Re: [FFmpeg-devel] [PATCH 09/10] lavc/hevc_ps: reduce the size of ShortTermRPS.used

[James Almer <jamrial@gmail.com>]

On 4/10/2024 10:31 AM, Anton Khirnov wrote:
> It is currently an array of 32 uint8_t, each storing a single flag. A
> single uint32_t is sufficient.
> 
> Reduces sizeof(HEVCSPS) by 1792 bytes.
> ---
>   libavcodec/hevc_ps.c     | 33 +++++++++++++++++++--------------
>   libavcodec/hevc_ps.h     |  2 +-
>   libavcodec/hevc_refs.c   |  6 +++---
>   libavcodec/vulkan_hevc.c |  8 ++++----
>   4 files changed, 27 insertions(+), 22 deletions(-)
> 
> diff --git a/libavcodec/hevc_ps.c b/libavcodec/hevc_ps.c
> index a6b0021bc3..76fe507e7b 100644
> --- a/libavcodec/hevc_ps.c
> +++ b/libavcodec/hevc_ps.c
> @@ -107,6 +107,7 @@ int ff_hevc_decode_short_term_rps(GetBitContext *gb, AVCodecContext *avctx,
>       int k  = 0;
>       int i;
>   
> +    rps->used        = 0;
>       rps->rps_predict = 0;
>   
>       if (rps != sps->st_rps && sps->nb_st_rps)
> @@ -114,6 +115,7 @@ int ff_hevc_decode_short_term_rps(GetBitContext *gb, AVCodecContext *avctx,
>   
>       if (rps->rps_predict) {
>           const ShortTermRPS *rps_ridx;
> +        uint8_t used[32] = { 0 };
>           int delta_rps;
>   
>           if (is_slice_header) {
> @@ -139,13 +141,13 @@ int ff_hevc_decode_short_term_rps(GetBitContext *gb, AVCodecContext *avctx,
>           }
>           delta_rps      = (1 - (rps->delta_rps_sign << 1)) * rps->abs_delta_rps;
>           for (i = 0; i <= rps_ridx->num_delta_pocs; i++) {
> -            int used = rps->used[k] = get_bits1(gb);
> +            used[k] = get_bits1(gb);
>   
>               rps->use_delta_flag = 0;
> -            if (!used)
> +            if (!used[k])
>                   rps->use_delta_flag = get_bits1(gb);
>   
> -            if (used || rps->use_delta_flag) {
> +            if (used[k] || rps->use_delta_flag) {
>                   if (i < rps_ridx->num_delta_pocs)
>                       delta_poc = delta_rps + rps_ridx->delta_poc[i];
>                   else
> @@ -157,7 +159,7 @@ int ff_hevc_decode_short_term_rps(GetBitContext *gb, AVCodecContext *avctx,
>               }
>           }
>   
> -        if (k >= FF_ARRAY_ELEMS(rps->used)) {
> +        if (k >= FF_ARRAY_ELEMS(used)) {
>               av_log(avctx, AV_LOG_ERROR,
>                      "Invalid num_delta_pocs: %d\n", k);
>               return AVERROR_INVALIDDATA;
> @@ -167,35 +169,38 @@ int ff_hevc_decode_short_term_rps(GetBitContext *gb, AVCodecContext *avctx,
>           rps->num_negative_pics = k0;
>           // sort in increasing order (smallest first)
>           if (rps->num_delta_pocs != 0) {
> -            int used, tmp;
> +            int u, tmp;
>               for (i = 1; i < rps->num_delta_pocs; i++) {
>                   delta_poc = rps->delta_poc[i];
> -                used      = rps->used[i];
> +                u         = used[i];
>                   for (k = i - 1; k >= 0; k--) {
>                       tmp = rps->delta_poc[k];
>                       if (delta_poc < tmp) {
>                           rps->delta_poc[k + 1] = tmp;
> -                        rps->used[k + 1]      = rps->used[k];
> +                        used[k + 1]           = used[k];
>                           rps->delta_poc[k]     = delta_poc;
> -                        rps->used[k]          = used;
> +                        used[k]               = u;
>                       }
>                   }
>               }
>           }
>           if ((rps->num_negative_pics >> 1) != 0) {
> -            int used;
> +            int u;
>               k = rps->num_negative_pics - 1;
>               // flip the negative values to largest first
>               for (i = 0; i < rps->num_negative_pics >> 1; i++) {
>                   delta_poc         = rps->delta_poc[i];
> -                used              = rps->used[i];
> +                u                 = used[i];
>                   rps->delta_poc[i] = rps->delta_poc[k];
> -                rps->used[i]      = rps->used[k];
> +                used[i]           = used[k];
>                   rps->delta_poc[k] = delta_poc;
> -                rps->used[k]      = used;
> +                used[k]           = u;
>                   k--;
>               }
>           }
> +
> +        for (unsigned i = 0; i < FF_ARRAY_ELEMS(used); i++)
> +            rps->used |= used[i] * (1 << i);
>       } else {
>           unsigned int nb_positive_pics;
>   
> @@ -222,7 +227,7 @@ int ff_hevc_decode_short_term_rps(GetBitContext *gb, AVCodecContext *avctx,
>                   }
>                   prev -= delta_poc;
>                   rps->delta_poc[i] = prev;
> -                rps->used[i]      = get_bits1(gb);
> +                rps->used        |= get_bits1(gb) * (1 << i);
>               }
>               prev = 0;
>               for (i = 0; i < nb_positive_pics; i++) {
> @@ -235,7 +240,7 @@ int ff_hevc_decode_short_term_rps(GetBitContext *gb, AVCodecContext *avctx,
>                   }
>                   prev += delta_poc;
>                   rps->delta_poc[rps->num_negative_pics + i] = prev;
> -                rps->used[rps->num_negative_pics + i]      = get_bits1(gb);
> +                rps->used                                 |= get_bits1(gb) * (1 << (rps->num_negative_pics + i));
>               }
>           }
>       }
> diff --git a/libavcodec/hevc_ps.h b/libavcodec/hevc_ps.h
> index 6ef29a8ea7..92b85115f7 100644
> --- a/libavcodec/hevc_ps.h
> +++ b/libavcodec/hevc_ps.h
> @@ -79,7 +79,7 @@ typedef struct ShortTermRPS {
>       int num_delta_pocs;
>       int rps_idx_num_delta_pocs;
>       int32_t delta_poc[32];
> -    uint8_t used[32];
> +    uint32_t used;
>   } ShortTermRPS;
>   
>   typedef struct HEVCWindow {
> diff --git a/libavcodec/hevc_refs.c b/libavcodec/hevc_refs.c
> index aed649933d..19f3fa81da 100644
> --- a/libavcodec/hevc_refs.c
> +++ b/libavcodec/hevc_refs.c
> @@ -501,7 +501,7 @@ int ff_hevc_frame_rps(HEVCContext *s)
>           int poc = s->poc + short_rps->delta_poc[i];
>           int list;
>   
> -        if (!short_rps->used[i])
> +        if (!(short_rps->used & (1 << i)))
>               list = ST_FOLL;
>           else if (i < short_rps->num_negative_pics)
>               list = ST_CURR_BEF;
> @@ -540,9 +540,9 @@ int ff_hevc_frame_nb_refs(const HEVCContext *s)
>   
>       if (rps) {
>           for (i = 0; i < rps->num_negative_pics; i++)
> -            ret += !!rps->used[i];
> +            ret += !!(rps->used & (1 << i));
>           for (; i < rps->num_delta_pocs; i++)
> -            ret += !!rps->used[i];
> +            ret += !!(rps->used & (1 << i));
>       }
>   
>       if (long_rps) {
> diff --git a/libavcodec/vulkan_hevc.c b/libavcodec/vulkan_hevc.c
> index 5d7c6b1b64..c2b65fc201 100644
> --- a/libavcodec/vulkan_hevc.c
> +++ b/libavcodec/vulkan_hevc.c
> @@ -374,17 +374,17 @@ static void set_sps(const HEVCSPS *sps, int sps_idx,
>           /* NOTE: This is the predicted, and *reordered* version.
>            * Probably incorrect, but the spec doesn't say which version to use. */
>           for (int j = 0; j < sps->st_rps[i].num_delta_pocs; j++)
> -            str[i].used_by_curr_pic_flag |= sps->st_rps[i].used[j] << j;
> +            str[i].used_by_curr_pic_flag |= st_rps->used;
>   
>           for (int j = 0; j < str[i].num_negative_pics; j++) {
> -            str[i].delta_poc_s0_minus1[j] = st_rps->delta_poc[j] - (j ? st_rps->delta_poc[j - 1] : 0) - 1;
> -            str[i].used_by_curr_pic_s0_flag |= sps->st_rps[i].used[j] << j;
> +            str[i].delta_poc_s0_minus1[j]    = st_rps->delta_poc[j] - (j ? st_rps->delta_poc[j - 1] : 0) - 1;
> +            str[i].used_by_curr_pic_s0_flag |= st_rps->used & ((1 << str[i].num_negative_pics) - 1);

av_mod_uintp2(st_rps->used, str[i].num_negative_pics).

>           }
>   
>           for (int j = 0; j < str[i].num_positive_pics; j++) {
>               str[i].delta_poc_s0_minus1[j] = st_rps->delta_poc[st_rps->num_negative_pics + j] -
>                                               (j ? st_rps->delta_poc[st_rps->num_negative_pics + j - 1] : 0) - 1;
> -            str[i].used_by_curr_pic_s0_flag |= sps->st_rps[i].used[str[i].num_negative_pics + j] << j;
> +            str[i].used_by_curr_pic_s0_flag |= st_rps->used >> str[i].num_negative_pics;
>           }
>       }
>   
_______________________________________________
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".