From patchwork Sun Dec 31 08:18:58 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Nuo Mi X-Patchwork-Id: 45421 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a20:6623:b0:194:e134:edd4 with SMTP id n35csp5659869pzh; Sun, 31 Dec 2023 00:22:07 -0800 (PST) X-Google-Smtp-Source: AGHT+IEiVAA2bw/ymMewX0OGA74DAQoXChPencmqH17GpfRyp4lQEIiX0BgyaGbN4vDnbhE0+t7b X-Received: by 2002:a17:906:2f05:b0:a26:e35b:d824 with SMTP id v5-20020a1709062f0500b00a26e35bd824mr5282718eji.108.1704010927221; Sun, 31 Dec 2023 00:22:07 -0800 (PST) Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id e27-20020a170906249b00b00a27e264197asi439615ejb.218.2023.12.31.00.22.06; Sun, 31 Dec 2023 00:22:07 -0800 (PST) Received-SPF: pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) client-ip=79.124.17.100; Authentication-Results: mx.google.com; dkim=neutral (body hash did not verify) header.i=@outlook.com header.s=selector1 header.b=mZkg5v15; arc=fail (body hash mismatch); spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org; dmarc=fail (p=NONE sp=QUARANTINE dis=NONE) header.from=gmail.com Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 233A668CD59; Sun, 31 Dec 2023 10:20:23 +0200 (EET) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from APC01-PSA-obe.outbound.protection.outlook.com (mail-psaapc01olkn2068.outbound.protection.outlook.com [40.92.52.68]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 72DCD68CDBB for ; Sun, 31 Dec 2023 10:20:15 +0200 (EET) ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=I7iIW/TzMF4O2nvcFure5GbTmgDmwAmUTeqTPWokLAUdEz/CiXXwtnrwZQGliIb3vXKfHpzmT7gAr9lR4rJ/tE3BG7sxtOyxAjv/pW8WmIiRTaFrEyLKjCdmKy6jUoegGNLWBqYb/Zuuv47GLzo1USZqFrkdy29MidkBCHicv3RxIHMTvYcOFYmtCb2ZaKKUL01jYKiCE8/pfrpmb1UYfnnX7HrIo5vG2RqhFinPyZmHSGZsVz4JlJozrW5FOBvMraWP9If/R6blnzKuuK6B8zZbFnzmFC5rLBkw83UZzSLee4Ww9H8/Op6j1TMao8vNX4HSxB0TNUluFiChUn8iMQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector9901; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=Gmh+QPWOseF6xsFDzmu0fuC205XzJrHzgQQAoTvteRE=; b=msjkLGDkNfl86QdxZezjW5XuvfvqZjhsRyiskg/dAtb7l72pJwuJKew4ZV1/0Ky4Xe1ly32pD/CWDf2gWIFUmb++w7VCc7GybUgXSUQ1w8Z5UmV7WlHOOe2y05/SANrGi4BlqMp36SlGNQtJO/bjTTQLMyTU+DRr6xHONwsUxtJK2TtTHSRwru7OrDXr+eRYbjQXz35QvITUlgtxF+PBsU+CnAGFXhD6ijU7metYVVpXUqTzCl+6AEqSCtMfQhAMTjfN+rTnNVp2EEgUzJOL9fx5qp9XA8WWUKsz1oKfQfOu8SBEyqqRw4ZWtlzr4BLeiF365V7kt8aWs3YijELXvQ== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=none; dmarc=none; dkim=none; arc=none DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=outlook.com; s=selector1; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=Gmh+QPWOseF6xsFDzmu0fuC205XzJrHzgQQAoTvteRE=; b=mZkg5v15/oip9kExdcBi0ZbqFtbkbrWCGsKVhbhj1x/z59ToStuDj87C4lAHC3+ViXKORiFmM+5/zJCRvYTNzfQmQO+Es/CnjfqdG8GQZFhOGvFBwGhAxU2DkpPbC8RqFFP8akD64rzuzU96nXbqmFrKe8Eqga48CotwseZb588ZkhWiOLK9rxfJUiRIjN4LjItoFfN4ppExazK0NDUKr3WdfRKsC5ocOb8avzbVzG0dTD2vMOMhJAgkU1d1vG8SFbFC6fT8RIiVWSoIXzcN1NgTvSEHEguC4OFfuoyb8sCK2G+JFJFFC/TpddNSXAqz1rTd5HGKuoxaMPEMHX3RgA== Received: from TYSPR06MB6433.apcprd06.prod.outlook.com (2603:1096:400:47a::6) by JH0PR06MB6367.apcprd06.prod.outlook.com (2603:1096:990:c::8) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.7135.21; Sun, 31 Dec 2023 08:19:55 +0000 Received: from TYSPR06MB6433.apcprd06.prod.outlook.com ([fe80::e139:fd7a:1b66:a3f7]) by TYSPR06MB6433.apcprd06.prod.outlook.com ([fe80::e139:fd7a:1b66:a3f7%6]) with mapi id 15.20.7135.023; Sun, 31 Dec 2023 08:19:55 +0000 From: Nuo Mi To: ffmpeg-devel@ffmpeg.org Date: Sun, 31 Dec 2023 16:18:58 +0800 Message-ID: X-Mailer: git-send-email 2.25.1 In-Reply-To: <20231231081858.1704-1-nuomi2021@gmail.com> References: <20231231081858.1704-1-nuomi2021@gmail.com> X-TMN: [XFQ7ea1IqofnjmHOT8RY2TY7quQ2lsSw] X-ClientProxiedBy: SI2PR02CA0039.apcprd02.prod.outlook.com (2603:1096:4:196::9) To TYSPR06MB6433.apcprd06.prod.outlook.com (2603:1096:400:47a::6) X-Microsoft-Original-Message-ID: <20231231081858.1704-14-nuomi2021@gmail.com> MIME-Version: 1.0 X-MS-Exchange-MessageSentRepresentingType: 2 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: TYSPR06MB6433:EE_|JH0PR06MB6367:EE_ X-MS-Office365-Filtering-Correlation-Id: 6d3bf765-4144-4d0c-b4f2-08dc09d94554 X-Microsoft-Antispam: BCL:0; X-Microsoft-Antispam-Message-Info: 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 X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1 X-MS-Exchange-AntiSpam-MessageData-0: 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 X-OriginatorOrg: outlook.com X-MS-Exchange-CrossTenant-Network-Message-Id: 6d3bf765-4144-4d0c-b4f2-08dc09d94554 X-MS-Exchange-CrossTenant-AuthSource: TYSPR06MB6433.apcprd06.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-OriginalArrivalTime: 31 Dec 2023 08:19:55.8106 (UTC) X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted X-MS-Exchange-CrossTenant-Id: 84df9e7f-e9f6-40af-b435-aaaaaaaaaaaa X-MS-Exchange-CrossTenant-RMS-PersistedConsumerOrg: 00000000-0000-0000-0000-000000000000 X-MS-Exchange-Transport-CrossTenantHeadersStamped: JH0PR06MB6367 Subject: [FFmpeg-devel] [PATCH v8 13/13] vvcdec: add vvc decoder X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: FFmpeg development discussions and patches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: FFmpeg development discussions and patches Cc: Nuo Mi Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" X-TUID: lxwiOB0VQfDc vvc decoder plug-in to avcodec. split frames into slices/tiles and send them to vvc_thread for further decoding reorder and wait for the frame decoding to be done and output the frame Features: + Support I, P, B frames + Support 8/10/12 bits, chroma 400, 420, 422, and 444 and range extension + Support VVC new tools like MIP, CCLM, AFFINE, GPM, DMVR, PROF, BDOF, LMCS, ALF + 295 conformace clips passed - Not support RPR, IBC, PALETTE, and other minor features yet Performance: C code FPS on an i7-12700K (x86): BQTerrace_1920x1080_60_10_420_22_RA.vvc 93.0 Chimera_8bit_1080P_1000_frames.vvc 184.3 NovosobornayaSquare_1920x1080.bin 191.3 RitualDance_1920x1080_60_10_420_32_LD.266 150.7 RitualDance_1920x1080_60_10_420_37_RA.266 170.0 Tango2_3840x2160_60_10_420_27_LD.266 33.7 C code FPS on a M1 Mac Pro (ARM): BQTerrace_1920x1080_60_10_420_22_RA.vvc 58.7 Chimera_8bit_1080P_1000_frames.vvc 153.3 NovosobornayaSquare_1920x1080.bin 150.3 RitualDance_1920x1080_60_10_420_32_LD.266 105.0 RitualDance_1920x1080_60_10_420_37_RA.266 133.0 Tango2_3840x2160_60_10_420_27_LD.266 21.7 Asm optimizations still working in progress. please check https://github.com/ffvvc/FFmpeg/wiki#performance-data for the latest Contributors(based on code merge order): Nuo Mi Xu Mu frankplow Shaun Loo --- Changelog | 1 + configure | 1 + libavcodec/allcodecs.c | 1 + libavcodec/version.h | 2 +- libavcodec/vvc/Makefile | 3 +- libavcodec/vvc/vvcdec.c | 1017 +++++++++++++++++++++++++++++++++++++++ 6 files changed, 1023 insertions(+), 2 deletions(-) create mode 100644 libavcodec/vvc/vvcdec.c diff --git a/Changelog b/Changelog index a638c03250..0451f265bc 100644 --- a/Changelog +++ b/Changelog @@ -13,6 +13,7 @@ version : - IAMF raw demuxer and muxer - D3D12VA hardware accelerated H264, HEVC, VP9, AV1, MPEG-2 and VC1 decoding - tiltandshift filter +- VVC decoder version 6.1: - libaribcaption decoder diff --git a/configure b/configure index cd66e42850..30a3d57f54 100755 --- a/configure +++ b/configure @@ -3025,6 +3025,7 @@ vp6f_decoder_select="vp6_decoder" vp7_decoder_select="h264pred videodsp vp8dsp" vp8_decoder_select="h264pred videodsp vp8dsp" vp9_decoder_select="videodsp vp9_parser vp9_superframe_split_bsf" +vvc_decoder_select="cabac golomb videodsp" wcmv_decoder_select="inflate_wrapper" webp_decoder_select="vp8_decoder exif" wmalossless_decoder_select="llauddsp" diff --git a/libavcodec/allcodecs.c b/libavcodec/allcodecs.c index b0f004e15c..93ce8e3224 100644 --- a/libavcodec/allcodecs.c +++ b/libavcodec/allcodecs.c @@ -389,6 +389,7 @@ extern const FFCodec ff_vp9_rkmpp_decoder; extern const FFCodec ff_vp9_v4l2m2m_decoder; extern const FFCodec ff_vqa_decoder; extern const FFCodec ff_vqc_decoder; +extern const FFCodec ff_vvc_decoder; extern const FFCodec ff_wbmp_decoder; extern const FFCodec ff_wbmp_encoder; extern const FFCodec ff_webp_decoder; diff --git a/libavcodec/version.h b/libavcodec/version.h index 34b059a8a9..376388c5bb 100644 --- a/libavcodec/version.h +++ b/libavcodec/version.h @@ -29,7 +29,7 @@ #include "version_major.h" -#define LIBAVCODEC_VERSION_MINOR 36 +#define LIBAVCODEC_VERSION_MINOR 37 #define LIBAVCODEC_VERSION_MICRO 100 #define LIBAVCODEC_VERSION_INT AV_VERSION_INT(LIBAVCODEC_VERSION_MAJOR, \ diff --git a/libavcodec/vvc/Makefile b/libavcodec/vvc/Makefile index 40bb509a8c..3ff0b8bcc1 100644 --- a/libavcodec/vvc/Makefile +++ b/libavcodec/vvc/Makefile @@ -1,6 +1,7 @@ clean:: $(RM) $(CLEANSUFFIXES:%=libavcodec/vvc/%) -OBJS-$(CONFIG_VVC_DECODER) += vvc/vvcdsp.o \ +OBJS-$(CONFIG_VVC_DECODER) += vvc/vvcdec.o \ + vvc/vvcdsp.o \ vvc/vvc_cabac.o \ vvc/vvc_ctu.o \ vvc/vvc_data.o \ diff --git a/libavcodec/vvc/vvcdec.c b/libavcodec/vvc/vvcdec.c new file mode 100644 index 0000000000..608d497cb7 --- /dev/null +++ b/libavcodec/vvc/vvcdec.c @@ -0,0 +1,1017 @@ +/* + * VVC video decoder + * + * Copyright (C) 2021 Nuo Mi + * Copyright (C) 2022 Xu Mu + * + * This file is part of FFmpeg. + * + * FFmpeg is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * FFmpeg is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with FFmpeg; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ +#include "libavcodec/codec_internal.h" +#include "libavcodec/decode.h" +#include "libavcodec/profiles.h" +#include "libavcodec/refstruct.h" +#include "libavutil/cpu.h" +#include "libavutil/thread.h" + +#include "vvcdec.h" +#include "vvc_ctu.h" +#include "vvc_data.h" +#include "vvc_refs.h" +#include "vvc_thread.h" + +#define TAB_MAX 32 + +typedef struct Tab { + void **tab; + size_t size; +} Tab; + +typedef struct TabList { + Tab tabs[TAB_MAX]; + int nb_tabs; + + int zero; + int realloc; +} TabList; + +#define TL_ADD(t, s) do { \ + av_assert0(l->nb_tabs < TAB_MAX); \ + l->tabs[l->nb_tabs].tab = (void**)&fc->tab.t; \ + l->tabs[l->nb_tabs].size = sizeof(*fc->tab.t) * (s); \ + l->nb_tabs++; \ +} while (0) + +static size_t tl_size(const TabList *l) +{ + size_t total = 0; + for (int i = 0; i < l->nb_tabs; i++) + total += l->tabs[i].size; + return total; +} + +static void tl_init(TabList *l, const int zero, const int realloc) +{ + l->nb_tabs = 0; + l->zero = zero; + l->realloc = realloc; +} + +static int tl_free(TabList *l) +{ + for (int i = 1; i < l->nb_tabs; i++) { + void **p = l->tabs[i].tab; + *p = NULL; + } + av_freep(l->tabs[0].tab); + return 0; +} + +static int tl_create(TabList *l) +{ + size_t size = tl_size(l); + if (l->realloc) { + uint8_t *p = l->zero ? av_mallocz(size) : av_malloc(size); + if (!p) + return AVERROR(ENOMEM); + tl_free(l); + + // set pointer for each table + for (int i = 0; i < l->nb_tabs; i++) { + Tab *t = l->tabs + i; + *t->tab = p; + p += t->size; + } + } else { + if (l->zero) + memset(*l->tabs[0].tab, 0, size); + } + return 0; +} + +static void ctu_tl_init(TabList *l, VVCFrameContext *fc) +{ + const VVCPPS *pps = fc->ps.pps; + const int ctu_count = pps ? pps->ctb_count : 0; + const int changed = fc->tab.sz.ctu_count != ctu_count; + + tl_init(l, 1, changed); + + TL_ADD(deblock, ctu_count); + TL_ADD(sao, ctu_count); + TL_ADD(alf, ctu_count); + TL_ADD(ctus, ctu_count); +} + +static void ctu_nz_tl_init(TabList *l, VVCFrameContext *fc) +{ + const VVCSPS *sps = fc->ps.sps; + const VVCPPS *pps = fc->ps.pps; + const int ctu_size = sps ? (1 << sps->ctb_log2_size_y << sps->ctb_log2_size_y) : 0; + const int ctu_count = pps ? pps->ctb_count : 0; + const int changed = fc->tab.sz.ctu_count != ctu_count || fc->tab.sz.ctu_size != ctu_size; + + tl_init(l, 0, changed); + TL_ADD(slice_idx, ctu_count); + TL_ADD(coeffs, ctu_count * ctu_size * VVC_MAX_SAMPLE_ARRAYS); +} + +static void min_cb_tl_init(TabList *l, VVCFrameContext *fc) +{ + const VVCPPS *pps = fc->ps.pps; + const int pic_size_in_min_cb = pps ? pps->min_cb_width * pps->min_cb_height : 0; + const int changed = fc->tab.sz.pic_size_in_min_cb != pic_size_in_min_cb; + + tl_init(l, 1, changed); + + TL_ADD(skip, pic_size_in_min_cb); + TL_ADD(imf, pic_size_in_min_cb); + TL_ADD(imtf, pic_size_in_min_cb); + TL_ADD(imm, pic_size_in_min_cb); + TL_ADD(ipm, pic_size_in_min_cb); + + for (int i = LUMA; i <= CHROMA; i++) { + TL_ADD(cb_pos_x[i], pic_size_in_min_cb); + TL_ADD(cb_pos_y[i], pic_size_in_min_cb); + TL_ADD(cb_width[i], pic_size_in_min_cb); + TL_ADD(cb_height[i], pic_size_in_min_cb); + TL_ADD(cqt_depth[i], pic_size_in_min_cb); + TL_ADD(cpm[i], pic_size_in_min_cb); + TL_ADD(cp_mv[i], pic_size_in_min_cb * MAX_CONTROL_POINTS); + }; +} + +static void min_pu_tl_init(TabList *l, VVCFrameContext *fc) +{ + const VVCPPS *pps = fc->ps.pps; + const int pic_size_in_min_pu = pps ? pps->min_pu_width * pps->min_pu_height : 0; + const int changed = fc->tab.sz.pic_size_in_min_pu != pic_size_in_min_pu; + + tl_init(l, 1, changed); + + TL_ADD(msf, pic_size_in_min_pu); + TL_ADD(iaf, pic_size_in_min_pu); + TL_ADD(mmi, pic_size_in_min_pu); + TL_ADD(mvf, pic_size_in_min_pu); +} + +static void min_tu_tl_init(TabList *l, VVCFrameContext *fc) +{ + const VVCPPS *pps = fc->ps.pps; + const int pic_size_in_min_tu = pps ? pps->min_tu_width * pps->min_tu_height : 0; + const int changed = fc->tab.sz.pic_size_in_min_tu != pic_size_in_min_tu; + + tl_init(l, 1, changed); + + TL_ADD(tu_joint_cbcr_residual_flag, pic_size_in_min_tu); + for (int i = LUMA; i <= CHROMA; i++) { + TL_ADD(tb_pos_x0[i], pic_size_in_min_tu); + TL_ADD(tb_pos_y0[i], pic_size_in_min_tu); + TL_ADD(tb_width[i], pic_size_in_min_tu); + TL_ADD(tb_height[i], pic_size_in_min_tu); + TL_ADD(pcmf[i], pic_size_in_min_tu); + } + + for (int i = 0; i < VVC_MAX_SAMPLE_ARRAYS; i++) { + TL_ADD(tu_coded_flag[i], pic_size_in_min_tu); + TL_ADD(qp[i], pic_size_in_min_tu); + } +} + +static void bs_tl_init(TabList *l, VVCFrameContext *fc) +{ + const VVCPPS *pps = fc->ps.pps; + const int bs_width = pps ? (pps->width >> 2) + 1 : 0; + const int bs_height = pps ? (pps->height >> 2) + 1 : 0; + const int bs_count = bs_width * bs_height; + const int changed = fc->tab.sz.bs_width != bs_width || + fc->tab.sz.bs_height != bs_height; + + tl_init(l, 1, changed); + + for (int i = 0; i < VVC_MAX_SAMPLE_ARRAYS; i++) { + TL_ADD(horizontal_bs[i], bs_count); + TL_ADD(vertical_bs[i], bs_count); + } + TL_ADD(horizontal_q, bs_count); + TL_ADD(horizontal_p, bs_count); + TL_ADD(vertical_p, bs_count); + TL_ADD(vertical_q, bs_count); +} + +static void pixel_buffer_nz_tl_init(TabList *l, VVCFrameContext *fc) +{ + const VVCSPS *sps = fc->ps.sps; + const VVCPPS *pps = fc->ps.pps; + const int width = pps ? pps->width : 0; + const int height = pps ? pps->height : 0; + const int ctu_width = pps ? pps->ctb_width : 0; + const int ctu_height = pps ? pps->ctb_height : 0; + const int chroma_idc = sps ? sps->r->sps_chroma_format_idc : 0; + const int ps = sps ? sps->pixel_shift : 0; + const int c_end = chroma_idc ? VVC_MAX_SAMPLE_ARRAYS : 1; + const int changed = fc->tab.sz.chroma_format_idc != chroma_idc || + fc->tab.sz.width != width || fc->tab.sz.height != height || + fc->tab.sz.ctu_width != ctu_width || fc->tab.sz.ctu_height != ctu_height; + + tl_init(l, 0, changed); + + for (int c_idx = 0; c_idx < c_end; c_idx++) { + const int w = width >> (sps ? sps->hshift[c_idx] : 0); + const int h = height >> (sps ? sps->vshift[c_idx] : 0); + TL_ADD(sao_pixel_buffer_h[c_idx], (w * 2 * ctu_height) << ps); + TL_ADD(sao_pixel_buffer_v[c_idx], (h * 2 * ctu_width) << ps); + } + + for (int c_idx = 0; c_idx < c_end; c_idx++) { + const int w = width >> (sps ? sps->hshift[c_idx] : 0); + const int h = height >> (sps ? sps->vshift[c_idx] : 0); + const int border_pixels = c_idx ? ALF_BORDER_CHROMA : ALF_BORDER_LUMA; + for (int i = 0; i < 2; i++) { + TL_ADD(alf_pixel_buffer_h[c_idx][i], (w * border_pixels * ctu_height) << ps); + TL_ADD(alf_pixel_buffer_v[c_idx][i], h * ALF_PADDING_SIZE * ctu_width); + } + } +} + +static void msm_tl_init(TabList *l, VVCFrameContext *fc) +{ + const VVCPPS *pps = fc->ps.pps; + const int w32 = pps ? AV_CEIL_RSHIFT(pps->width, 5) : 0; + const int h32 = pps ? AV_CEIL_RSHIFT(pps->height, 5) : 0; + const int changed = AV_CEIL_RSHIFT(fc->tab.sz.width, 5) != w32 || + AV_CEIL_RSHIFT(fc->tab.sz.height, 5) != h32; + + tl_init(l, 1, changed); + + for (int i = LUMA; i <= CHROMA; i++) + TL_ADD(msm[i], w32 * h32); +} + +static void ispmf_tl_init(TabList *l, VVCFrameContext *fc) +{ + const VVCPPS *pps = fc->ps.pps; + const int w64 = pps ? AV_CEIL_RSHIFT(pps->width, 6) : 0; + const int h64 = pps ? AV_CEIL_RSHIFT(pps->height, 6) : 0; + const int changed = AV_CEIL_RSHIFT(fc->tab.sz.width, 6) != w64 || + AV_CEIL_RSHIFT(fc->tab.sz.height, 6) != h64; + + tl_init(l, 1, changed); + + TL_ADD(ispmf, w64 * h64); +} + +typedef void (*tl_init_fn)(TabList *l, VVCFrameContext *fc); + +static int frame_context_for_each_tl(VVCFrameContext *fc, int (*unary_fn)(TabList *l)) +{ + const tl_init_fn init[] = { + ctu_tl_init, + ctu_nz_tl_init, + min_cb_tl_init, + min_pu_tl_init, + min_tu_tl_init, + bs_tl_init, + pixel_buffer_nz_tl_init, + msm_tl_init, + ispmf_tl_init, + }; + + for (int i = 0; i < FF_ARRAY_ELEMS(init); i++) { + TabList l; + int ret; + + init[i](&l, fc); + ret = unary_fn(&l); + if (ret < 0) + return ret; + } + return 0; +} + +static void free_cus(VVCFrameContext *fc) +{ + if (fc->tab.ctus) { + for (int i = 0; i < fc->tab.sz.ctu_count; i++) + ff_vvc_ctu_free_cus(fc->tab.ctus + i); + } +} + +static void pic_arrays_free(VVCFrameContext *fc) +{ + free_cus(fc); + frame_context_for_each_tl(fc, tl_free); + ff_refstruct_pool_uninit(&fc->rpl_tab_pool); + ff_refstruct_pool_uninit(&fc->tab_dmvr_mvf_pool); + + memset(&fc->tab.sz, 0, sizeof(fc->tab.sz)); +} + +static int pic_arrays_init(VVCContext *s, VVCFrameContext *fc) +{ + const VVCSPS *sps = fc->ps.sps; + const VVCPPS *pps = fc->ps.pps; + const int ctu_count = pps->ctb_count; + const int pic_size_in_min_pu = pps->min_pu_width * pps->min_pu_height; + int ret; + + free_cus(fc); + + ret = frame_context_for_each_tl(fc, tl_create); + if (ret < 0) + return ret; + + memset(fc->tab.slice_idx, -1, sizeof(*fc->tab.slice_idx) * fc->tab.sz.ctu_count); + + if (fc->tab.sz.ctu_count != ctu_count) { + ff_refstruct_pool_uninit(&fc->rpl_tab_pool); + fc->rpl_tab_pool = ff_refstruct_pool_alloc(ctu_count * sizeof(RefPicListTab), 0); + if (!fc->rpl_tab_pool) + return AVERROR(ENOMEM); + } + + if (fc->tab.sz.pic_size_in_min_pu != pic_size_in_min_pu) { + ff_refstruct_pool_uninit(&fc->tab_dmvr_mvf_pool); + fc->tab_dmvr_mvf_pool = ff_refstruct_pool_alloc( + pic_size_in_min_pu * sizeof(MvField), FF_REFSTRUCT_POOL_FLAG_ZERO_EVERY_TIME); + if (!fc->tab_dmvr_mvf_pool) + return AVERROR(ENOMEM); + } + + fc->tab.sz.ctu_count = pps->ctb_count; + fc->tab.sz.ctu_size = 1 << sps->ctb_log2_size_y << sps->ctb_log2_size_y; + fc->tab.sz.pic_size_in_min_cb = pps->min_cb_width * pps->min_cb_height; + fc->tab.sz.pic_size_in_min_pu = pic_size_in_min_pu; + fc->tab.sz.pic_size_in_min_tu = pps->min_tu_width * pps->min_tu_height; + fc->tab.sz.width = pps->width; + fc->tab.sz.height = pps->height; + fc->tab.sz.ctu_width = pps->ctb_width; + fc->tab.sz.ctu_height = pps->ctb_height; + fc->tab.sz.chroma_format_idc = sps->r->sps_chroma_format_idc; + fc->tab.sz.pixel_shift = sps->pixel_shift; + fc->tab.sz.bs_width = (fc->ps.pps->width >> 2) + 1; + fc->tab.sz.bs_height = (fc->ps.pps->height >> 2) + 1; + + return 0; +} + +static int min_positive(const int idx, const int diff, const int min_diff) +{ + return diff > 0 && (idx < 0 || diff < min_diff); +} + +static int max_negtive(const int idx, const int diff, const int max_diff) +{ + return diff < 0 && (idx < 0 || diff > max_diff); +} + +typedef int (*smvd_find_fxn)(const int idx, const int diff, const int old_diff); + +static int8_t smvd_find(const VVCFrameContext *fc, const SliceContext *sc, int lx, smvd_find_fxn find) +{ + const H266RawSliceHeader *rsh = sc->sh.r; + const RefPicList *rpl = sc->rpl + lx; + const int poc = fc->ref->poc; + int8_t idx = -1; + int old_diff = -1; + for (int i = 0; i < rsh->num_ref_idx_active[lx]; i++) { + if (!rpl->isLongTerm[i]) { + int diff = poc - rpl->list[i]; + if (find(idx, diff, old_diff)) { + idx = i; + old_diff = diff; + } + } + } + return idx; +} + +static void smvd_ref_idx(const VVCFrameContext *fc, SliceContext *sc) +{ + VVCSH *sh = &sc->sh; + if (IS_B(sh->r)) { + sh->ref_idx_sym[0] = smvd_find(fc, sc, 0, min_positive); + sh->ref_idx_sym[1] = smvd_find(fc, sc, 1, max_negtive); + if (sh->ref_idx_sym[0] == -1 || sh->ref_idx_sym[1] == -1) { + sh->ref_idx_sym[0] = smvd_find(fc, sc, 0, max_negtive); + sh->ref_idx_sym[1] = smvd_find(fc, sc, 1, min_positive); + } + } +} + +static void eps_free(SliceContext *slice) +{ + av_freep(&slice->eps); + slice->nb_eps = 0; +} + +static void slices_free(VVCFrameContext *fc) +{ + if (fc->slices) { + for (int i = 0; i < fc->nb_slices_allocated; i++) { + SliceContext *slice = fc->slices[i]; + if (slice) { + ff_refstruct_unref(&slice->ref); + ff_refstruct_unref(&slice->sh.r); + eps_free(slice); + av_free(slice); + } + } + av_freep(&fc->slices); + } + fc->nb_slices_allocated = 0; + fc->nb_slices = 0; +} + +static int slices_realloc(VVCFrameContext *fc) +{ + void *p; + const int size = (fc->nb_slices_allocated + 1) * 3 / 2; + + if (fc->nb_slices < fc->nb_slices_allocated) + return 0; + + p = av_realloc_array(fc->slices, size, sizeof(*fc->slices)); + if (!p) + return AVERROR(ENOMEM); + + fc->slices = p; + for (int i = fc->nb_slices_allocated; i < size; i++) { + fc->slices[i] = av_mallocz(sizeof(*fc->slices[0])); + if (!fc->slices[i]) { + fc->nb_slices_allocated = i; + return AVERROR(ENOMEM); + } + fc->slices[i]->slice_idx = i; + } + fc->nb_slices_allocated = size; + + return 0; +} + +static void ep_init_cabac_decoder(SliceContext *sc, const int index, + const H2645NAL *nal, GetBitContext *gb) +{ + const H266RawSliceHeader *rsh = sc->sh.r; + EntryPoint *ep = sc->eps + index; + int size; + + if (index < rsh->num_entry_points) { + int skipped = 0; + int64_t start = (gb->index >> 3); + int64_t end = start + rsh->sh_entry_point_offset_minus1[index] + 1; + while (skipped < nal->skipped_bytes && nal->skipped_bytes_pos[skipped] <= start) { + skipped++; + } + while (skipped < nal->skipped_bytes && nal->skipped_bytes_pos[skipped] < end) { + end--; + skipped++; + } + size = end - start; + } else { + size = get_bits_left(gb) / 8; + } + ff_init_cabac_decoder (&ep->cc, gb->buffer + get_bits_count(gb) / 8, size); + skip_bits(gb, size * 8); +} + +static int slice_init_entry_points(SliceContext *sc, + VVCFrameContext *fc, const H2645NAL *nal, const CodedBitstreamUnit *unit) +{ + const VVCSH *sh = &sc->sh; + const H266RawSlice *slice = unit->content_ref; + int nb_eps = sh->r->num_entry_points + 1; + int ctu_addr = 0; + GetBitContext gb; + + if (sc->nb_eps != nb_eps) { + eps_free(sc); + sc->eps = av_calloc(nb_eps, sizeof(*sc->eps)); + if (!sc->eps) + return AVERROR(ENOMEM); + sc->nb_eps = nb_eps; + } + + init_get_bits8(&gb, slice->data, slice->data_size); + for (int i = 0; i < sc->nb_eps; i++) + { + EntryPoint *ep = sc->eps + i; + + ep->ctu_start = ctu_addr; + ep->ctu_end = (i + 1 == sc->nb_eps ? sh->num_ctus_in_curr_slice : sh->entry_point_start_ctu[i]); + + for (int j = ep->ctu_start; j < ep->ctu_end; j++) { + const int rs = sc->sh.ctb_addr_in_curr_slice[j]; + fc->tab.slice_idx[rs] = sc->slice_idx; + } + + ep_init_cabac_decoder(sc, i, nal, &gb); + + if (i + 1 < sc->nb_eps) + ctu_addr = sh->entry_point_start_ctu[i]; + } + + return 0; +} + +static VVCFrameContext* get_frame_context(const VVCContext *s, const VVCFrameContext *fc, const int delta) +{ + const int size = s->nb_fcs; + const int idx = (fc - s->fcs + delta + size) % size; + return s->fcs + idx; +} + +static int ref_frame(VVCFrame *dst, const VVCFrame *src) +{ + int ret; + + ret = av_frame_ref(dst->frame, src->frame); + if (ret < 0) + return ret; + + ff_refstruct_replace(&dst->progress, src->progress); + + ff_refstruct_replace(&dst->tab_dmvr_mvf, src->tab_dmvr_mvf); + + ff_refstruct_replace(&dst->rpl_tab, src->rpl_tab); + ff_refstruct_replace(&dst->rpl, src->rpl); + dst->nb_rpl_elems = src->nb_rpl_elems; + + dst->poc = src->poc; + dst->ctb_count = src->ctb_count; + dst->flags = src->flags; + dst->sequence = src->sequence; + + return 0; +} + +static av_cold void frame_context_free(VVCFrameContext *fc) +{ + slices_free(fc); + + ff_refstruct_pool_uninit(&fc->tu_pool); + ff_refstruct_pool_uninit(&fc->cu_pool); + + for (int i = 0; i < FF_ARRAY_ELEMS(fc->DPB); i++) { + ff_vvc_unref_frame(fc, &fc->DPB[i], ~0); + av_frame_free(&fc->DPB[i].frame); + } + + ff_vvc_frame_thread_free(fc); + pic_arrays_free(fc); + av_frame_free(&fc->output_frame); + ff_vvc_frame_ps_free(&fc->ps); +} + +static av_cold int frame_context_init(VVCFrameContext *fc, AVCodecContext *avctx) +{ + + fc->log_ctx = avctx; + + fc->output_frame = av_frame_alloc(); + if (!fc->output_frame) + return AVERROR(ENOMEM); + + for (int j = 0; j < FF_ARRAY_ELEMS(fc->DPB); j++) { + fc->DPB[j].frame = av_frame_alloc(); + if (!fc->DPB[j].frame) + return AVERROR(ENOMEM); + } + fc->cu_pool = ff_refstruct_pool_alloc(sizeof(CodingUnit), 0); + if (!fc->cu_pool) + return AVERROR(ENOMEM); + + fc->tu_pool = ff_refstruct_pool_alloc(sizeof(TransformUnit), 0); + if (!fc->tu_pool) + return AVERROR(ENOMEM); + + return 0; +} + +static int frame_context_setup(VVCFrameContext *fc, VVCContext *s) +{ + int ret; + + // copy refs from the last frame + if (s->nb_frames && s->nb_fcs > 1) { + VVCFrameContext *prev = get_frame_context(s, fc, -1); + for (int i = 0; i < FF_ARRAY_ELEMS(fc->DPB); i++) { + ff_vvc_unref_frame(fc, &fc->DPB[i], ~0); + if (prev->DPB[i].frame->buf[0]) { + ret = ref_frame(&fc->DPB[i], &prev->DPB[i]); + if (ret < 0) + return ret; + } + } + } + + if (IS_IDR(s)) { + s->seq_decode = (s->seq_decode + 1) & 0xff; + ff_vvc_clear_refs(fc); + } + + ret = pic_arrays_init(s, fc); + if (ret < 0) + return ret; + ff_vvc_dsp_init(&fc->vvcdsp, fc->ps.sps->bit_depth); + ff_videodsp_init(&fc->vdsp, fc->ps.sps->bit_depth); + return 0; +} + +static int frame_start(VVCContext *s, VVCFrameContext *fc, SliceContext *sc) +{ + const VVCPH *ph = &fc->ps.ph; + const H266RawSliceHeader *rsh = sc->sh.r; + int ret; + + // 8.3.1 Decoding process for picture order count + if (!s->temporal_id && !ph->r->ph_non_ref_pic_flag && !(IS_RASL(s) || IS_RADL(s))) + s->poc_tid0 = ph->poc; + + if ((ret = ff_vvc_set_new_ref(s, fc, &fc->frame)) < 0) + goto fail; + + if (!IS_IDR(s)) + ff_vvc_bump_frame(s, fc); + + av_frame_unref(fc->output_frame); + + if ((ret = ff_vvc_output_frame(s, fc, fc->output_frame,rsh->sh_no_output_of_prior_pics_flag, 0)) < 0) + goto fail; + + if ((ret = ff_vvc_frame_rpl(s, fc, sc)) < 0) + goto fail; + + if ((ret = ff_vvc_frame_thread_init(fc)) < 0) + goto fail; + return 0; +fail: + if (fc->ref) + ff_vvc_unref_frame(fc, fc->ref, ~0); + fc->ref = NULL; + return ret; +} + +static int slice_start(SliceContext *sc, VVCContext *s, VVCFrameContext *fc, + const CodedBitstreamUnit *unit, const int is_first_slice) +{ + VVCSH *sh = &sc->sh; + int ret; + + ret = ff_vvc_decode_sh(sh, &fc->ps, unit); + if (ret < 0) + return ret; + + ff_refstruct_replace(&sc->ref, unit->content_ref); + + if (is_first_slice) { + ret = frame_start(s, fc, sc); + if (ret < 0) + return ret; + } else if (fc->ref) { + if (!IS_I(sh->r)) { + ret = ff_vvc_slice_rpl(s, fc, sc); + if (ret < 0) { + av_log(fc->log_ctx, AV_LOG_WARNING, + "Error constructing the reference lists for the current slice.\n"); + return ret; + } + } + } else { + av_log(fc->log_ctx, AV_LOG_ERROR, "First slice in a frame missing.\n"); + return ret; + } + + if (!IS_I(sh->r)) + smvd_ref_idx(fc, sc); + + return 0; +} + +static void export_frame_params(VVCContext *s, const VVCFrameContext *fc) +{ + AVCodecContext *c = s->avctx; + const VVCSPS *sps = fc->ps.sps; + const VVCPPS *pps = fc->ps.pps; + + c->pix_fmt = sps->pix_fmt; + c->coded_width = pps->width; + c->coded_height = pps->height; + c->width = pps->width - pps->r->pps_conf_win_left_offset - pps->r->pps_conf_win_right_offset; + c->height = pps->height - pps->r->pps_conf_win_top_offset - pps->r->pps_conf_win_bottom_offset; +} + +static int frame_setup(VVCFrameContext *fc, VVCContext *s) +{ + int ret = ff_vvc_decode_frame_ps(&fc->ps, s); + if (ret < 0) + return ret; + + ret = frame_context_setup(fc, s); + if (ret < 0) + return ret; + + export_frame_params(s, fc); + return ret; +} + +static int decode_slice(VVCContext *s, VVCFrameContext *fc, const H2645NAL *nal, const CodedBitstreamUnit *unit) +{ + int ret; + SliceContext *sc; + const int is_first_slice = !fc->nb_slices; + + ret = slices_realloc(fc); + if (ret < 0) + return ret; + + sc = fc->slices[fc->nb_slices]; + + s->vcl_unit_type = nal->type; + if (is_first_slice) { + ret = frame_setup(fc, s); + if (ret < 0) + return ret; + } + + ret = slice_start(sc, s, fc, unit, is_first_slice); + if (ret < 0) + return ret; + + ret = slice_init_entry_points(sc, fc, nal, unit); + if (ret < 0) + return ret; + fc->nb_slices++; + + return 0; +} + +static int decode_nal_unit(VVCContext *s, VVCFrameContext *fc, const H2645NAL *nal, const CodedBitstreamUnit *unit) +{ + int ret; + + s->temporal_id = nal->temporal_id; + + switch (unit->type) { + case VVC_VPS_NUT: + case VVC_SPS_NUT: + case VVC_PPS_NUT: + /* vps, sps, sps cached by s->cbc */ + break; + case VVC_TRAIL_NUT: + case VVC_STSA_NUT: + case VVC_RADL_NUT: + case VVC_RASL_NUT: + case VVC_IDR_W_RADL: + case VVC_IDR_N_LP: + case VVC_CRA_NUT: + case VVC_GDR_NUT: + ret = decode_slice(s, fc, nal, unit); + if (ret < 0) + return ret; + break; + case VVC_PREFIX_APS_NUT: + case VVC_SUFFIX_APS_NUT: + ret = ff_vvc_decode_aps(&s->ps, unit); + if (ret < 0) + return ret; + break; + } + + return 0; +} + +static int decode_nal_units(VVCContext *s, VVCFrameContext *fc, AVPacket *avpkt) +{ + const CodedBitstreamH266Context *h266 = s->cbc->priv_data; + CodedBitstreamFragment *frame = &s->current_frame; + int ret = 0; + int eos_at_start = 1; + s->last_eos = s->eos; + s->eos = 0; + + ff_cbs_fragment_reset(frame); + ret = ff_cbs_read_packet(s->cbc, frame, avpkt); + if (ret < 0) { + av_log(s->avctx, AV_LOG_ERROR, "Failed to read packet.\n"); + return ret; + } + /* decode the NAL units */ + for (int i = 0; i < frame->nb_units; i++) { + const H2645NAL *nal = h266->common.read_packet.nals + i; + const CodedBitstreamUnit *unit = frame->units + i; + + if (unit->type == VVC_EOB_NUT || unit->type == VVC_EOS_NUT) { + if (eos_at_start) + s->last_eos = 1; + else + s->eos = 1; + } else { + ret = decode_nal_unit(s, fc, nal, unit); + if (ret < 0) { + av_log(s->avctx, AV_LOG_WARNING, + "Error parsing NAL unit #%d.\n", i); + goto fail; + } + } + } + return 0; + +fail: + if (fc->ref) + ff_vvc_report_frame_finished(fc->ref); + return ret; +} + +static int set_output_format(const VVCContext *s, const AVFrame *output) +{ + AVCodecContext *c = s->avctx; + int ret; + + if (output->width != c->width || output->height != c->height) { + if ((ret = ff_set_dimensions(c, output->width, output->height)) < 0) + return ret; + } + c->pix_fmt = output->format; + return 0; +} + +static int wait_delayed_frame(VVCContext *s, AVFrame *output, int *got_output) +{ + VVCFrameContext *delayed = get_frame_context(s, s->fcs, s->nb_frames - s->nb_delayed); + int ret = ff_vvc_frame_wait(s, delayed); + + if (!ret && delayed->output_frame->buf[0] && output) { + av_frame_move_ref(output, delayed->output_frame); + ret = set_output_format(s, output); + if (!ret) + *got_output = 1; + } + s->nb_delayed--; + + return ret; +} + +static int submit_frame(VVCContext *s, VVCFrameContext *fc, AVFrame *output, int *got_output) +{ + int ret; + s->nb_frames++; + s->nb_delayed++; + ff_vvc_frame_submit(s, fc); + if (s->nb_delayed >= s->nb_fcs) { + if ((ret = wait_delayed_frame(s, output, got_output)) < 0) + return ret; + } + return 0; +} + +static int get_decoded_frame(VVCContext *s, AVFrame *output, int *got_output) +{ + int ret; + while (s->nb_delayed) { + if ((ret = wait_delayed_frame(s, output, got_output)) < 0) + return ret; + if (*got_output) + return 0; + } + if (s->nb_frames) { + //we still have frames cached in dpb. + VVCFrameContext *last = get_frame_context(s, s->fcs, s->nb_frames - 1); + + ret = ff_vvc_output_frame(s, last, output, 0, 1); + if (ret < 0) + return ret; + if (ret) { + *got_output = ret; + if ((ret = set_output_format(s, output)) < 0) + return ret; + } + } + return 0; +} + +static int vvc_decode_frame(AVCodecContext *avctx, AVFrame *output, + int *got_output, AVPacket *avpkt) +{ + VVCContext *s = avctx->priv_data; + VVCFrameContext *fc; + int ret; + + if (!avpkt->size) + return get_decoded_frame(s, output, got_output); + + fc = get_frame_context(s, s->fcs, s->nb_frames); + + fc->nb_slices = 0; + fc->decode_order = s->nb_frames; + + ret = decode_nal_units(s, fc, avpkt); + if (ret < 0) + return ret; + + ret = submit_frame(s, fc, output, got_output); + if (ret < 0) + return ret; + + return avpkt->size; +} + +static av_cold void vvc_decode_flush(AVCodecContext *avctx) +{ + VVCContext *s = avctx->priv_data; + int got_output = 0; + + while (s->nb_delayed) + wait_delayed_frame(s, NULL, &got_output); +} + +static av_cold int vvc_decode_free(AVCodecContext *avctx) +{ + VVCContext *s = avctx->priv_data; + + ff_cbs_fragment_free(&s->current_frame); + vvc_decode_flush(avctx); + ff_vvc_executor_free(&s->executor); + if (s->fcs) { + for (int i = 0; i < s->nb_fcs; i++) + frame_context_free(s->fcs + i); + av_free(s->fcs); + } + ff_vvc_ps_uninit(&s->ps); + ff_cbs_close(&s->cbc); + + return 0; +} + +static av_cold void init_default_scale_m(void) +{ + memset(&ff_vvc_default_scale_m, 16, sizeof(ff_vvc_default_scale_m)); +} + +#define VVC_MAX_DELAYED_FRAMES 16 +static av_cold int vvc_decode_init(AVCodecContext *avctx) +{ + VVCContext *s = avctx->priv_data; + static AVOnce init_static_once = AV_ONCE_INIT; + const int cpu_count = av_cpu_count(); + const int delayed = FFMIN(cpu_count, VVC_MAX_DELAYED_FRAMES); + const int thread_count = avctx->thread_count ? avctx->thread_count : delayed; + int ret; + + s->avctx = avctx; + + ret = ff_cbs_init(&s->cbc, AV_CODEC_ID_VVC, avctx); + if (ret) + return ret; + + s->nb_fcs = (avctx->flags & AV_CODEC_FLAG_LOW_DELAY) ? 1 : delayed; + s->fcs = av_calloc(s->nb_fcs, sizeof(*s->fcs)); + if (!s->fcs) + return AVERROR(ENOMEM); + + for (int i = 0; i < s->nb_fcs; i++) { + VVCFrameContext *fc = s->fcs + i; + ret = frame_context_init(fc, avctx); + if (ret < 0) + return ret; + } + + s->executor = ff_vvc_executor_alloc(s, thread_count); + if (!s->executor) + return AVERROR(ENOMEM); + + s->eos = 1; + GDR_SET_RECOVERED(s); + ff_thread_once(&init_static_once, init_default_scale_m); + + return 0; +} + +const FFCodec ff_vvc_decoder = { + .p.name = "vvc", + .p.long_name = NULL_IF_CONFIG_SMALL("VVC (Versatile Video Coding)"), + .p.type = AVMEDIA_TYPE_VIDEO, + .p.id = AV_CODEC_ID_VVC, + .priv_data_size = sizeof(VVCContext), + .init = vvc_decode_init, + .close = vvc_decode_free, + FF_CODEC_DECODE_CB(vvc_decode_frame), + .flush = vvc_decode_flush, + .p.capabilities = AV_CODEC_CAP_DR1 | AV_CODEC_CAP_DELAY | AV_CODEC_CAP_OTHER_THREADS, + .caps_internal = FF_CODEC_CAP_EXPORTS_CROPPING | FF_CODEC_CAP_INIT_CLEANUP | + FF_CODEC_CAP_AUTO_THREADS, + .p.profiles = NULL_IF_CONFIG_SMALL(ff_vvc_profiles), +};