February 2024 - ffmpeg-cvslog

avcodec/av1dec: implement FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM
by James Almer 29 Feb '24

29 Feb '24

ffmpeg | branch: master | James Almer <jamrial(a)gmail.com> | Tue Feb 20 19:09:12 2024 -0300| [194414f62d987ad831654c45fff6ee27898b832e] | committer: James Almer avcodec/av1dec: implement FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM Fixes errors when opening streams with no extradata (like those from raw OBU sources). It also calls get_format() on new Sequence Headers when required. Signed-off-by: James Almer <jamrial(a)gmail.com> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=194414f62d987ad83… --- libavcodec/av1dec.c | 58 ++++++++++++++++++++++++++++++++++------------------- libavcodec/av1dec.h | 2 ++ 2 files changed, 39 insertions(+), 21 deletions(-) diff --git a/libavcodec/av1dec.c b/libavcodec/av1dec.c index 820fa79f48..704b9d6298 100644 --- a/libavcodec/av1dec.c +++ b/libavcodec/av1dec.c @@ -620,6 +620,12 @@ static int get_pixel_format(AVCodecContext *avctx) *fmtp++ = pix_fmt; *fmtp = AV_PIX_FMT_NONE; + for (int i = 0; pix_fmts[i] != pix_fmt; i++) + if (pix_fmts[i] == avctx->pix_fmt) { + s->pix_fmt = pix_fmt; + return 1; + } + ret = ff_get_format(avctx, pix_fmts); /** @@ -715,6 +721,7 @@ static av_cold int av1_decode_free(AVCodecContext *avctx) av1_frame_unref(&s->cur_frame); av_frame_free(&s->cur_frame.f); } + av_buffer_unref(&s->seq_data_ref); ff_refstruct_unref(&s->seq_ref); ff_refstruct_unref(&s->header_ref); ff_refstruct_unref(&s->cll_ref); @@ -771,6 +778,9 @@ static int set_context_with_sequence(AVCodecContext *avctx, seq->timing_info.num_units_in_display_tick, seq->timing_info.time_scale); + if (avctx->pix_fmt == AV_PIX_FMT_NONE) + avctx->pix_fmt = get_sw_pixel_format(avctx, seq); + return 0; } @@ -869,8 +879,6 @@ static av_cold int av1_decode_init(AVCodecContext *avctx) goto end; } - avctx->pix_fmt = get_sw_pixel_format(avctx, seq); - end: ff_cbs_fragment_reset(&s->current_obu); } @@ -1174,6 +1182,23 @@ static int get_current_frame(AVCodecContext *avctx) avctx->skip_frame >= AVDISCARD_ALL) return 0; + if (s->pix_fmt == AV_PIX_FMT_NONE) { + ret = get_pixel_format(avctx); + if (ret < 0) { + av_log(avctx, AV_LOG_ERROR, "Failed to get pixel format.\n"); + return ret; + } + + if (!ret && FF_HW_HAS_CB(avctx, decode_params)) { + ret = FF_HW_CALL(avctx, decode_params, AV1_OBU_SEQUENCE_HEADER, + s->seq_data_ref->data, s->seq_data_ref->size); + if (ret < 0) { + av_log(avctx, AV_LOG_ERROR, "HW accel decode params fail.\n"); + return ret; + } + } + } + ret = av1_frame_alloc(avctx, &s->cur_frame); if (ret < 0) { av_log(avctx, AV_LOG_ERROR, @@ -1215,6 +1240,12 @@ static int av1_receive_frame_internal(AVCodecContext *avctx, AVFrame *frame) switch (unit->type) { case AV1_OBU_SEQUENCE_HEADER: + ret = av_buffer_replace(&s->seq_data_ref, unit->data_ref); + if (ret < 0) + goto end; + + s->seq_data_ref->data = unit->data; + s->seq_data_ref->size = unit->data_size; ff_refstruct_replace(&s->seq_ref, unit->content_ref); s->raw_seq = &obu->obu.sequence_header; @@ -1228,25 +1259,8 @@ static int av1_receive_frame_internal(AVCodecContext *avctx, AVFrame *frame) s->operating_point_idc = s->raw_seq->operating_point_idc[s->operating_point]; - if (s->pix_fmt == AV_PIX_FMT_NONE) { - ret = get_pixel_format(avctx); - if (ret < 0) { - av_log(avctx, AV_LOG_ERROR, - "Failed to get pixel format.\n"); - s->raw_seq = NULL; - goto end; - } - } + s->pix_fmt = AV_PIX_FMT_NONE; - if (FF_HW_HAS_CB(avctx, decode_params)) { - ret = FF_HW_CALL(avctx, decode_params, unit->type, - unit->data, unit->data_size); - if (ret < 0) { - av_log(avctx, AV_LOG_ERROR, "HW accel decode params fail.\n"); - s->raw_seq = NULL; - goto end; - } - } break; case AV1_OBU_REDUNDANT_FRAME_HEADER: if (s->raw_frame_header) @@ -1423,6 +1437,8 @@ end: ff_cbs_fragment_reset(&s->current_obu); s->nb_unit = 0; } + if (!ret && !frame->buf[0]) + ret = AVERROR(EAGAIN); return ret; } @@ -1507,7 +1523,7 @@ const FFCodec ff_av1_decoder = { .close = av1_decode_free, FF_CODEC_RECEIVE_FRAME_CB(av1_receive_frame), .p.capabilities = AV_CODEC_CAP_DR1, - .caps_internal = FF_CODEC_CAP_INIT_CLEANUP, + .caps_internal = FF_CODEC_CAP_INIT_CLEANUP | FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM, .flush = av1_decode_flush, .p.profiles = NULL_IF_CONFIG_SMALL(ff_av1_profiles), .p.priv_class = &av1_class, diff --git a/libavcodec/av1dec.h b/libavcodec/av1dec.h index b6a0c08e48..a6ad80c12a 100644 --- a/libavcodec/av1dec.h +++ b/libavcodec/av1dec.h @@ -23,6 +23,7 @@ #include <stdint.h> +#include "libavutil/buffer.h" #include "libavutil/fifo.h" #include "libavutil/frame.h" #include "libavutil/pixfmt.h" @@ -69,6 +70,7 @@ typedef struct AV1DecContext { CodedBitstreamFragment current_obu; AVPacket *pkt; + AVBufferRef *seq_data_ref; AV1RawOBU *seq_ref; ///< RefStruct reference backing raw_seq AV1RawSequenceHeader *raw_seq; AV1RawOBU *header_ref; ///< RefStruct reference backing raw_frame_header

1 0

avformat/iamf: remove duplicated function
by James Almer 29 Feb '24

29 Feb '24

ffmpeg | branch: master | James Almer <jamrial(a)gmail.com> | Thu Feb 29 12:57:25 2024 -0300| [ec7937f4a56e2fbd4070660ff19f0e02c039768a] | committer: James Almer avformat/iamf: remove duplicated function Signed-off-by: James Almer <jamrial(a)gmail.com> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=ec7937f4a56e2fbd4… --- libavformat/iamf.h | 14 ++++++++++++++ libavformat/iamf_reader.c | 18 +----------------- libavformat/iamf_writer.h | 14 -------------- 3 files changed, 15 insertions(+), 31 deletions(-) diff --git a/libavformat/iamf.h b/libavformat/iamf.h index ae1e46a99e..d8715b7333 100644 --- a/libavformat/iamf.h +++ b/libavformat/iamf.h @@ -165,6 +165,20 @@ struct IAMFSoundSystemMap { extern const AVChannelLayout ff_iamf_scalable_ch_layouts[10]; extern const struct IAMFSoundSystemMap ff_iamf_sound_system_map[13]; +static inline IAMFParamDefinition *ff_iamf_get_param_definition(const IAMFContext *iamf, + unsigned int parameter_id) +{ + IAMFParamDefinition *param_definition = NULL; + + for (int i = 0; i < iamf->nb_param_definitions; i++) + if (iamf->param_definitions[i]->param->parameter_id == parameter_id) { + param_definition = iamf->param_definitions[i]; + break; + } + + return param_definition; +} + void ff_iamf_free_audio_element(IAMFAudioElement **paudio_element); void ff_iamf_free_mix_presentation(IAMFMixPresentation **pmix_presentation); void ff_iamf_uninit_context(IAMFContext *c); diff --git a/libavformat/iamf_reader.c b/libavformat/iamf_reader.c index f63bd94b61..42d20f1ae6 100644 --- a/libavformat/iamf_reader.c +++ b/libavformat/iamf_reader.c @@ -98,22 +98,6 @@ static int audio_frame_obu(AVFormatContext *s, const IAMFDemuxContext *c, return 0; } -static const IAMFParamDefinition *get_param_definition(AVFormatContext *s, - const IAMFDemuxContext *c, - unsigned int parameter_id) -{ - const IAMFContext *const iamf = &c->iamf; - const IAMFParamDefinition *param_definition = NULL; - - for (int i = 0; i < iamf->nb_param_definitions; i++) - if (iamf->param_definitions[i]->param->parameter_id == parameter_id) { - param_definition = iamf->param_definitions[i]; - break; - } - - return param_definition; -} - static int parameter_block_obu(AVFormatContext *s, IAMFDemuxContext *c, AVIOContext *pbc, int len) { @@ -144,7 +128,7 @@ static int parameter_block_obu(AVFormatContext *s, IAMFDemuxContext *c, pb = &b.pub; parameter_id = ffio_read_leb(pb); - param_definition = get_param_definition(s, c, parameter_id); + param_definition = ff_iamf_get_param_definition(&c->iamf, parameter_id); if (!param_definition) { av_log(s, AV_LOG_VERBOSE, "Non existant parameter_id %d referenced in a parameter block. Ignoring\n", parameter_id); diff --git a/libavformat/iamf_writer.h b/libavformat/iamf_writer.h index 671d9cc11d..8e2949d8f2 100644 --- a/libavformat/iamf_writer.h +++ b/libavformat/iamf_writer.h @@ -29,20 +29,6 @@ #include "avio.h" #include "iamf.h" -static inline IAMFParamDefinition *ff_iamf_get_param_definition(const IAMFContext *iamf, - unsigned int parameter_id) -{ - IAMFParamDefinition *param_definition = NULL; - - for (int i = 0; i < iamf->nb_param_definitions; i++) - if (iamf->param_definitions[i]->param->parameter_id == parameter_id) { - param_definition = iamf->param_definitions[i]; - break; - } - - return param_definition; -} - int ff_iamf_add_audio_element(IAMFContext *iamf, const AVStreamGroup *stg, void *log_ctx); int ff_iamf_add_mix_presentation(IAMFContext *iamf, const AVStreamGroup *stg, void *log_ctx);

1 0

avcodec/intrax8: Fix assert
by Andreas Rheinhardt 29 Feb '24

29 Feb '24

ffmpeg | branch: master | Andreas Rheinhardt <andreas.rheinhardt(a)outlook.com> | Mon Feb 26 23:19:09 2024 +0100| [4a134eb14abbbf73f5e2b9452f3078c2bf3912ec] | committer: Andreas Rheinhardt avcodec/intrax8: Fix assert Commit 900ce6f8c3526f27173057bb955f54f4f4f41246 replaced IntraX8Context.ac_vlc by IntraX8Context.ac_vlc_table, but forgot to update an av_assert2()*. cf7ed01938a4d8b2ccd28f1fadacd79103e54eed then replaced this with a check for j_ac_vlc[mode], but this makes no sense as j_ac_vlc is of type const VLCElem [2][2][8][]. Worse yet, mode can be up to three and then j_ac_vlc[mode] is undefined behaviour. This happened during the wmv8-x8intra FATE test. *: Since 84f16bb5e68dc47eca4dc96b3391c58471cd7328 config.h was no longer auto-included in avassert.h and this disabled av_assert1() and av_assert2() in files where config.h has not been included before the inclusion of avassert.h. Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt(a)outlook.com> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=4a134eb14abbbf73f… --- libavcodec/intrax8.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/libavcodec/intrax8.c b/libavcodec/intrax8.c index b6aacb170a..948391599f 100644 --- a/libavcodec/intrax8.c +++ b/libavcodec/intrax8.c @@ -103,7 +103,7 @@ static inline void x8_select_ac_table(IntraX8Context *const w, int mode) table_index = get_bits(w->gb, 3); // 2 modes use same tables w->j_ac_vlc_table[mode] = j_ac_vlc[w->quant < 13][mode >> 1][table_index]; - av_assert2(j_ac_vlc[mode]); + av_assert2(w->j_ac_vlc_table[mode]); } static inline int x8_get_orient_vlc(IntraX8Context *w)

1 0

lavc/qsvenc: update the selection of bitrate control method
by Haihao Xiang 29 Feb '24

29 Feb '24

ffmpeg | branch: master | Haihao Xiang <haihao.xiang(a)intel.com> | Thu Feb 1 16:35:35 2024 +0800| [d263fce2b209e86a5a1e8f1b6aa33430ecc2c187] | committer: Haihao Xiang lavc/qsvenc: update the selection of bitrate control method The default method is changed to CQP Signed-off-by: Haihao Xiang <haihao.xiang(a)intel.com> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=d263fce2b209e86a5… --- Changelog | 1 + doc/encoders.texi | 7 ++++-- libavcodec/qsvenc.c | 61 +++++++++++++++++++++++++++++++++-------------- libavcodec/qsvenc_av1.c | 2 +- libavcodec/qsvenc_h264.c | 2 +- libavcodec/qsvenc_hevc.c | 2 +- libavcodec/qsvenc_mpeg2.c | 2 +- libavcodec/qsvenc_vp9.c | 2 +- 8 files changed, 54 insertions(+), 25 deletions(-) diff --git a/Changelog b/Changelog index 610ee61dd6..6e03a49426 100644 --- a/Changelog +++ b/Changelog @@ -27,6 +27,7 @@ version <next>: - a C11-compliant compiler is now required; note that this requirement will be bumped to C17 in the near future, so consider updating your build environment if it lacks C17 support +- Change the default bitrate control method from VBR to CQP for QSV encoders. version 6.1: - libaribcaption decoder diff --git a/doc/encoders.texi b/doc/encoders.texi index 9f477d7c53..5f7864770e 100644 --- a/doc/encoders.texi +++ b/doc/encoders.texi @@ -3338,8 +3338,8 @@ quality range is 1 to 51, with 1 being the best quality. @end itemize @item -Otherwise, a bitrate-based mode is used. For all of those, you should specify at -least the desired average bitrate with the @option{b} option. +Otherwise when the desired average bitrate is specified with the @option{b} +option, a bitrate-based mode is used. @itemize @minus @item @var{LA} - VBR with lookahead, when the @option{look_ahead} option is specified. @@ -3360,6 +3360,9 @@ than the average bitrate. @option{avbr_accuracy} and @option{avbr_convergence} are set to non-zero. This mode is available for H264 and HEVC on Windows. @end itemize + +@item +Otherwise the default ratecontrol method @var{CQP} is used. @end itemize Note that depending on your system, a different mode than the one you specified diff --git a/libavcodec/qsvenc.c b/libavcodec/qsvenc.c index c63b72e384..3a8607fca6 100644 --- a/libavcodec/qsvenc.c +++ b/libavcodec/qsvenc.c @@ -597,6 +597,13 @@ static int select_rc_mode(AVCodecContext *avctx, QSVEncContext *q) else if (want_vcm) { rc_mode = MFX_RATECONTROL_VCM; rc_desc = "video conferencing mode (VCM)"; + + if (!avctx->bit_rate) { + av_log(avctx, AV_LOG_ERROR, "Using the %s ratecontrol method without " + "setting bitrate. Please use the b option to set the desired " + "bitrate.\n", rc_desc); + return AVERROR(EINVAL); + } } #endif else if (want_la) { @@ -606,32 +613,50 @@ static int select_rc_mode(AVCodecContext *avctx, QSVEncContext *q) if (avctx->global_quality > 0) { rc_mode = MFX_RATECONTROL_LA_ICQ; rc_desc = "intelligent constant quality with lookahead (LA_ICQ)"; + } else if (!avctx->bit_rate) { + av_log(avctx, AV_LOG_ERROR, "Using the %s ratecontrol method without " + "setting bitrate. Please use the b option to set the desired " + "bitrate.\n", rc_desc); + return AVERROR(EINVAL); } } else if (avctx->global_quality > 0 && !avctx->rc_max_rate) { rc_mode = MFX_RATECONTROL_ICQ; rc_desc = "intelligent constant quality (ICQ)"; } - else if (avctx->rc_max_rate == avctx->bit_rate) { - rc_mode = MFX_RATECONTROL_CBR; - rc_desc = "constant bitrate (CBR)"; - } + else if (avctx->bit_rate) { + if (avctx->rc_max_rate == avctx->bit_rate) { + rc_mode = MFX_RATECONTROL_CBR; + rc_desc = "constant bitrate (CBR)"; + } #if QSV_HAVE_AVBR - else if (!avctx->rc_max_rate && - (avctx->codec_id == AV_CODEC_ID_H264 || avctx->codec_id == AV_CODEC_ID_HEVC) && - q->avbr_accuracy && - q->avbr_convergence) { - rc_mode = MFX_RATECONTROL_AVBR; - rc_desc = "average variable bitrate (AVBR)"; - } + else if (!avctx->rc_max_rate && + (avctx->codec_id == AV_CODEC_ID_H264 || avctx->codec_id == AV_CODEC_ID_HEVC) && + q->avbr_accuracy && + q->avbr_convergence) { + rc_mode = MFX_RATECONTROL_AVBR; + rc_desc = "average variable bitrate (AVBR)"; + } #endif - else if (avctx->global_quality > 0) { - rc_mode = MFX_RATECONTROL_QVBR; - rc_desc = "constant quality with VBR algorithm (QVBR)"; - } - else { - rc_mode = MFX_RATECONTROL_VBR; - rc_desc = "variable bitrate (VBR)"; + else if (avctx->global_quality > 0) { + rc_mode = MFX_RATECONTROL_QVBR; + rc_desc = "constant quality with VBR algorithm (QVBR)"; + } else { + rc_mode = MFX_RATECONTROL_VBR; + rc_desc = "variable bitrate (VBR)"; + } + } else { + rc_mode = MFX_RATECONTROL_CQP; + rc_desc = "constant quantization parameter (CQP)"; + if (avctx->codec_id == AV_CODEC_ID_AV1) + avctx->global_quality = FF_QP2LAMBDA * 128; + else + avctx->global_quality = FF_QP2LAMBDA * 26; + av_log(avctx, AV_LOG_WARNING, "Using the constant quantization " + "parameter (CQP) by default. Please use the global_quality " + "option and other options for a quality-based mode or the b " + "option and other options for a bitrate-based mode if the " + "default is not the desired choice.\n"); } q->param.mfx.RateControlMethod = rc_mode; diff --git a/libavcodec/qsvenc_av1.c b/libavcodec/qsvenc_av1.c index 4b6e2545ca..33727bb07e 100644 --- a/libavcodec/qsvenc_av1.c +++ b/libavcodec/qsvenc_av1.c @@ -129,7 +129,7 @@ static const AVClass class = { }; static const FFCodecDefault qsv_enc_defaults[] = { - { "b", "1M" }, + { "b", "0" }, { "g", "-1" }, { "bf", "-1" }, { "refs", "0" }, diff --git a/libavcodec/qsvenc_h264.c b/libavcodec/qsvenc_h264.c index 9c4b65ceac..53e4e744b2 100644 --- a/libavcodec/qsvenc_h264.c +++ b/libavcodec/qsvenc_h264.c @@ -178,7 +178,7 @@ static const AVClass class = { }; static const FFCodecDefault qsv_enc_defaults[] = { - { "b", "1M" }, + { "b", "0" }, { "refs", "0" }, { "g", "-1" }, { "bf", "-1" }, diff --git a/libavcodec/qsvenc_hevc.c b/libavcodec/qsvenc_hevc.c index 004b34287b..4920b0bca4 100644 --- a/libavcodec/qsvenc_hevc.c +++ b/libavcodec/qsvenc_hevc.c @@ -374,7 +374,7 @@ static const AVClass class = { }; static const FFCodecDefault qsv_enc_defaults[] = { - { "b", "1M" }, + { "b", "0" }, { "refs", "0" }, { "g", "248" }, { "bf", "-1" }, diff --git a/libavcodec/qsvenc_mpeg2.c b/libavcodec/qsvenc_mpeg2.c index 9151c59fc9..fabf461fe3 100644 --- a/libavcodec/qsvenc_mpeg2.c +++ b/libavcodec/qsvenc_mpeg2.c @@ -82,7 +82,7 @@ static const AVClass class = { }; static const FFCodecDefault qsv_enc_defaults[] = { - { "b", "1M" }, + { "b", "0" }, { "refs", "0" }, // same as the x264 default { "g", "250" }, diff --git a/libavcodec/qsvenc_vp9.c b/libavcodec/qsvenc_vp9.c index 070567c73c..a760e4932e 100644 --- a/libavcodec/qsvenc_vp9.c +++ b/libavcodec/qsvenc_vp9.c @@ -93,7 +93,7 @@ static const AVClass class = { }; static const FFCodecDefault qsv_enc_defaults[] = { - { "b", "1M" }, + { "b", "0" }, { "refs", "0" }, { "g", "250" }, { "trellis", "-1" },

1 0

avcodec/av1dec: Return error for unsupported tile list OBU
by Fei Wang 29 Feb '24

29 Feb '24

ffmpeg | branch: master | Fei Wang <fei.w.wang(a)intel.com> | Thu Dec 28 09:24:03 2023 +0800| [57fbe929f368e65ff0bfaa3c1df5b1aa3b8b88db] | committer: Haihao Xiang avcodec/av1dec: Return error for unsupported tile list OBU Otherwise decoding maybe successful but output result is incorrect. Signed-off-by: Fei Wang <fei.w.wang(a)intel.com> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=57fbe929f368e65ff… --- libavcodec/av1dec.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/libavcodec/av1dec.c b/libavcodec/av1dec.c index d4bfa3c69c..820fa79f48 100644 --- a/libavcodec/av1dec.c +++ b/libavcodec/av1dec.c @@ -1202,6 +1202,12 @@ static int av1_receive_frame_internal(AVCodecContext *avctx, AVFrame *frame) av_log(avctx, AV_LOG_DEBUG, "OBU idx:%d, type:%d, content available:%d.\n", i, unit->type, !!obu); + if (unit->type == AV1_OBU_TILE_LIST) { + av_log(avctx, AV_LOG_ERROR, "Large scale tile decoding is unsupported.\n"); + ret = AVERROR_PATCHWELCOME; + goto end; + } + if (!obu) continue;

1 0

avcodec/av1dec: Move message of OBU info back to the beginning
by Fei Wang 29 Feb '24

29 Feb '24

ffmpeg | branch: master | Fei Wang <fei.w.wang(a)intel.com> | Thu Dec 28 09:24:02 2023 +0800| [3f7e50f53939cfd3153a21f7342c9e65364984dd] | committer: Haihao Xiang avcodec/av1dec: Move message of OBU info back to the beginning So that can show OBU info even it doesn't have decomposed content. And add OBU content status into the message. Signed-off-by: Fei Wang <fei.w.wang(a)intel.com> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=3f7e50f53939cfd31… --- libavcodec/av1dec.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/libavcodec/av1dec.c b/libavcodec/av1dec.c index 7debc4deda..d4bfa3c69c 100644 --- a/libavcodec/av1dec.c +++ b/libavcodec/av1dec.c @@ -1200,11 +1200,12 @@ static int av1_receive_frame_internal(AVCodecContext *avctx, AVFrame *frame) AV1RawOBU *obu = unit->content; const AV1RawOBUHeader *header; + av_log(avctx, AV_LOG_DEBUG, "OBU idx:%d, type:%d, content available:%d.\n", i, unit->type, !!obu); + if (!obu) continue; header = &obu->header; - av_log(avctx, AV_LOG_DEBUG, "Obu idx:%d, obu type:%d.\n", i, unit->type); switch (unit->type) { case AV1_OBU_SEQUENCE_HEADER:

1 0

avdevice: deprecate sdl outdev
by J. Dekker 28 Feb '24

28 Feb '24

ffmpeg | branch: master | J. Dekker <jdek(a)itanimul.li> | Tue Feb 13 08:34:26 2024 +0100| [2b17a74df5fbbc87cdf7a0a784e2e088ab4afd3c] | committer: J. Dekker avdevice: deprecate sdl outdev Signed-off-by: J. Dekker <jdek(a)itanimul.li> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=2b17a74df5fbbc87c… --- doc/outdevs.texi | 8 +++++++- libavdevice/sdl2.c | 10 ++++++++++ libavdevice/version_major.h | 2 ++ 3 files changed, 19 insertions(+), 1 deletion(-) diff --git a/doc/outdevs.texi b/doc/outdevs.texi index 941429a8c8..9ee857528e 100644 --- a/doc/outdevs.texi +++ b/doc/outdevs.texi @@ -408,7 +408,13 @@ ffmpeg -i INPUT -f pulse "stream name" @section sdl -SDL (Simple DirectMedia Layer) output device. +SDL (Simple DirectMedia Layer) output device. Deprecated and will be removed. + +For monitoring purposes in FFmpeg, pipes and a video player such as ffplay can be used: + +@example +ffmpeg -i INPUT -f nut -c:v rawvideo - | ffplay - +@end example "sdl2" can be used as alias for "sdl". diff --git a/libavdevice/sdl2.c b/libavdevice/sdl2.c index 342a253dc0..ec3c3d19b5 100644 --- a/libavdevice/sdl2.c +++ b/libavdevice/sdl2.c @@ -51,6 +51,7 @@ typedef struct { SDL_Rect texture_rect; int inited; + int warned; } SDLContext; static const struct sdl_texture_format_entry { @@ -165,6 +166,15 @@ static int sdl2_write_header(AVFormatContext *s) int i, ret = 0; int flags = 0; + if (!sdl->warned) { + av_log(sdl, AV_LOG_WARNING, + "The sdl output device is deprecated due to being fundamentally incompatible with libavformat API. " + "For monitoring purposes in ffmpeg you can output to a file or use pipes and a video player.\n" + "Example: ffmpeg -i INPUT -f nut -c:v rawvideo - | ffplay -\n" + ); + sdl->warned = 1; + } + if (!sdl->window_title) sdl->window_title = av_strdup(s->url); diff --git a/libavdevice/version_major.h b/libavdevice/version_major.h index da5854ed4c..6e04e0939d 100644 --- a/libavdevice/version_major.h +++ b/libavdevice/version_major.h @@ -37,5 +37,7 @@ #define FF_API_BKTR_DEVICE (LIBAVDEVICE_VERSION_MAJOR < 62) // reminder to remove the opengl device on next major bump #define FF_API_OPENGL_DEVICE (LIBAVDEVICE_VERSION_MAJOR < 62) +// reminder to remove the sdl2 device on next major bump +#define FF_API_SDL2_DEVICE (LIBAVDEVICE_VERSION_MAJOR < 62) #endif /* AVDEVICE_VERSION_MAJOR_H */

1 0

avdevice: deprecate opengl outdev
by J. Dekker 28 Feb '24

28 Feb '24

ffmpeg | branch: master | J. Dekker <jdek(a)itanimul.li> | Tue Feb 13 08:34:25 2024 +0100| [e4c0cdf8df96047ee195cc594a2a93443e2aa25d] | committer: J. Dekker avdevice: deprecate opengl outdev Signed-off-by: J. Dekker <jdek(a)itanimul.li> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=e4c0cdf8df96047ee… --- doc/outdevs.texi | 2 +- libavdevice/opengl_enc.c | 11 +++++++++++ libavdevice/version_major.h | 2 ++ 3 files changed, 14 insertions(+), 1 deletion(-) diff --git a/doc/outdevs.texi b/doc/outdevs.texi index f0484bbf8f..941429a8c8 100644 --- a/doc/outdevs.texi +++ b/doc/outdevs.texi @@ -302,7 +302,7 @@ ffmpeg -re -i INPUT -c:v rawvideo -pix_fmt bgra -f fbdev /dev/fb0 See also @url{http://linux-fbdev.sourceforge.net/}, and fbset(1). @section opengl -OpenGL output device. +OpenGL output device. Deprecated and will be removed. To enable this output device you need to configure FFmpeg with @code{--enable-opengl}. diff --git a/libavdevice/opengl_enc.c b/libavdevice/opengl_enc.c index b2ac6eb16a..69de6fad03 100644 --- a/libavdevice/opengl_enc.c +++ b/libavdevice/opengl_enc.c @@ -224,6 +224,8 @@ typedef struct OpenGLContext { int picture_height; ///< Rendered height int window_width; int window_height; + + int warned; } OpenGLContext; static const struct OpenGLFormatDesc { @@ -1060,6 +1062,15 @@ static av_cold int opengl_write_header(AVFormatContext *h) AVStream *st; int ret; + if (!opengl->warned) { + av_log(opengl, AV_LOG_WARNING, + "The opengl output device is deprecated due to being fundamentally incompatible with libavformat API. " + "For monitoring purposes in ffmpeg you can output to a file or use pipes and a video player.\n" + "Example: ffmpeg -i INPUT -f nut -c:v rawvideo - | ffplay -\n" + ); + opengl->warned = 1; + } + if (h->nb_streams != 1 || par->codec_type != AVMEDIA_TYPE_VIDEO || (par->codec_id != AV_CODEC_ID_WRAPPED_AVFRAME && par->codec_id != AV_CODEC_ID_RAWVIDEO)) { diff --git a/libavdevice/version_major.h b/libavdevice/version_major.h index 9f7b79b2ee..da5854ed4c 100644 --- a/libavdevice/version_major.h +++ b/libavdevice/version_major.h @@ -35,5 +35,7 @@ // reminder to remove the bktr device on next major bump #define FF_API_BKTR_DEVICE (LIBAVDEVICE_VERSION_MAJOR < 62) +// reminder to remove the opengl device on next major bump +#define FF_API_OPENGL_DEVICE (LIBAVDEVICE_VERSION_MAJOR < 62) #endif /* AVDEVICE_VERSION_MAJOR_H */

1 0

avcodec/aarch64/hevc: add luma deblock NEON
by J. Dekker 28 Feb '24

28 Feb '24

ffmpeg | branch: master | J. Dekker <jdek(a)itanimul.li> | Tue Feb 13 01:09:28 2024 +0100| [570052cd2a38200ae6aca52e817517513812ec56] | committer: J. Dekker avcodec/aarch64/hevc: add luma deblock NEON Benched using single-threaded full decode on an Ampere Altra. Bpp Before After Speedup 8 73,3s 65,2s 1.124x 10 114,2s 104,0s 1.098x 12 125,8s 115,7s 1.087x Signed-off-by: J. Dekker <jdek(a)itanimul.li> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=570052cd2a38200ae… --- libavcodec/aarch64/hevcdsp_deblock_neon.S | 417 ++++++++++++++++++++++++++++++ libavcodec/aarch64/hevcdsp_init_aarch64.c | 18 ++ 2 files changed, 435 insertions(+) diff --git a/libavcodec/aarch64/hevcdsp_deblock_neon.S b/libavcodec/aarch64/hevcdsp_deblock_neon.S index 8227f65649..581056a91e 100644 --- a/libavcodec/aarch64/hevcdsp_deblock_neon.S +++ b/libavcodec/aarch64/hevcdsp_deblock_neon.S @@ -181,3 +181,420 @@ hevc_h_loop_filter_chroma 12 hevc_v_loop_filter_chroma 8 hevc_v_loop_filter_chroma 10 hevc_v_loop_filter_chroma 12 + +.macro hevc_loop_filter_luma_body bitdepth +function hevc_loop_filter_luma_body_\bitdepth\()_neon, export=0 +.if \bitdepth > 8 + lsl w2, w2, #(\bitdepth - 8) // beta <<= BIT_DEPTH - 8 +.else + uxtl v0.8h, v0.8b + uxtl v1.8h, v1.8b + uxtl v2.8h, v2.8b + uxtl v3.8h, v3.8b + uxtl v4.8h, v4.8b + uxtl v5.8h, v5.8b + uxtl v6.8h, v6.8b + uxtl v7.8h, v7.8b +.endif + ldr w7, [x3] // tc[0] + ldr w8, [x3, #4] // tc[1] + dup v18.4h, w7 + dup v19.4h, w8 + trn1 v18.2d, v18.2d, v19.2d +.if \bitdepth > 8 + shl v18.8h, v18.8h, #(\bitdepth - 8) +.endif + dup v27.8h, w2 // beta + // tc25 + shl v19.8h, v18.8h, #2 // * 4 + add v19.8h, v19.8h, v18.8h // (tc * 5) + srshr v19.8h, v19.8h, #1 // (tc * 5 + 1) >> 1 + sshr v17.8h, v27.8h, #2 // beta2 + + ////// beta_2 check + // dp0 = abs(P2 - 2 * P1 + P0) + add v22.8h, v3.8h, v1.8h + shl v23.8h, v2.8h, #1 + sabd v30.8h, v22.8h, v23.8h + // dq0 = abs(Q2 - 2 * Q1 + Q0) + add v21.8h, v6.8h, v4.8h + shl v26.8h, v5.8h, #1 + sabd v31.8h, v21.8h, v26.8h + // d0 = dp0 + dq0 + add v20.8h, v30.8h, v31.8h + shl v25.8h, v20.8h, #1 + // (d0 << 1) < beta_2 + cmgt v23.8h, v17.8h, v25.8h + + ////// beta check + // d0 + d3 < beta + mov x9, #0xFFFF00000000FFFF + dup v24.2d, x9 + and v25.16b, v24.16b, v20.16b + addp v25.8h, v25.8h, v25.8h // 1+0 0+1 1+0 0+1 + addp v25.4h, v25.4h, v25.4h // 1+0+0+1 1+0+0+1 + cmgt v25.4h, v27.4h, v25.4h // lower/upper mask in h[0/1] + mov w9, v25.s[0] + cmp w9, #0 + sxtl v26.4s, v25.4h + sxtl v16.2d, v26.2s // full skip mask + b.eq 3f // skip both blocks + + // TODO: we can check the full skip mask with the weak/strong mask to + // potentially skip weak or strong calculation entirely if we only have one + + ////// beta_3 check + // abs(P3 - P0) + abs(Q3 - Q0) < beta_3 + sshr v17.8h, v17.8h, #1 // beta_3 + sabd v20.8h, v0.8h, v3.8h + saba v20.8h, v7.8h, v4.8h + cmgt v21.8h, v17.8h, v20.8h + + and v23.16b, v23.16b, v21.16b + + ////// tc25 check + // abs(P0 - Q0) < tc25 + sabd v20.8h, v3.8h, v4.8h + cmgt v21.8h, v19.8h, v20.8h + + and v23.16b, v23.16b, v21.16b + + ////// Generate low/high line max from lines 0/3/4/7 + // mask out lines 2/3/5/6 + not v20.16b, v24.16b // 0x0000FFFFFFFF0000 + orr v23.16b, v23.16b, v20.16b + + // generate weak/strong mask + uminp v23.8h, v23.8h, v23.8h // extend to singles + sxtl v23.4s, v23.4h + uminp v26.4s, v23.4s, v23.4s // check lines + // extract to gpr + ext v25.16b, v26.16b, v26.16b, #2 + zip1 v17.4s, v26.4s, v26.4s + mov w12, v25.s[0] + mov w11, #0x0000FFFF + mov w13, #0xFFFF0000 + // FFFF FFFF -> strong strong + // FFFF 0000 -> strong weak + // 0000 FFFF -> weak strong + // 0000 0000 -> weak weak + cmp w12, w13 + b.hi 0f // only strong/strong, skip weak nd_p/nd_q calc + + ////// weak nd_p/nd_q + // d0+d3 + and v30.16b, v30.16b, v24.16b // d0 __ __ d3 d4 __ __ d7 + and v31.16b, v31.16b, v24.16b + addp v30.8h, v30.8h, v30.8h // [d0+__ __+d3 d4+__ __+d7] [ ... ] + addp v31.8h, v31.8h, v31.8h // [d0+d3 d4+d7] + addp v30.4h, v30.4h, v30.4h + addp v31.4h, v31.4h, v31.4h + + // ((beta + (beta >> 1)) >> 3) + sshr v21.8h, v27.8h, #1 + add v21.8h, v21.8h, v27.8h + sshr v21.8h, v21.8h, #3 + + // nd_p = dp0 + dp3 < ((beta + (beta >> 1)) >> 3) + cmgt v30.8h, v21.8h, v30.8h + // nd_q = dq0 + dq3 < ((beta + (beta >> 1)) >> 3) + cmgt v31.8h, v21.8h, v31.8h + + sxtl v30.4s, v30.4h + sxtl v31.4s, v31.4h + sxtl v28.2d, v30.2s + sxtl v29.2d, v31.2s + + cmp w12, w11 + b.lo 1f // can only be weak weak, skip strong + +0: // STRONG FILTER + + // P0 = p0 + av_clip(((p2 + 2 * p1 + 2 * p0 + 2 * q0 + q1 + 4) >> 3) - p0, -tc3, tc3); + add v21.8h, v2.8h, v3.8h // (p1 + p0 + add v21.8h, v4.8h, v21.8h // + q0) + shl v21.8h, v21.8h, #1 // * 2 + add v22.8h, v1.8h, v5.8h // (p2 + q1) + add v21.8h, v22.8h, v21.8h // + + srshr v21.8h, v21.8h, #3 // >> 3 + sub v21.8h, v21.8h, v3.8h // - p0 + + // P1 = p1 + av_clip(((p2 + p1 + p0 + q0 + 2) >> 2) - p1, -tc2, tc2); + + add v22.8h, v1.8h, v2.8h + add v23.8h, v3.8h, v4.8h + add v22.8h, v22.8h, v23.8h + srshr v22.8h, v22.8h, #2 + sub v22.8h, v22.8h, v2.8h + + // P2 = p2 + av_clip(((2 * p3 + 3 * p2 + p1 + p0 + q0 + 4) >> 3) - p2, -tc, tc); + + add v23.8h, v0.8h, v1.8h // p3 + p2 + add v24.8h, v3.8h, v4.8h // p0 + q0 + shl v23.8h, v23.8h, #1 // * 2 + add v23.8h, v23.8h, v24.8h + add v24.8h, v1.8h, v2.8h // p2 + p1 + add v23.8h, v23.8h, v24.8h + srshr v23.8h, v23.8h, #3 + sub v23.8h, v23.8h, v1.8h + + // Q0 = q0 + av_clip(((p1 + 2 * p0 + 2 * q0 + 2 * q1 + q2 + 4) >> 3) - q0, -tc3, tc3); + add v24.8h, v3.8h, v4.8h // (p0 + q0 + add v24.8h, v5.8h, v24.8h // + q1) + shl v24.8h, v24.8h, #1 // * 2 + add v25.8h, v2.8h, v6.8h // (p1 + q2) + add v24.8h, v25.8h, v24.8h // + + srshr v24.8h, v24.8h, #3 // >> 3 + sub v24.8h, v24.8h, v4.8h // - q0 + + // Q1 = q1 + av_clip(((p0 + q0 + q1 + q2 + 2) >> 2) - q1, -tc2, tc2); + + add v25.8h, v6.8h, v5.8h + add v26.8h, v3.8h, v4.8h + add v25.8h, v25.8h, v26.8h + srshr v25.8h, v25.8h, #2 + sub v25.8h, v25.8h, v5.8h + + // Q2 = q2 + av_clip(((2 * q3 + 3 * q2 + q1 + q0 + p0 + 4) >> 3) - q2, -tc, tc); + + add v26.8h, v7.8h, v6.8h + add v27.8h, v6.8h, v5.8h + shl v26.8h, v26.8h, #1 + add v26.8h, v26.8h, v27.8h + add v27.8h, v3.8h, v4.8h + add v26.8h, v26.8h, v27.8h + srshr v26.8h, v26.8h, #3 + sub v26.8h, v26.8h, v6.8h + + // this clip should work properly + shl v30.8h, v18.8h, #1 // tc2 + neg v31.8h, v30.8h // -tc2 + clip v31.8h, v30.8h, v21.8h, v22.8h, v23.8h, v24.8h, v25.8h, v26.8h + + and v21.16b, v21.16b, v16.16b + and v22.16b, v22.16b, v16.16b + and v23.16b, v23.16b, v16.16b + and v24.16b, v24.16b, v16.16b + and v25.16b, v25.16b, v16.16b + and v26.16b, v26.16b, v16.16b + + add v23.8h, v23.8h, v1.8h // careful + add v22.8h, v22.8h, v2.8h + add v21.8h, v21.8h, v3.8h + add v24.8h, v24.8h, v4.8h + add v25.8h, v25.8h, v5.8h + add v26.8h, v26.8h, v6.8h + + cmp w12, w13 + b.hi 2f // only strong/strong, skip weak + +1: // WEAK FILTER + + // delta0 = (9 * (q0 - p0) - 3 * (q1 - p1) + 8) >> 4 +.if \bitdepth < 12 + sub v27.8h, v4.8h, v3.8h // q0 - p0 + shl v30.8h, v27.8h, #3 // * 8 + add v27.8h, v27.8h, v30.8h // 9 * (q0 - p0) + + sub v30.8h, v5.8h, v2.8h // q1 - p1 + shl v31.8h, v30.8h, #1 // * 2 + + sub v27.8h, v27.8h, v31.8h + sub v27.8h, v27.8h, v30.8h // - 3 * (q1 - p1) + srshr v27.8h, v27.8h, #4 +.else + sub v19.8h, v4.8h, v3.8h // q0 - p0 + sub v20.8h, v5.8h, v2.8h // q1 - p1 + + sshll v30.4s, v19.4h, #3 // * 8 + sshll2 v31.4s, v19.8h, #3 + + shl v27.8h, v20.8h, #1 + + saddw v30.4s, v30.4s, v19.4h // 9 * (q0 - p0) + saddw2 v31.4s, v31.4s, v19.8h + + saddl v19.4s, v27.4h, v20.4h // 3 * (q1 - p1) + saddl2 v20.4s, v27.8h, v20.8h + + sub v19.4s, v30.4s, v19.4s + sub v20.4s, v31.4s, v20.4s + + sqrshrn v27.4h, v19.4s, #4 + sqrshrn2 v27.8h, v20.4s, #4 +.endif + + // delta0 10tc check mask + shl v30.8h, v18.8h, #1 // * 2 + shl v31.8h, v18.8h, #3 // * 8 + add v30.8h, v30.8h, v31.8h // 10 * tc + abs v31.8h, v27.8h + cmgt v20.8h, v30.8h, v31.8h // abs(delta0) < 10 * tc + + and v20.16b, v20.16b, v16.16b // combine with full mask + + neg v31.8h, v18.8h // -tc + clip v31.8h, v18.8h, v27.8h // delta0 = av_clip(delta0, -tc, tc) + + // deltap1 = av_clip((((p2 + p0 + 1) >> 1) - p1 + delta0) >> 1, -tc_2, tc_2) + add v30.8h, v1.8h, v3.8h + srshr v30.8h, v30.8h, #1 + sub v30.8h, v30.8h, v2.8h + add v30.8h, v30.8h, v27.8h + sshr v30.8h, v30.8h, #1 + + // p3 p2 p1 p0 q0 q1 q2 q3 + // v0 v1 v2 v3 v4 v5 v6 v7 + + // deltaq1 = av_clip((((q2 + q0 + 1) >> 1) - q1 - delta0) >> 1, -tc_2, tc_2); + add v31.8h, v6.8h, v4.8h + srshr v31.8h, v31.8h, #1 + sub v31.8h, v31.8h, v5.8h + sub v31.8h, v31.8h, v27.8h + sshr v31.8h, v31.8h, #1 + + // apply nd_p nd_q mask to deltap1/deltaq1 + and v30.16b, v30.16b, v28.16b + and v31.16b, v31.16b, v29.16b + + // apply full skip mask to deltap1/deltaq1/delta0 + and v30.16b, v30.16b, v20.16b + and v27.16b, v27.16b, v20.16b + and v31.16b, v31.16b, v20.16b + + // clip P1/Q1 to -tc_2, tc_2 + sshr v18.8h, v18.8h, #1 // tc2 + neg v28.8h, v18.8h + clip v28.8h, v18.8h, v30.8h, v31.8h + + // P0 = av_clip_pixel(p0 + delta0) + // Q0 = av_clip_pixel(q0 - delta0) + add v29.8h, v3.8h, v27.8h // P0 + sub v27.8h, v4.8h, v27.8h // Q0 + + // P1 = av_clip_pixel(p1 + deltap1) + // Q1 = av_clip_pixel(q1 + deltaq1) + add v30.8h, v2.8h, v30.8h // P1 + add v31.8h, v5.8h, v31.8h // Q1 + +2: // MIX WEAK/STRONG + + mov v19.16b, v1.16b + mov v20.16b, v6.16b + // copy selection mask + mov v1.16b, v17.16b + mov v2.16b, v17.16b + mov v3.16b, v17.16b + mov v4.16b, v17.16b + mov v5.16b, v17.16b + mov v6.16b, v17.16b + // select + bsl v1.16b, v23.16b, v19.16b // P2 strong/orig + bsl v2.16b, v22.16b, v30.16b // P1 strong/weak + bsl v3.16b, v21.16b, v29.16b // P0 strong/weak + bsl v4.16b, v24.16b, v27.16b // Q0 strong/weak + bsl v5.16b, v25.16b, v31.16b // Q1 strong/weak + bsl v6.16b, v26.16b, v20.16b // Q2 strong/orig + // NOTE: Q3/P3 are unchanged + +.if \bitdepth > 8 + movi v19.8h, #0 + dup v20.8h, w14 + clip v19.8h, v20.8h, v1.8h, v2.8h, v3.8h, v4.8h, v5.8h, v6.8h +.else + sqxtun v0.8b, v0.8h + sqxtun v1.8b, v1.8h + sqxtun v2.8b, v2.8h + sqxtun v3.8b, v3.8h + sqxtun v4.8b, v4.8h + sqxtun v5.8b, v5.8h + sqxtun v6.8b, v6.8h + sqxtun v7.8b, v7.8h +.endif + ret +3: ret x6 +endfunc +.endm + +hevc_loop_filter_luma_body 8 +hevc_loop_filter_luma_body 10 +hevc_loop_filter_luma_body 12 + +// hevc_v_loop_filter_luma(uint8_t *pix, ptrdiff_t stride, int beta, const int32_t *tc, const uint8_t *no_p, const uint8_t *no_q) + +.macro hevc_loop_filter_luma dir, bitdepth +function ff_hevc_\dir\()_loop_filter_luma_\bitdepth\()_neon, export=1 + mov x6, x30 +.ifc \dir, v +.if \bitdepth > 8 + sub x0, x0, #8 +.else + sub x0, x0, #4 +.endif +.else + sub x0, x0, x1, lsl #2 // -4 * xstride +.endif + mov x10, x0 +.if \bitdepth > 8 + ld1 {v0.8h}, [x0], x1 + ld1 {v1.8h}, [x0], x1 + ld1 {v2.8h}, [x0], x1 + ld1 {v3.8h}, [x0], x1 + ld1 {v4.8h}, [x0], x1 + ld1 {v5.8h}, [x0], x1 + ld1 {v6.8h}, [x0], x1 + ld1 {v7.8h}, [x0] + mov w14, #((1 << \bitdepth) - 1) +.ifc \dir, v + transpose_8x8H v0, v1, v2, v3, v4, v5, v6, v7, v16, v17 +.endif +.else + ld1 {v0.8b}, [x0], x1 + ld1 {v1.8b}, [x0], x1 + ld1 {v2.8b}, [x0], x1 + ld1 {v3.8b}, [x0], x1 + ld1 {v4.8b}, [x0], x1 + ld1 {v5.8b}, [x0], x1 + ld1 {v6.8b}, [x0], x1 + ld1 {v7.8b}, [x0] +.ifc \dir, v + transpose_8x8B v0, v1, v2, v3, v4, v5, v6, v7, v16, v17 +.endif +.endif + bl hevc_loop_filter_luma_body_\bitdepth\()_neon +.if \bitdepth > 8 +.ifc \dir, v + transpose_8x8H v0, v1, v2, v3, v4, v5, v6, v7, v16, v17 +.endif + st1 {v0.8h}, [x10], x1 + st1 {v1.8h}, [x10], x1 + st1 {v2.8h}, [x10], x1 + st1 {v3.8h}, [x10], x1 + st1 {v4.8h}, [x10], x1 + st1 {v5.8h}, [x10], x1 + st1 {v6.8h}, [x10], x1 + st1 {v7.8h}, [x10] +.else +.ifc \dir, v + transpose_8x8B v0, v1, v2, v3, v4, v5, v6, v7, v16, v17 +.endif + st1 {v0.8b}, [x10], x1 + st1 {v1.8b}, [x10], x1 + st1 {v2.8b}, [x10], x1 + st1 {v3.8b}, [x10], x1 + st1 {v4.8b}, [x10], x1 + st1 {v5.8b}, [x10], x1 + st1 {v6.8b}, [x10], x1 + st1 {v7.8b}, [x10] +.endif + ret x6 +endfunc +.endm + +hevc_loop_filter_luma h, 8 +hevc_loop_filter_luma h, 10 +hevc_loop_filter_luma h, 12 + +hevc_loop_filter_luma v, 8 +hevc_loop_filter_luma v, 10 +hevc_loop_filter_luma v, 12 diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c index 687b6cc5c3..04692aa98e 100644 --- a/libavcodec/aarch64/hevcdsp_init_aarch64.c +++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c @@ -38,6 +38,18 @@ void ff_hevc_h_loop_filter_chroma_10_neon(uint8_t *_pix, ptrdiff_t _stride, const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q); void ff_hevc_h_loop_filter_chroma_12_neon(uint8_t *_pix, ptrdiff_t _stride, const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q); +void ff_hevc_v_loop_filter_luma_8_neon(uint8_t *_pix, ptrdiff_t _stride, int beta, + const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q); +void ff_hevc_v_loop_filter_luma_10_neon(uint8_t *_pix, ptrdiff_t _stride, int beta, + const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q); +void ff_hevc_v_loop_filter_luma_12_neon(uint8_t *_pix, ptrdiff_t _stride, int beta, + const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q); +void ff_hevc_h_loop_filter_luma_8_neon(uint8_t *_pix, ptrdiff_t _stride, int beta, + const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q); +void ff_hevc_h_loop_filter_luma_10_neon(uint8_t *_pix, ptrdiff_t _stride, int beta, + const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q); +void ff_hevc_h_loop_filter_luma_12_neon(uint8_t *_pix, ptrdiff_t _stride, int beta, + const int *_tc, const uint8_t *_no_p, const uint8_t *_no_q); void ff_hevc_add_residual_4x4_8_neon(uint8_t *_dst, const int16_t *coeffs, ptrdiff_t stride); void ff_hevc_add_residual_4x4_10_neon(uint8_t *_dst, const int16_t *coeffs, @@ -291,6 +303,8 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth) if (!have_neon(cpu_flags)) return; if (bit_depth == 8) { + c->hevc_h_loop_filter_luma = ff_hevc_h_loop_filter_luma_8_neon; + c->hevc_v_loop_filter_luma = ff_hevc_v_loop_filter_luma_8_neon; c->hevc_h_loop_filter_chroma = ff_hevc_h_loop_filter_chroma_8_neon; c->hevc_v_loop_filter_chroma = ff_hevc_v_loop_filter_chroma_8_neon; c->add_residual[0] = ff_hevc_add_residual_4x4_8_neon; @@ -379,6 +393,8 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth) } if (bit_depth == 10) { + c->hevc_h_loop_filter_luma = ff_hevc_h_loop_filter_luma_10_neon; + c->hevc_v_loop_filter_luma = ff_hevc_v_loop_filter_luma_10_neon; c->hevc_h_loop_filter_chroma = ff_hevc_h_loop_filter_chroma_10_neon; c->hevc_v_loop_filter_chroma = ff_hevc_v_loop_filter_chroma_10_neon; c->add_residual[0] = ff_hevc_add_residual_4x4_10_neon; @@ -395,6 +411,8 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth) c->idct_dc[3] = ff_hevc_idct_32x32_dc_10_neon; } if (bit_depth == 12) { + c->hevc_h_loop_filter_luma = ff_hevc_h_loop_filter_luma_12_neon; + c->hevc_v_loop_filter_luma = ff_hevc_v_loop_filter_luma_12_neon; c->hevc_h_loop_filter_chroma = ff_hevc_h_loop_filter_chroma_12_neon; c->hevc_v_loop_filter_chroma = ff_hevc_v_loop_filter_chroma_12_neon; c->add_residual[0] = ff_hevc_add_residual_4x4_12_neon;

1 0

avcodec/libsvtav1: send the EOS signal without a one frame delay to allow for the library to operate in a low-delay mode
by Cosmin Stejerean 27 Feb '24

27 Feb '24

ffmpeg | branch: release/6.1 | Cosmin Stejerean <cosmin(a)cosmin.at> | Fri Feb 23 23:21:39 2024 +0000| [33efa50fa4508567b1d84d0a84728b400e492a6a] | committer: James Almer avcodec/libsvtav1: send the EOS signal without a one frame delay to allow for the library to operate in a low-delay mode Co-authored-by: Amir Naghdinezhad <amir.naghdinezhad(a)intel.com> Signed-off-by: Cosmin Stejerean <cosmin(a)cosmin.at> Signed-off-by: James Almer <jamrial(a)gmail.com> (cherry picked from commit 69dd1ce610fcffec453a0663c613c9b13165fd9e) > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=33efa50fa4508567b… --- libavcodec/libsvtav1.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/libavcodec/libsvtav1.c b/libavcodec/libsvtav1.c index 862192945b..66486591f2 100644 --- a/libavcodec/libsvtav1.c +++ b/libavcodec/libsvtav1.c @@ -539,6 +539,14 @@ static int eb_receive_packet(AVCodecContext *avctx, AVPacket *pkt) if (svt_ret == EB_NoErrorEmptyQueue) return AVERROR(EAGAIN); +#if SVT_AV1_CHECK_VERSION(2, 0, 0) + if (headerPtr->flags & EB_BUFFERFLAG_EOS) { + svt_enc->eos_flag = EOS_RECEIVED; + svt_av1_enc_release_out_buffer(&headerPtr); + return AVERROR_EOF; + } +#endif + ref = get_output_ref(avctx, svt_enc, headerPtr->n_filled_len); if (!ref) { av_log(avctx, AV_LOG_ERROR, "Failed to allocate output packet.\n"); @@ -573,8 +581,10 @@ static int eb_receive_packet(AVCodecContext *avctx, AVPacket *pkt) if (headerPtr->pic_type == EB_AV1_NON_REF_PICTURE) pkt->flags |= AV_PKT_FLAG_DISPOSABLE; +#if !(SVT_AV1_CHECK_VERSION(2, 0, 0)) if (headerPtr->flags & EB_BUFFERFLAG_EOS) svt_enc->eos_flag = EOS_RECEIVED; +#endif ff_side_data_set_encoder_stats(pkt, headerPtr->qp * FF_QP2LAMBDA, NULL, 0, pict_type);

1 0