[FFmpeg-devel] [PATCH 7/7] prores: use VLC LUTs

[Andreas Rheinhardt]

Christophe Gisquet:
> One indirection less, around 1% speedup.
> ---
>  libavcodec/proresdec2.c | 16 +++++++++-------
>  1 file changed, 9 insertions(+), 7 deletions(-)
> 
> diff --git a/libavcodec/proresdec2.c b/libavcodec/proresdec2.c
> index b20021c622..85f81d92d3 100644
> --- a/libavcodec/proresdec2.c
> +++ b/libavcodec/proresdec2.c
> @@ -561,12 +561,18 @@ static av_always_inline int decode_dc_coeffs(GetBitContext *gb, int16_t *out,
>          prev_dc += (((code + 1) >> 1) ^ sign) - sign;
>          out[0] = prev_dc;
>      }
> -    return 0;
> +    return 0;	

You are adding trailing whitespace.

>  }
>  
> +#include "libavutil/timer.h"

You really need to look over your patches once more before you send
them. Both of these changes are obviously not ok to commit.

> +
> +
>  static av_always_inline int decode_ac_coeffs(AVCodecContext *avctx, GetBitContext *gb,
>                                               int16_t *out, int blocks_per_slice)
>  {
> +	static VLC* lvl_vlc[9] = { &ac_vlc[0], &ac_vlc[1], &ac_vlc[2], &ac_vlc[3], &ac_vlc[0], &ac_vlc[4], &ac_vlc[4], &ac_vlc[4], &ac_vlc[4], };
> +	static VLC* run_vlc[15] = { &ac_vlc[3], &ac_vlc[3], &ac_vlc[2], &ac_vlc[2], &ac_vlc[0], &ac_vlc[5], &ac_vlc[5], &ac_vlc[5], &ac_vlc[5],
> +	                            &ac_vlc[4], &ac_vlc[4], &ac_vlc[4], &ac_vlc[4], &ac_vlc[4], &ac_vlc[4], };

This still incurs an unnecessary indirection. The LUT should not point
to the VLC's, but rather to the VLC tables (as this is the only thing
needed from them lateron given that the number of bits is a compile-time
constant. The LUT should be initialized when the VLCs are initialized.

In fact, this is so common that I always pondered adding an explicit
function for it. Will probably do so soon.

(Apart from that: This could be "static const VLC *const run_vlc[15]".)

>      const ProresContext *ctx = avctx->priv_data;
>      int block_mask, sign;
>      unsigned pos, run, level;
> @@ -585,9 +591,7 @@ static av_always_inline int decode_ac_coeffs(AVCodecContext *avctx, GetBitContex
>              break;
>  
>          if (run < 15) {
> -            static const uint8_t ctx_to_tbl[] = { 3, 3, 2, 2, 0, 5, 5, 5, 5, 4, 4, 4, 4, 4, 4 };
> -            const VLC* tbl = ac_vlc + ctx_to_tbl[run];
> -            run = get_vlc2(gb, tbl->table, PRORES_LEV_BITS, 3);
> +            run = get_vlc2(gb, run_vlc[run]->table, PRORES_LEV_BITS, 3);
>          } else {
>              unsigned int bits = 21 - 2*av_log2(show_bits(gb, 10));
>              run = READ_BITS(gb, bits) - 4; // up to 17 bits
> @@ -599,9 +603,7 @@ static av_always_inline int decode_ac_coeffs(AVCodecContext *avctx, GetBitContex
>          }
>  
>          if (level < 9) {
> -            static const uint8_t ctx_to_tbl[] = { 0, 1, 2, 3, 0, 4, 4, 4, 4 };
> -            const VLC* tbl = ac_vlc + ctx_to_tbl[level];
> -            level = 1+get_vlc2(gb, tbl->table, PRORES_LEV_BITS, 3);
> +            level = 1+get_vlc2(gb, lvl_vlc[level]->table, PRORES_LEV_BITS, 3);

Seems like these VLCs should be offset by 1 to avoid the "1+".

>          } else {
>              unsigned int bits = 25 - 2*av_log2(show_bits(gb, 12));
>              level = READ_BITS(gb, bits) - 4 + 1; // up to 21 bits