleave them with
the loads and stores a bit more for better dual-issue opportunities.

-- 
M?ns Rullg?rd
mans at mansr.com