June 2022 - ffmpeg-devel - lists.ffmpeg.org

[PATCH v2 4/5] libswscale: Enable hscale_avx2 for all input sizes.
by Alan Kelly 15 Aug '22

15 Aug '22

ff_shuffle_filter_coefficients shuffles the tail as required. --- libswscale/utils.c | 19 ++++++++++++++++--- libswscale/x86/swscale.c | 6 ++---- 2 files changed, 18 insertions(+), 7 deletions(-) diff --git a/libswscale/utils.c b/libswscale/utils.c index 7c8e1bbdde..d818c9ce55 100644 --- a/libswscale/utils.c +++ b/libswscale/utils.c @@ -285,8 +285,7 @@ int ff_shuffle_filter_coefficients(SwsContext *c, int *filterPos, #if ARCH_X86_64 int i, j, k; int cpu_flags = av_get_cpu_flags(); - // avx2 hscale filter processes 16 pixel blocks. - if (!filter || dstW % 16 != 0) + if (!filter) return 0; if (EXTERNAL_AVX2_FAST(cpu_flags) && !(cpu_flags & AV_CPU_FLAG_SLOW_GATHER)) { if ((c->srcBpc == 8) && (c->dstBpc <= 14)) { @@ -298,9 +297,11 @@ int ff_shuffle_filter_coefficients(SwsContext *c, int *filterPos, } // Do not swap filterPos for pixels which won't be processed by // the main loop. - for (i = 0; i + 8 <= dstW; i += 8) { + for (i = 0; i + 16 <= dstW; i += 16) { FFSWAP(int, filterPos[i + 2], filterPos[i + 4]); FFSWAP(int, filterPos[i + 3], filterPos[i + 5]); + FFSWAP(int, filterPos[i + 10], filterPos[i + 12]); + FFSWAP(int, filterPos[i + 11], filterPos[i + 13]); } if (filterSize > 4) { // 16 pixels are processed at a time. @@ -314,6 +315,18 @@ int ff_shuffle_filter_coefficients(SwsContext *c, int *filterPos, } } } + // 4 pixels are processed at a time in the tail. + for (; i < dstW; i += 4) { + // 4 filter coeffs are processed at a time. + int rem = dstW - i >= 4 ? 4 : dstW - i; + for (k = 0; k + 4 <= filterSize; k += 4) { + for (j = 0; j < rem; ++j) { + int from = (i + j) * filterSize + k; + int to = i * filterSize + j * 4 + k * 4; + memcpy(&filter[to], &filterCopy[from], 4 * sizeof(int16_t)); + } + } + } } av_free(filterCopy); } diff --git a/libswscale/x86/swscale.c b/libswscale/x86/swscale.c index 73869355b8..76f5a70fc5 100644 --- a/libswscale/x86/swscale.c +++ b/libswscale/x86/swscale.c @@ -691,10 +691,8 @@ switch(c->dstBpc){ \ if (EXTERNAL_AVX2_FAST(cpu_flags) && !(cpu_flags & AV_CPU_FLAG_SLOW_GATHER)) { if ((c->srcBpc == 8) && (c->dstBpc <= 14)) { - if (c->chrDstW % 16 == 0) - ASSIGN_AVX2_SCALE_FUNC(c->hcScale, c->hChrFilterSize); - if (c->dstW % 16 == 0) - ASSIGN_AVX2_SCALE_FUNC(c->hyScale, c->hLumFilterSize); + ASSIGN_AVX2_SCALE_FUNC(c->hcScale, c->hChrFilterSize); + ASSIGN_AVX2_SCALE_FUNC(c->hyScale, c->hLumFilterSize); } } -- 2.35.1.265.g69c8d7142f-goog

2 9

[PATCH 1/2] avformat/mov: Rework the AVIF parser to handle multiple items
by Vignesh Venkatasubramanian 09 Aug '22

09 Aug '22

Stores the item ids of all the items found in the file and processes the primary item at the end of the meta box. This patch does not change any behavior. It sets up the code for parsing alpha channel (and possibly images with 'grid') in follow up patches. Signed-off-by: Vignesh Venkatasubramanian <vigneshv(a)google.com> --- libavformat/isom.h | 4 ++ libavformat/mov.c | 148 ++++++++++++++++++++++++++++----------------- 2 files changed, 97 insertions(+), 55 deletions(-) diff --git a/libavformat/isom.h b/libavformat/isom.h index f05c2d9c28..d8b262e915 100644 --- a/libavformat/isom.h +++ b/libavformat/isom.h @@ -318,6 +318,10 @@ typedef struct MOVContext { uint32_t max_stts_delta; int is_still_picture_avif; int primary_item_id; + int *avif_item_ids; + int avif_item_ids_size; + int *avif_extent_lengths; + int64_t *avif_extent_offsets; } MOVContext; int ff_mp4_read_descr_len(AVIOContext *pb); diff --git a/libavformat/mov.c b/libavformat/mov.c index 88669faa70..9df5055d4e 100644 --- a/libavformat/mov.c +++ b/libavformat/mov.c @@ -4683,6 +4683,69 @@ static int mov_read_custom(MOVContext *c, AVIOContext *pb, MOVAtom atom) return ret; } +static int avif_add_stream(MOVContext *c, int item_id) +{ + MOVStreamContext *sc; + AVStream *st; + int item_index = -1; + for (int i = 0; i < c->avif_item_ids_size; i++) + if (c->avif_item_ids[i] == item_id) { + item_index = i; + break; + } + if (item_index < 0) + return AVERROR_INVALIDDATA; + st = avformat_new_stream(c->fc, NULL); + if (!st) + return AVERROR(ENOMEM); + st->id = c->fc->nb_streams; + sc = av_mallocz(sizeof(MOVStreamContext)); + if (!sc) + return AVERROR(ENOMEM); + + st->priv_data = sc; + st->codecpar->codec_type = AVMEDIA_TYPE_VIDEO; + st->codecpar->codec_id = AV_CODEC_ID_AV1; + sc->ffindex = st->index; + c->trak_index = st->index; + st->avg_frame_rate.num = st->avg_frame_rate.den = 1; + st->time_base.num = st->time_base.den = 1; + st->nb_frames = 1; + sc->time_scale = 1; + sc = st->priv_data; + sc->pb = c->fc->pb; + sc->pb_is_copied = 1; + + // Populate the necessary fields used by mov_build_index. + sc->stsc_count = 1; + sc->stsc_data = av_malloc_array(1, sizeof(*sc->stsc_data)); + if (!sc->stsc_data) + return AVERROR(ENOMEM); + sc->stsc_data[0].first = 1; + sc->stsc_data[0].count = 1; + sc->stsc_data[0].id = 1; + sc->chunk_count = 1; + sc->chunk_offsets = av_malloc_array(1, sizeof(*sc->chunk_offsets)); + if (!sc->chunk_offsets) + return AVERROR(ENOMEM); + sc->sample_count = 1; + sc->sample_sizes = av_malloc_array(1, sizeof(*sc->sample_sizes)); + if (!sc->sample_sizes) + return AVERROR(ENOMEM); + sc->stts_count = 1; + sc->stts_data = av_malloc_array(1, sizeof(*sc->stts_data)); + if (!sc->stts_data) + return AVERROR(ENOMEM); + sc->stts_data[0].count = 1; + // Not used for still images. But needed by mov_build_index. + sc->stts_data[0].duration = 0; + sc->sample_sizes[0] = c->avif_extent_lengths[item_index]; + sc->chunk_offsets[0] = c->avif_extent_offsets[item_index]; + + mov_build_index(c, st); + return 0; +} + static int mov_read_meta(MOVContext *c, AVIOContext *pb, MOVAtom atom) { while (atom.size > 8) { @@ -4692,9 +4755,25 @@ static int mov_read_meta(MOVContext *c, AVIOContext *pb, MOVAtom atom) tag = avio_rl32(pb); atom.size -= 4; if (tag == MKTAG('h','d','l','r')) { + int ret; avio_seek(pb, -8, SEEK_CUR); atom.size += 8; - return mov_read_default(c, pb, atom); + ret = mov_read_default(c, pb, atom); + if (ret < 0) + return ret; + if (c->is_still_picture_avif) { + int ret; + // Add a stream for the YUV planes (primary item). + ret = avif_add_stream(c, c->primary_item_id); + if (ret) + return ret; + // For still AVIF images, the meta box contains all the + // necessary information that would generally be provided by the + // moov box. So simply mark that we have found the moov box so + // that parsing can continue. + c->found_moov = 1; + } + return ret; } } return 0; @@ -7483,8 +7562,6 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom) int item_count, extent_count; uint64_t base_offset, extent_offset, extent_length; uint8_t value; - AVStream *st; - MOVStreamContext *sc; if (!c->is_still_picture_avif) { // * For non-avif, we simply ignore the iloc box. @@ -7498,27 +7575,6 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom) return 0; } - st = avformat_new_stream(c->fc, NULL); - if (!st) - return AVERROR(ENOMEM); - st->id = c->fc->nb_streams; - sc = av_mallocz(sizeof(MOVStreamContext)); - if (!sc) - return AVERROR(ENOMEM); - - st->priv_data = sc; - st->codecpar->codec_type = AVMEDIA_TYPE_VIDEO; - st->codecpar->codec_id = AV_CODEC_ID_AV1; - sc->ffindex = st->index; - c->trak_index = st->index; - st->avg_frame_rate.num = st->avg_frame_rate.den = 1; - st->time_base.num = st->time_base.den = 1; - st->nb_frames = 1; - sc->time_scale = 1; - sc = st->priv_data; - sc->pb = c->fc->pb; - sc->pb_is_copied = 1; - version = avio_r8(pb); avio_rb24(pb); // flags. @@ -7534,32 +7590,20 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom) } item_count = (version < 2) ? avio_rb16(pb) : avio_rb32(pb); - // Populate the necessary fields used by mov_build_index. - sc->stsc_count = 1; - sc->stsc_data = av_malloc_array(1, sizeof(*sc->stsc_data)); - if (!sc->stsc_data) + c->avif_item_ids = av_malloc_array(item_count, sizeof(*c->avif_item_ids)); + if (!c->avif_item_ids) return AVERROR(ENOMEM); - sc->stsc_data[0].first = 1; - sc->stsc_data[0].count = 1; - sc->stsc_data[0].id = 1; - sc->chunk_count = 1; - sc->chunk_offsets = av_malloc_array(1, sizeof(*sc->chunk_offsets)); - if (!sc->chunk_offsets) + c->avif_item_ids_size = item_count; + c->avif_extent_lengths = av_malloc_array(item_count, sizeof(*c->avif_extent_lengths)); + if (!c->avif_extent_lengths) return AVERROR(ENOMEM); - sc->sample_count = 1; - sc->sample_sizes = av_malloc_array(1, sizeof(*sc->sample_sizes)); - if (!sc->sample_sizes) + c->avif_extent_offsets = av_malloc_array(item_count, sizeof(*c->avif_extent_offsets)); + if (!c->avif_extent_offsets) return AVERROR(ENOMEM); - sc->stts_count = 1; - sc->stts_data = av_malloc_array(1, sizeof(*sc->stts_data)); - if (!sc->stts_data) - return AVERROR(ENOMEM); - sc->stts_data[0].count = 1; - // Not used for still images. But needed by mov_build_index. - sc->stts_data[0].duration = 0; for (int i = 0; i < item_count; i++) { int item_id = (version < 2) ? avio_rb16(pb) : avio_rb32(pb); + c->avif_item_ids[i] = item_id; if (version > 0) avio_rb16(pb); // construction_method. avio_rb16(pb); // data_reference_index. @@ -7575,20 +7619,11 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom) if (rb_size(pb, &extent_offset, offset_size) < 0 || rb_size(pb, &extent_length, length_size) < 0) return AVERROR_INVALIDDATA; - if (item_id == c->primary_item_id) { - sc->sample_sizes[0] = extent_length; - sc->chunk_offsets[0] = base_offset + extent_offset; - } + c->avif_extent_lengths[i] = extent_length; + c->avif_extent_offsets[i] = base_offset + extent_offset; } } - mov_build_index(c, st); - - // For still AVIF images, the iloc box contains all the necessary - // information that would generally be provided by the moov box. So simply - // mark that we have found the moov box so that parsing can continue. - c->found_moov = 1; - return atom.size; } @@ -8192,6 +8227,9 @@ static int mov_read_close(AVFormatContext *s) av_freep(&mov->aes_decrypt); av_freep(&mov->chapter_tracks); + av_freep(&mov->avif_item_ids); + av_freep(&mov->avif_extent_lengths); + av_freep(&mov->avif_extent_offsets); return 0; } -- 2.37.0.rc0.161.g10f37bed90-goog

5 22

[PATCH 1/2] lavc/aarch64: new 8-bit hevc 16x16 idct
by J. Dekker 09 Aug '22

09 Aug '22

old: hevc_idct_16x16_8_c: 5366.2 hevc_idct_16x16_8_neon: 1493.2 new: hevc_idct_16x16_8_c: 5363.2 hevc_idct_16x16_8_neon: 943.5 Co-developed-by: Rafal Dabrowa <fatwildcat(a)gmail.com> Signed-off-by: J. Dekker <jdek(a)itanimul.li> --- libavcodec/aarch64/hevcdsp_idct_neon.S | 666 ++++++++++++++++++++++ libavcodec/aarch64/hevcdsp_init_aarch64.c | 3 +- 2 files changed, 668 insertions(+), 1 deletion(-) This idct is significantly faster than the one we currently have, I suspect its for a couple reasons: 1) it's only written for 8bit 2) it's unrolled signficantly more. It comes at a hefty cost of roughly 2.25x the object size. I'm wondering if this idct is salvagable, or the one we have should just be improved instead. diff --git a/libavcodec/aarch64/hevcdsp_idct_neon.S b/libavcodec/aarch64/hevcdsp_idct_neon.S index 0869431294..784bae33b3 100644 --- a/libavcodec/aarch64/hevcdsp_idct_neon.S +++ b/libavcodec/aarch64/hevcdsp_idct_neon.S @@ -618,3 +618,669 @@ idct_dc 16, 10 idct_dc 32, 8 idct_dc 32, 10 + +// WIP + +.Lo0_coeff: .hword 83, 36, 0, 0, 0, 0, 0, 0 +.Lo8transform0: .hword 89, 75, 50, 18 // transform[4,12,20,28][0] +.Lo8transform1: .hword 75, -18, -89, -50 +.Lo8transform2: .hword 50, -89, 18, 75 +.Lo8transform3: .hword 18, -50, 75, -89 + +.LimitMask: + .hword 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0, 0, 0 + .hword 0xffff, 0, 0, 0, 0, 0, 0, 0 + +.Leo_coeff: + .hword 64, 64, 64, 64, 83, 36, -36, -83 + .hword 64, -64, -64, 64, 36, -83, 83, -36 + .hword 89, 75, 50, 18, 75, -18, -89, -50 // transform[4,12][0-3] + .hword 50, -89, 18, 75, 18, -50, 75, -89 // transform[20,28][0-3] +.Lo16transform0: .hword 90, 87, 80, 70, 57, 43, 25, 9 // transform[2][0-7], also transform[2,6,10..][0] +.Lo16transform1: .hword 87, 57, 9, -43, -80, -90, -70, -25 // transform[6][0-7] +.Lo16transform2: .hword 80, 9, -70, -87, -25, 57, 90, 43 // transform[10][0-7] +.Lo16transform3: .hword 70, -43, -87, 9, 90, 25, -80, -57 // transform[14][0-7] +.Lo16transform4: .hword 57, -80, -25, 90, -9, -87, 43, 70 // transform[18][0-7] +.Lo16transform5: .hword 43, -90, 57, 25, -87, 70, 9, -80 // transform[22][0-7] +.Lo16transform6: .hword 25, -70, 90, -80, 43, 9, -57, 87 // transform[26][0-7] +.Lo16transform7: .hword 9, -25, 43, -57, 70, -80, 87, -90 // transform[30][0-7] + +// void ff_hevc_idct_16x16_8_neon(int16_t *coeffs, int col_limit) +function ff_hevc_idct_16x16_8_neon_new, export=1 + sub sp, sp, 64 + st1 {v8.16b, v9.16b, v10.16b, v11.16b}, [sp] + sub sp, sp, 32 + st1 {v14.16b, v15.16b}, [sp] + mov x3, 0 + mov x2, x0 +1: mov x4, x2 + mov x5, 32 + ld1 {v16.8h}, [x4], x5 + ld1 {v17.8h}, [x4], x5 + ld1 {v18.8h}, [x4], x5 + ld1 {v19.8h}, [x4], x5 + ld1 {v20.8h}, [x4], x5 + ld1 {v21.8h}, [x4], x5 + ld1 {v22.8h}, [x4], x5 + ld1 {v23.8h}, [x4], x5 + ld1 {v24.8h}, [x4], x5 + ld1 {v25.8h}, [x4], x5 + ld1 {v26.8h}, [x4], x5 + ld1 {v27.8h}, [x4], x5 + ld1 {v28.8h}, [x4], x5 + ld1 {v29.8h}, [x4], x5 + ld1 {v30.8h}, [x4], x5 + ld1 {v31.8h}, [x4], x5 + cmp x1, 12 + b.hs 5f + // limit2 below 16 + bic x4, x1, 1 + adr x5, .LimitMask + cbnz x3, 3f + // columns 0 .. 7 - cleanup of indexes 5 .. 7 + ld1 {v0.8h}, [x5] + adr x5, 2f + add x5, x5, x4, lsl 2 + add x5, x5, x4, lsl 1 + br x5 +2: and v17.16b, v17.16b, v0.16b // col_limit 0..1 -> limit2 == 4..5 + and v19.16b, v19.16b, v0.16b + b 5f + and v19.16b, v19.16b, v0.16b // col_limit 2..3 -> limit2 == 6..7 + and v21.16b, v21.16b, v0.16b + b 5f + and v21.16b, v21.16b, v0.16b // col_limit 4..5 -> limit2 == 8..9 + and v23.16b, v23.16b, v0.16b + b 5f + and v23.16b, v23.16b, v0.16b // col_limit 6..7 -> limit2 == 10..11 + and v25.16b, v25.16b, v0.16b + b 5f + and v25.16b, v25.16b, v0.16b // col_limit 8..9 -> limit2 == 12..13 + and v27.16b, v27.16b, v0.16b + b 5f + and v27.16b, v27.16b, v0.16b // col_limit 10..11 -> limit2 == 14..15 + and v29.16b, v29.16b, v0.16b + b 5f + // columns 8 .. 15 +3: subs x4, x4, 2 + b.lo 5f + ld1 {v0.8h, v1.8h}, [x5] + adr x5, 4f + add x5, x5, x4, lsl 3 + add x5, x5, x4, lsl 1 + br x5 +4: and v17.16b, v17.16b, v1.16b // col_limit 2..3 -> limit2 == 2..3 + b 5f + nop + nop + nop + and v17.16b, v17.16b, v1.16b // col_limit 4..5 -> limit2 == 4..5 + and v19.16b, v19.16b, v1.16b + b 5f + nop + nop + and v17.16b, v17.16b, v0.16b // col_limit 6..7 -> limit2 == 6..7 + and v19.16b, v19.16b, v1.16b + and v21.16b, v21.16b, v1.16b + b 5f + nop + and v17.16b, v17.16b, v0.16b // col_limit 8..9 -> limit2 == 8..9 + and v19.16b, v19.16b, v0.16b + and v21.16b, v21.16b, v1.16b + and v23.16b, v23.16b, v1.16b + b 5f + and v19.16b, v19.16b, v0.16b // col_limit 10..11 -> limit2 == 10..11 + and v21.16b, v21.16b, v0.16b + and v23.16b, v23.16b, v1.16b + and v25.16b, v25.16b, v1.16b + b 5f +5: adr x4, .Lo0_coeff + ld1 {v14.8h}, [x4] + + // v0,v1 = e0 + sshll v0.4s, v16.4h, 6 + sshll v1.4s, v24.4h, 6 + add v0.4s, v0.4s, v1.4s + sshll2 v1.4s, v16.8h, 6 + sshll2 v2.4s, v24.8h, 6 + add v1.4s, v1.4s, v2.4s + + // v2,v3 = o0 + smull v2.4s, v20.4h, v14.h[0] + smlal v2.4s, v28.4h, v14.h[1] + smull2 v3.4s, v20.8h, v14.h[0] + smlal2 v3.4s, v28.8h, v14.h[1] + + // v4,v5 = e_8[0] + add v4.4s, v0.4s, v2.4s + add v5.4s, v1.4s, v3.4s + + // v6,v7 = e_8[3] + sub v6.4s, v0.4s, v2.4s + sub v7.4s, v1.4s, v3.4s + + + // v0,v1 = o_8[0] + adr x4, .Lo8transform0 + ld1 {v15.4h}, [x4] + smull v0.4s, v18.4h, v15.h[0] + smlal v0.4s, v22.4h, v15.h[1] + smlal v0.4s, v26.4h, v15.h[2] + smlal v0.4s, v30.4h, v15.h[3] + smull2 v1.4s, v18.8h, v15.h[0] + smlal2 v1.4s, v22.8h, v15.h[1] + smlal2 v1.4s, v26.8h, v15.h[2] + smlal2 v1.4s, v30.8h, v15.h[3] + + // v2,v3 = e_16[0] + add v2.4s, v4.4s, v0.4s + add v3.4s, v5.4s, v1.4s + + // v8,v9 = o_16[0] + adr x4, .Lo16transform0 + ld1 {v15.8h}, [x4] + + mov x5, 16 + cmp x1, 12 + b.hs 6f + add x5, x1, 4 + bic x5, x5, 1 + cbz x3, 6f + orr x5, x1, 1 + subs x5, x5, 2 + csel x5, x5, xzr, hs +6: mov x4, 64 + sub x6, x4, x5, lsl 2 + adr x5, 7f + add x5, x5, x6 + movi v8.4s, 0 + movi v9.4s, 0 + br x5 +7: smlal2 v9.4s, v31.8h, v15.h[7] + smlal v8.4s, v31.4h, v15.h[7] + smlal2 v9.4s, v29.8h, v15.h[6] + smlal v8.4s, v29.4h, v15.h[6] + smlal2 v9.4s, v27.8h, v15.h[5] + smlal v8.4s, v27.4h, v15.h[5] + smlal2 v9.4s, v25.8h, v15.h[4] + smlal v8.4s, v25.4h, v15.h[4] + smlal2 v9.4s, v23.8h, v15.h[3] + smlal v8.4s, v23.4h, v15.h[3] + smlal2 v9.4s, v21.8h, v15.h[2] + smlal v8.4s, v21.4h, v15.h[2] + smlal2 v9.4s, v19.8h, v15.h[1] + smlal v8.4s, v19.4h, v15.h[1] + smlal2 v9.4s, v17.8h, v15.h[0] + smlal v8.4s, v17.4h, v15.h[0] + + // tmp[0 * 16] + add v10.4s, v2.4s, v8.4s + add v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + st1 {v10.8h}, [x2] + + // tmp[15 * 16] + sub v10.4s, v2.4s, v8.4s + sub v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 15 * 32 + st1 {v10.8h}, [x4] + + // v2,v3 = e_16[7] + sub v2.4s, v4.4s, v0.4s + sub v3.4s, v5.4s, v1.4s + + // v8,v9 = o_16[7] + adr x4, .Lo16transform7 + ld1 {v15.8h}, [x4] + adr x5, 8f + add x5, x5, x6 + movi v8.4s, 0 + movi v9.4s, 0 + br x5 +8: smlal2 v9.4s, v31.8h, v15.h[7] + smlal v8.4s, v31.4h, v15.h[7] + smlal2 v9.4s, v29.8h, v15.h[6] + smlal v8.4s, v29.4h, v15.h[6] + smlal2 v9.4s, v27.8h, v15.h[5] + smlal v8.4s, v27.4h, v15.h[5] + smlal2 v9.4s, v25.8h, v15.h[4] + smlal v8.4s, v25.4h, v15.h[4] + smlal2 v9.4s, v23.8h, v15.h[3] + smlal v8.4s, v23.4h, v15.h[3] + smlal2 v9.4s, v21.8h, v15.h[2] + smlal v8.4s, v21.4h, v15.h[2] + smlal2 v9.4s, v19.8h, v15.h[1] + smlal v8.4s, v19.4h, v15.h[1] + smlal2 v9.4s, v17.8h, v15.h[0] + smlal v8.4s, v17.4h, v15.h[0] + + // tmp[7 * 16] + add v10.4s, v2.4s, v8.4s + add v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 7 * 32 + st1 {v10.8h}, [x4] + + // tmp[8 * 16] + sub v10.4s, v2.4s, v8.4s + sub v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 8 * 32 + st1 {v10.8h}, [x4] + + // v0,v1 = o_8[3] + adr x4, .Lo8transform3 + ld1 {v15.4h}, [x4] + smull v0.4s, v18.4h, v15.h[0] + smlal v0.4s, v22.4h, v15.h[1] + smlal v0.4s, v26.4h, v15.h[2] + smlal v0.4s, v30.4h, v15.h[3] + smull2 v1.4s, v18.8h, v15.h[0] + smlal2 v1.4s, v22.8h, v15.h[1] + smlal2 v1.4s, v26.8h, v15.h[2] + smlal2 v1.4s, v30.8h, v15.h[3] + + // v2,v3 = e_16[3] + add v2.4s, v6.4s, v0.4s + add v3.4s, v7.4s, v1.4s + + // v8,v9 = o_16[3] + adr x4, .Lo16transform3 + ld1 {v15.8h}, [x4] + adr x5, 9f + add x5, x5, x6 + movi v8.4s, 0 + movi v9.4s, 0 + br x5 +9: smlal2 v9.4s, v31.8h, v15.h[7] + smlal v8.4s, v31.4h, v15.h[7] + smlal2 v9.4s, v29.8h, v15.h[6] + smlal v8.4s, v29.4h, v15.h[6] // 13 + smlal2 v9.4s, v27.8h, v15.h[5] + smlal v8.4s, v27.4h, v15.h[5] // 11 + smlal2 v9.4s, v25.8h, v15.h[4] + smlal v8.4s, v25.4h, v15.h[4] // 9 + smlal2 v9.4s, v23.8h, v15.h[3] + smlal v8.4s, v23.4h, v15.h[3] // 7 + smlal2 v9.4s, v21.8h, v15.h[2] + smlal v8.4s, v21.4h, v15.h[2] // 5 + smlal2 v9.4s, v19.8h, v15.h[1] + smlal v8.4s, v19.4h, v15.h[1] // 3 + smlal2 v9.4s, v17.8h, v15.h[0] + smlal v8.4s, v17.4h, v15.h[0] // 1 + + // tmp[3 * 16] + add v10.4s, v2.4s, v8.4s + add v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 3 * 32 + st1 {v10.8h}, [x4] + + // tmp[12 * 16] + sub v10.4s, v2.4s, v8.4s + sub v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 12 * 32 + st1 {v10.8h}, [x4] + + // v2,v3 = e_16[4] + sub v2.4s, v6.4s, v0.4s + sub v3.4s, v7.4s, v1.4s + + // v8,v9 = o_16[4] + adr x4, .Lo16transform4 + ld1 {v15.8h}, [x4] + adr x5, 10f + add x5, x5, x6 + movi v8.4s, 0 + movi v9.4s, 0 + br x5 +10: smlal2 v9.4s, v31.8h, v15.h[7] + smlal v8.4s, v31.4h, v15.h[7] + smlal2 v9.4s, v29.8h, v15.h[6] + smlal v8.4s, v29.4h, v15.h[6] + smlal2 v9.4s, v27.8h, v15.h[5] + smlal v8.4s, v27.4h, v15.h[5] + smlal2 v9.4s, v25.8h, v15.h[4] + smlal v8.4s, v25.4h, v15.h[4] + smlal2 v9.4s, v23.8h, v15.h[3] + smlal v8.4s, v23.4h, v15.h[3] + smlal2 v9.4s, v21.8h, v15.h[2] + smlal v8.4s, v21.4h, v15.h[2] + smlal2 v9.4s, v19.8h, v15.h[1] + smlal v8.4s, v19.4h, v15.h[1] + smlal2 v9.4s, v17.8h, v15.h[0] + smlal v8.4s, v17.4h, v15.h[0] + + // tmp[4 * 16] + add v10.4s, v2.4s, v8.4s + add v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 4 * 32 + st1 {v10.8h}, [x4] + + // tmp[11 * 16] + sub v10.4s, v2.4s, v8.4s + sub v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 11 * 32 + st1 {v10.8h}, [x4] + + + // v0,v1 = e1 + sshll v0.4s, v16.4h, 6 + sshll v1.4s, v24.4h, 6 + sub v0.4s, v0.4s, v1.4s + sshll2 v1.4s, v16.8h, 6 + sshll2 v2.4s, v24.8h, 6 + sub v1.4s, v1.4s, v2.4s + + // v2,v3 = o1 + smull v2.4s, v20.4h, v14.h[1] + smlsl v2.4s, v28.4h, v14.h[0] + smull2 v3.4s, v20.8h, v14.h[1] + smlsl2 v3.4s, v28.8h, v14.h[0] + + // v4,v5 = e_8[1] + add v4.4s, v0.4s, v2.4s + add v5.4s, v1.4s, v3.4s + + // v6,v7 = e_8[2] + sub v6.4s, v0.4s, v2.4s + sub v7.4s, v1.4s, v3.4s + + // v0,v1 = o_8[1] + adr x4, .Lo8transform1 + ld1 {v15.4h}, [x4] + smull v0.4s, v18.4h, v15.h[0] + smlal v0.4s, v22.4h, v15.h[1] + smlal v0.4s, v26.4h, v15.h[2] + smlal v0.4s, v30.4h, v15.h[3] + smull2 v1.4s, v18.8h, v15.h[0] + smlal2 v1.4s, v22.8h, v15.h[1] + smlal2 v1.4s, v26.8h, v15.h[2] + smlal2 v1.4s, v30.8h, v15.h[3] + + // v2,v3 = e_16[1] + add v2.4s, v4.4s, v0.4s + add v3.4s, v5.4s, v1.4s + + // v8,v9 = o_16[1] + adr x4, .Lo16transform1 + ld1 {v15.8h}, [x4] + adr x5, 11f + add x5, x5, x6 + movi v8.4s, 0 + movi v9.4s, 0 + br x5 +11: smlal2 v9.4s, v31.8h, v15.h[7] + smlal v8.4s, v31.4h, v15.h[7] + smlal2 v9.4s, v29.8h, v15.h[6] + smlal v8.4s, v29.4h, v15.h[6] + smlal2 v9.4s, v27.8h, v15.h[5] + smlal v8.4s, v27.4h, v15.h[5] + smlal2 v9.4s, v25.8h, v15.h[4] + smlal v8.4s, v25.4h, v15.h[4] + smlal2 v9.4s, v23.8h, v15.h[3] + smlal v8.4s, v23.4h, v15.h[3] + smlal2 v9.4s, v21.8h, v15.h[2] + smlal v8.4s, v21.4h, v15.h[2] + smlal2 v9.4s, v19.8h, v15.h[1] + smlal v8.4s, v19.4h, v15.h[1] + smlal2 v9.4s, v17.8h, v15.h[0] + smlal v8.4s, v17.4h, v15.h[0] + + // tmp[1 * 16] + add v10.4s, v2.4s, v8.4s + add v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 1 * 32 + st1 {v10.8h}, [x4] + + // tmp[14 * 16] + sub v10.4s, v2.4s, v8.4s + sub v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 14 * 32 + st1 {v10.8h}, [x4] + + // v2,v3 = e_16[6] + sub v2.4s, v4.4s, v0.4s + sub v3.4s, v5.4s, v1.4s + + // v8,v9 = o_16[6] + adr x4, .Lo16transform6 + ld1 {v15.8h}, [x4] + adr x5, 12f + add x5, x5, x6 + movi v8.4s, 0 + movi v9.4s, 0 + br x5 +12: smlal2 v9.4s, v31.8h, v15.h[7] + smlal v8.4s, v31.4h, v15.h[7] + smlal2 v9.4s, v29.8h, v15.h[6] + smlal v8.4s, v29.4h, v15.h[6] + smlal2 v9.4s, v27.8h, v15.h[5] + smlal v8.4s, v27.4h, v15.h[5] + smlal2 v9.4s, v25.8h, v15.h[4] + smlal v8.4s, v25.4h, v15.h[4] + smlal2 v9.4s, v23.8h, v15.h[3] + smlal v8.4s, v23.4h, v15.h[3] + smlal2 v9.4s, v21.8h, v15.h[2] + smlal v8.4s, v21.4h, v15.h[2] + smlal2 v9.4s, v19.8h, v15.h[1] + smlal v8.4s, v19.4h, v15.h[1] + smlal2 v9.4s, v17.8h, v15.h[0] + smlal v8.4s, v17.4h, v15.h[0] + + // tmp[6 * 16] + add v10.4s, v2.4s, v8.4s + add v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 6 * 32 + st1 {v10.8h}, [x4] + + // tmp[9 * 16] + sub v10.4s, v2.4s, v8.4s + sub v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 9 * 32 + st1 {v10.8h}, [x4] + + // v0,v1 = o_8[2] + adr x4, .Lo8transform2 + ld1 {v15.4h}, [x4] + smull v0.4s, v18.4h, v15.h[0] + smlal v0.4s, v22.4h, v15.h[1] + smlal v0.4s, v26.4h, v15.h[2] + smlal v0.4s, v30.4h, v15.h[3] + smull2 v1.4s, v18.8h, v15.h[0] + smlal2 v1.4s, v22.8h, v15.h[1] + smlal2 v1.4s, v26.8h, v15.h[2] + smlal2 v1.4s, v30.8h, v15.h[3] + + // v2,v3 = e_16[2] + add v2.4s, v6.4s, v0.4s + add v3.4s, v7.4s, v1.4s + + // v8,v9 = o_16[2] + adr x4, .Lo16transform2 + ld1 {v15.8h}, [x4] + adr x5, 13f + add x5, x5, x6 + movi v8.4s, 0 + movi v9.4s, 0 + br x5 +13: smlal2 v9.4s, v31.8h, v15.h[7] + smlal v8.4s, v31.4h, v15.h[7] + smlal2 v9.4s, v29.8h, v15.h[6] + smlal v8.4s, v29.4h, v15.h[6] + smlal2 v9.4s, v27.8h, v15.h[5] + smlal v8.4s, v27.4h, v15.h[5] + smlal2 v9.4s, v25.8h, v15.h[4] + smlal v8.4s, v25.4h, v15.h[4] + smlal2 v9.4s, v23.8h, v15.h[3] + smlal v8.4s, v23.4h, v15.h[3] + smlal2 v9.4s, v21.8h, v15.h[2] + smlal v8.4s, v21.4h, v15.h[2] + smlal2 v9.4s, v19.8h, v15.h[1] + smlal v8.4s, v19.4h, v15.h[1] + smlal2 v9.4s, v17.8h, v15.h[0] + smlal v8.4s, v17.4h, v15.h[0] + + // tmp[2 * 16] + add v10.4s, v2.4s, v8.4s + add v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 2 * 32 + st1 {v10.8h}, [x4] + + // tmp[13 * 16] + sub v10.4s, v2.4s, v8.4s + sub v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 13 * 32 + st1 {v10.8h}, [x4] + + // v2,v3 = e_16[5] + sub v2.4s, v6.4s, v0.4s + sub v3.4s, v7.4s, v1.4s + + // v8,v9 = o_16[5] + adr x4, .Lo16transform5 + ld1 {v15.8h}, [x4] + adr x5, 14f + add x5, x5, x6 + movi v8.4s, 0 + movi v9.4s, 0 + br x5 +14: smlal2 v9.4s, v31.8h, v15.h[7] + smlal v8.4s, v31.4h, v15.h[7] + smlal2 v9.4s, v29.8h, v15.h[6] + smlal v8.4s, v29.4h, v15.h[6] + smlal2 v9.4s, v27.8h, v15.h[5] + smlal v8.4s, v27.4h, v15.h[5] + smlal2 v9.4s, v25.8h, v15.h[4] + smlal v8.4s, v25.4h, v15.h[4] + smlal2 v9.4s, v23.8h, v15.h[3] + smlal v8.4s, v23.4h, v15.h[3] + smlal2 v9.4s, v21.8h, v15.h[2] + smlal v8.4s, v21.4h, v15.h[2] + smlal2 v9.4s, v19.8h, v15.h[1] + smlal v8.4s, v19.4h, v15.h[1] + smlal2 v9.4s, v17.8h, v15.h[0] + smlal v8.4s, v17.4h, v15.h[0] + + // tmp[5 * 16] + add v10.4s, v2.4s, v8.4s + add v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 5 * 32 + st1 {v10.8h}, [x4] + + // tmp[10 * 16] + sub v10.4s, v2.4s, v8.4s + sub v11.4s, v3.4s, v9.4s + sqrshrn v10.4h, v10.4s, 7 + sqrshrn2 v10.8h, v11.4s, 7 + add x4, x2, 10 * 32 + st1 {v10.8h}, [x4] + + add x2, x2, 16 + add x3, x3, 1 + cmp x3, 2 + b.lo 1b + + + // horizontal transform + adr x4, .Leo_coeff + ld1 {v16.8h, v17.8h, v18.8h, v19.8h}, [x4], 64 + ld1 {v20.8h, v21.8h, v22.8h, v23.8h}, [x4], 64 + ld1 {v24.8h, v25.8h, v26.8h, v27.8h}, [x4], 64 + // o_16 jump address + mov x4, 64 + bic x5, x1, 1 + subs x4, x4, x5, lsl 2 + csel x4, x4, xzr, hs + adr x5, 15f + add x5, x5, x4 + + mov x3, 16 +14: ld1 {v6.8h, v7.8h}, [x0] + + // v2 = e_8 + smull v2.4s, v16.4h, v6.h[0] + smlal2 v2.4s, v16.8h, v6.h[4] + smlal v2.4s, v17.4h, v7.h[0] + smlal2 v2.4s, v17.8h, v7.h[4] + + // v3 = o_8 + smull v3.4s, v18.4h, v6.h[2] + smlal2 v3.4s, v18.8h, v6.h[6] + smlal v3.4s, v19.4h, v7.h[2] + smlal2 v3.4s, v19.8h, v7.h[6] + + // v0,v1 = e_16 + add v0.4s, v2.4s, v3.4s + sub v2.4s, v2.4s, v3.4s + mov v1.d[0], v2.d[1] + mov v1.d[1], v2.d[0] + rev64 v1.4s, v1.4s + + // v2,v3 = o_16 + movi v2.4s, 0 + movi v3.4s, 0 + br x5 +15: smlal v2.4s, v27.4h, v7.h[7] + smlal2 v3.4s, v27.8h, v7.h[7] + smlal v2.4s, v26.4h, v7.h[5] + smlal2 v3.4s, v26.8h, v7.h[5] + smlal v2.4s, v25.4h, v7.h[3] + smlal2 v3.4s, v25.8h, v7.h[3] + smlal v2.4s, v24.4h, v7.h[1] + smlal2 v3.4s, v24.8h, v7.h[1] + smlal v2.4s, v23.4h, v6.h[7] + smlal2 v3.4s, v23.8h, v6.h[7] + smlal v2.4s, v22.4h, v6.h[5] + smlal2 v3.4s, v22.8h, v6.h[5] + smlal v2.4s, v21.4h, v6.h[3] + smlal2 v3.4s, v21.8h, v6.h[3] + smlal v2.4s, v20.4h, v6.h[1] + smlal2 v3.4s, v20.8h, v6.h[1] + + // coeff + add v4.4s, v0.4s, v2.4s + add v5.4s, v1.4s, v3.4s + sub v6.4s, v0.4s, v2.4s + sub v7.4s, v1.4s, v3.4s + sqrshrn v4.4h, v4.4s, 12 + sqrshrn2 v4.8h, v5.4s, 12 + sqrshrn v6.4h, v6.4s, 12 + sqrshrn2 v6.8h, v7.4s, 12 + mov v5.d[0], v6.d[1] + mov v5.d[1], v6.d[0] + rev64 v5.8h, v5.8h + st1 {v4.8h, v5.8h}, [x0], 32 + subs x3, x3, 1 + b.ne 14b + + ld1 {v14.16b, v15.16b}, [sp], 32 + ld1 {v8.16b, v9.16b, v10.16b, v11.16b}, [sp], 64 + ret +endfunc diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c index 2002530266..612ebb9541 100644 --- a/libavcodec/aarch64/hevcdsp_init_aarch64.c +++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c @@ -45,6 +45,7 @@ void ff_hevc_idct_8x8_8_neon(int16_t *coeffs, int col_limit); void ff_hevc_idct_8x8_10_neon(int16_t *coeffs, int col_limit); void ff_hevc_idct_16x16_8_neon(int16_t *coeffs, int col_limit); void ff_hevc_idct_16x16_10_neon(int16_t *coeffs, int col_limit); +void ff_hevc_idct_16x16_8_neon_new(int16_t *coeffs, int col_limit); void ff_hevc_idct_4x4_dc_8_neon(int16_t *coeffs); void ff_hevc_idct_8x8_dc_8_neon(int16_t *coeffs); void ff_hevc_idct_16x16_dc_8_neon(int16_t *coeffs); @@ -72,7 +73,7 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth) c->add_residual[2] = ff_hevc_add_residual_16x16_8_neon; c->add_residual[3] = ff_hevc_add_residual_32x32_8_neon; c->idct[1] = ff_hevc_idct_8x8_8_neon; - c->idct[2] = ff_hevc_idct_16x16_8_neon; + c->idct[2] = ff_hevc_idct_16x16_8_neon_new; c->idct_dc[0] = ff_hevc_idct_4x4_dc_8_neon; c->idct_dc[1] = ff_hevc_idct_8x8_dc_8_neon; c->idct_dc[2] = ff_hevc_idct_16x16_dc_8_neon; -- 2.32.0 (Apple Git-132)

2 2

[PATCH] lavc/aarch64: add hevc chroma loop filter 8-12bit
by J. Dekker 09 Aug '22

09 Aug '22

Signed-off-by: J. Dekker <jdek(a)itanimul.li> --- libavcodec/aarch64/Makefile | 3 +- libavcodec/aarch64/hevcdsp_deblock_neon.S | 168 ++++++++++++++++++++++ libavcodec/aarch64/hevcdsp_init_aarch64.c | 14 ++ 3 files changed, 184 insertions(+), 1 deletion(-) create mode 100644 libavcodec/aarch64/hevcdsp_deblock_neon.S Passes FATE, I never completed the checkasm for loop_filter, working on that currently alongside the luma loop filter. This asm can also go into hevcdsp_sao_neon.S if you would prefer not creating an extra file for it. diff --git a/libavcodec/aarch64/Makefile b/libavcodec/aarch64/Makefile index c8935f205e..66bd8b596c 100644 --- a/libavcodec/aarch64/Makefile +++ b/libavcodec/aarch64/Makefile @@ -63,6 +63,7 @@ NEON-OBJS-$(CONFIG_VP9_DECODER) += aarch64/vp9itxfm_16bpp_neon.o \ aarch64/vp9lpf_neon.o \ aarch64/vp9mc_16bpp_neon.o \ aarch64/vp9mc_neon.o -NEON-OBJS-$(CONFIG_HEVC_DECODER) += aarch64/hevcdsp_idct_neon.o \ +NEON-OBJS-$(CONFIG_HEVC_DECODER) += aarch64/hevcdsp_deblock_neon.o \ + aarch64/hevcdsp_idct_neon.o \ aarch64/hevcdsp_init_aarch64.o \ aarch64/hevcdsp_sao_neon.o diff --git a/libavcodec/aarch64/hevcdsp_deblock_neon.S b/libavcodec/aarch64/hevcdsp_deblock_neon.S new file mode 100644 index 0000000000..d21ad0a54f --- /dev/null +++ b/libavcodec/aarch64/hevcdsp_deblock_neon.S @@ -0,0 +1,168 @@ +/* -*-arm64-*- + * vim: syntax=arm64asm + * + * Copyright (c) 2014 Seppo Tomperi <seppo.tomperi(a)vtt.fi> + * Copyright (c) 2022 J. Dekker <jdek(a)itanimul.li> + * + * 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 "libavutil/aarch64/asm.S" +#include "neon.S" + +.macro hevc_loop_filter_chroma_start bitdepth + ldr w14, [x2] + ldr w15, [x2, #4] +.if \bitdepth > 8 + lsl w14, w14, #(\bitdepth - 8) + lsl w15, w15, #(\bitdepth - 8) +.endif + adds w2, w14, w15 + b.eq 1f + dup v16.4h, w14 + dup v17.4h, w15 + trn1 v16.2d, v16.2d, v17.2d +.if \bitdepth == 10 + mvni v19.8h, #0xFC, lsl #8 // movi #0x03FF +.endif +.if \bitdepth == 12 + mvni v19.8h, #0xF0, lsl #8 // movi #0x0FFF +.endif +.if \bitdepth > 8 + movi v18.8h, #0 +.endif + neg v17.8h, v16.8h +.endm + +.macro hevc_loop_filter_chroma_body bitdepth +.if \bitdepth <= 8 + uxtl v0.8h, v0.8b // p1 + uxtl v1.8h, v1.8b // p0 + uxtl v2.8h, v2.8b // q0 + uxtl v3.8h, v3.8b // q1 +.endif + sub v5.8h, v2.8h, v1.8h // q0 - p0 + sub v6.8h, v0.8h, v3.8h // p1 - q1 + shl v5.8h, v5.8h, #2 + add v5.8h, v6.8h, v5.8h + srshr v5.8h, v5.8h, #3 + smin v5.8h, v5.8h, v16.8h + smax v5.8h, v5.8h, v17.8h + sqadd v1.8h, v1.8h, v5.8h // p0 + delta + sqsub v2.8h, v2.8h, v5.8h // q0 - delta +.if \bitdepth <= 8 + sqxtun v1.8b, v1.8h + sqxtun v2.8b, v2.8h +.else + smin v1.8h, v1.8h, v19.8h + smin v2.8h, v2.8h, v19.8h + smax v1.8h, v1.8h, v18.8h + smax v2.8h, v2.8h, v18.8h +.endif +.endm + +.macro hevc_h_loop_filter_chroma bitdepth +function ff_hevc_h_loop_filter_chroma_\bitdepth\()_neon, export=1 + hevc_loop_filter_chroma_start \bitdepth + sub x0, x0, x1, lsl #1 +.if \bitdepth > 8 + ld1 {v0.8h}, [x0], x1 + ld1 {v1.8h}, [x0], x1 + ld1 {v2.8h}, [x0], x1 + ld1 {v3.8h}, [x0] +.else + ld1 {v0.8b}, [x0], x1 + ld1 {v1.8b}, [x0], x1 + ld1 {v2.8b}, [x0], x1 + ld1 {v3.8h}, [x0] +.endif + hevc_loop_filter_chroma_body \bitdepth + sub x0, x0, x1, lsl #1 +.if \bitdepth > 8 + st1 {v1.8h}, [x0], x1 + st1 {v2.8h}, [x0] +.else + st1 {v1.8b}, [x0], x1 + st1 {v2.8b}, [x0] +.endif +1: ret +endfunc +.endm + +.macro hevc_v_loop_filter_chroma bitdepth +function ff_hevc_v_loop_filter_chroma_\bitdepth\()_neon, export=1 + hevc_loop_filter_chroma_start \bitdepth +.if \bitdepth > 8 + sub x0, x0, #8 + ld1 {v20.8h}, [x0], x1 + ld1 {v21.8h}, [x0], x1 + ld1 {v0.8h}, [x0], x1 + ld1 {v1.8h}, [x0], x1 + ld1 {v2.8h}, [x0], x1 + ld1 {v3.8h}, [x0], x1 + ld1 {v22.8h}, [x0], x1 + ld1 {v23.8h}, [x0], x1 + transpose_8x8H v20, v21, v0, v1, v2, v3, v22, v23, v24, v25 +.else + sub x0, x0, #4 + ld1 {v20.8b}, [x0], x1 + ld1 {v21.8b}, [x0], x1 + ld1 {v0.8b}, [x0], x1 + ld1 {v1.8b}, [x0], x1 + ld1 {v2.8b}, [x0], x1 + ld1 {v3.8b}, [x0], x1 + ld1 {v22.8b}, [x0], x1 + ld1 {v23.8b}, [x0], x1 + transpose_8x8B v20, v21, v0, v1, v2, v3, v22, v23, v24, v25 +.endif + hevc_loop_filter_chroma_body \bitdepth + sub x0, x0, x1, lsl #3 +.if \bitdepth > 8 + transpose_8x8H v20, v21, v0, v1, v2, v3, v22, v23, v24, v25 + st1 {v20.8h}, [x0], x1 + st1 {v21.8h}, [x0], x1 + st1 {v0.8h}, [x0], x1 + st1 {v1.8h}, [x0], x1 + st1 {v2.8h}, [x0], x1 + st1 {v3.8h}, [x0], x1 + st1 {v22.8h}, [x0], x1 + st1 {v23.8h}, [x0] +.else + xtn v0.8b, v0.8h // restore + xtn v3.8b, v3.8h + transpose_8x8B v20, v21, v0, v1, v2, v3, v22, v23, v24, v25 + st1 {v20.8b}, [x0], x1 + st1 {v21.8b}, [x0], x1 + st1 {v0.8b}, [x0], x1 + st1 {v1.8b}, [x0], x1 + st1 {v2.8b}, [x0], x1 + st1 {v3.8b}, [x0], x1 + st1 {v22.8b}, [x0], x1 + st1 {v23.8b}, [x0] +.endif +1: ret +endfunc +.endm + +hevc_h_loop_filter_chroma 8 +hevc_h_loop_filter_chroma 10 +hevc_h_loop_filter_chroma 12 + +hevc_v_loop_filter_chroma 8 +hevc_v_loop_filter_chroma 10 +hevc_v_loop_filter_chroma 12 diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c index 2002530266..3502edb77a 100644 --- a/libavcodec/aarch64/hevcdsp_init_aarch64.c +++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c @@ -25,6 +25,12 @@ #include "libavutil/aarch64/cpu.h" #include "libavcodec/hevcdsp.h" +void ff_hevc_v_loop_filter_chroma_8_neon(uint8_t *_pix, ptrdiff_t _stride, int *_tc, uint8_t *_no_p, uint8_t *_no_q); +void ff_hevc_v_loop_filter_chroma_10_neon(uint8_t *_pix, ptrdiff_t _stride, int *_tc, uint8_t *_no_p, uint8_t *_no_q); +void ff_hevc_v_loop_filter_chroma_12_neon(uint8_t *_pix, ptrdiff_t _stride, int *_tc, uint8_t *_no_p, uint8_t *_no_q); +void ff_hevc_h_loop_filter_chroma_8_neon(uint8_t *_pix, ptrdiff_t _stride, int *_tc, uint8_t *_no_p, uint8_t *_no_q); +void ff_hevc_h_loop_filter_chroma_10_neon(uint8_t *_pix, ptrdiff_t _stride, int *_tc, uint8_t *_no_p, uint8_t *_no_q); +void ff_hevc_h_loop_filter_chroma_12_neon(uint8_t *_pix, ptrdiff_t _stride, int *_tc, uint8_t *_no_p, uint8_t *_no_q); void ff_hevc_add_residual_4x4_8_neon(uint8_t *_dst, int16_t *coeffs, ptrdiff_t stride); void ff_hevc_add_residual_4x4_10_neon(uint8_t *_dst, int16_t *coeffs, @@ -67,6 +73,8 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth) if (!have_neon(av_get_cpu_flags())) return; if (bit_depth == 8) { + 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; c->add_residual[1] = ff_hevc_add_residual_8x8_8_neon; c->add_residual[2] = ff_hevc_add_residual_16x16_8_neon; @@ -89,6 +97,8 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth) c->sao_edge_filter[4] = ff_hevc_sao_edge_filter_16x16_8_neon; } if (bit_depth == 10) { + 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; c->add_residual[1] = ff_hevc_add_residual_8x8_10_neon; c->add_residual[2] = ff_hevc_add_residual_16x16_10_neon; @@ -100,4 +110,8 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth) c->idct_dc[2] = ff_hevc_idct_16x16_dc_10_neon; c->idct_dc[3] = ff_hevc_idct_32x32_dc_10_neon; } + if (bit_depth == 12) { + 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; + } } -- 2.32.0 (Apple Git-132)

2 2

[PATCH] checkasm: Silence warnings about unused return value from read()
by Martin Storsjö 08 Aug '22

08 Aug '22

This codepath is enabled by default on arm, if the linux perf API is available, unless disabled with --disable-linux-perf. --- tests/checkasm/checkasm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tests/checkasm/checkasm.h b/tests/checkasm/checkasm.h index a86db140e3..7fd1e1606d 100644 --- a/tests/checkasm/checkasm.h +++ b/tests/checkasm/checkasm.h @@ -229,8 +229,10 @@ typedef struct CheckasmPerf { ioctl(sysfd, PERF_EVENT_IOC_ENABLE, 0); \ } while (0) #define PERF_STOP(t) do { \ + int ret; \ ioctl(sysfd, PERF_EVENT_IOC_DISABLE, 0); \ - read(sysfd, &t, sizeof(t)); \ + ret = read(sysfd, &t, sizeof(t)); \ + (void)ret; \ } while (0) #elif CONFIG_MACOS_KPERF #define PERF_START(t) t = ff_kperf_cycles() -- 2.32.0 (Apple Git-132)

3 4

[PATCH] avcodec/jpeg2000: Fast fail if HTJ2K codeblocks are present.
by caleb 07 Aug '22

07 Aug '22

--- libavcodec/jpeg2000.h | 2 ++ libavcodec/jpeg2000dec.c | 4 ++++ 2 files changed, 6 insertions(+) diff --git a/libavcodec/jpeg2000.h b/libavcodec/jpeg2000.h index d06313425e..e5ecb4cbf9 100644 --- a/libavcodec/jpeg2000.h +++ b/libavcodec/jpeg2000.h @@ -110,6 +110,8 @@ enum Jpeg2000Quantsty { // quantization style #define JPEG2000_CSTY_PREC 0x01 // Precincts defined in coding style #define JPEG2000_CSTY_SOP 0x02 // SOP marker present #define JPEG2000_CSTY_EPH 0x04 // EPH marker present +#define JPEG2000_CTSY_HTJ2K_F 0x40 // Only HT code-blocks (Rec. ITU-T T.814 | ISO/IEC 15444-15) are present +#define JPEG2000_CTSY_HTJ2K_M 0xC0 // HT code blocks (Rec. ITU-T T.814 | ISO/IEC 15444-15) can be present // Progression orders #define JPEG2000_PGOD_LRCP 0x00 // Layer-resolution level-component-position progression diff --git a/libavcodec/jpeg2000dec.c b/libavcodec/jpeg2000dec.c index 92966b11f5..30f8c878d1 100644 --- a/libavcodec/jpeg2000dec.c +++ b/libavcodec/jpeg2000dec.c @@ -521,6 +521,10 @@ static int get_cox(Jpeg2000DecoderContext *s, Jpeg2000CodingStyle *c) c->cblk_style = bytestream2_get_byteu(&s->g); if (c->cblk_style != 0) { // cblk style + if (c->cblk_style & JPEG2000_CTSY_HTJ2K_M || c->cblk_style & JPEG2000_CTSY_HTJ2K_F) { + av_log(s->avctx, AV_LOG_ERROR, "Support for High throughput JPEG 2000 is not yet available\n"); + return AVERROR_PATCHWELCOME; + } av_log(s->avctx, AV_LOG_WARNING, "extra cblk styles %X\n", c->cblk_style); if (c->cblk_style & JPEG2000_CBLK_BYPASS) av_log(s->avctx, AV_LOG_WARNING, "Selective arithmetic coding bypass\n"); -- 2.34.0

5 7

[PATCH] avformat: allow .ec3 as extension for raw E-AC-3 stream
by Ruben Gonzalez 05 Aug '22

05 Aug '22

In addition to .eac3, .ec3 is also commonly used by people to name raw E-AC-3 streams. Enables automatic recognition of the eac3 format for the .ac3 extension. For instance Dolby Digital Plus software only support files with .ec3. Files with .eac3 are not supported. Check issue #18 in the public dlb_mp4base repository from DolbyLaboratories. Signed-off-by: Ruben Gonzalez <rgonzalez(a)fluendo.com> --- libavformat/ac3dec.c | 2 +- libavformat/rawenc.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/libavformat/ac3dec.c b/libavformat/ac3dec.c index 51461befd8..989d126a81 100644 --- a/libavformat/ac3dec.c +++ b/libavformat/ac3dec.c @@ -131,7 +131,7 @@ const AVInputFormat ff_eac3_demuxer = { .read_header = ff_raw_audio_read_header, .read_packet = ff_raw_read_partial_packet, .flags = AVFMT_GENERIC_INDEX, - .extensions = "eac3", + .extensions = "eac3,ec3", .raw_codec_id = AV_CODEC_ID_EAC3, .priv_data_size = sizeof(FFRawDemuxerContext), .priv_class = &ff_raw_demuxer_class, diff --git a/libavformat/rawenc.c b/libavformat/rawenc.c index 26099cb1c1..267fce252d 100644 --- a/libavformat/rawenc.c +++ b/libavformat/rawenc.c @@ -252,7 +252,7 @@ const AVOutputFormat ff_eac3_muxer = { .name = "eac3", .long_name = NULL_IF_CONFIG_SMALL("raw E-AC-3"), .mime_type = "audio/x-eac3", - .extensions = "eac3", + .extensions = "eac3,ec3", .audio_codec = AV_CODEC_ID_EAC3, .video_codec = AV_CODEC_ID_NONE, .init = force_one_stream, -- 2.25.1

2 3

[PATCH 1/2] ffmpeg: add display_{rotation, hflip, vflip} options
by Jan Ekström 02 Aug '22

02 Aug '22

This enables overriding the rotation as well as horizontal/vertical flip state of a specific video stream on either the input or output side. Additionally, switch the singular test that was utilizing the rotation metadata to instead override the input display rotation, thus leading to the same result. --- doc/ffmpeg.texi | 29 +++++++++++++++++++++ fftools/ffmpeg.h | 6 +++++ fftools/ffmpeg_opt.c | 52 +++++++++++++++++++++++++++++++++++++ tests/fate/filter-video.mak | 2 +- 4 files changed, 88 insertions(+), 1 deletion(-) diff --git a/doc/ffmpeg.texi b/doc/ffmpeg.texi index 0d7e1a479d..f44d863f02 100644 --- a/doc/ffmpeg.texi +++ b/doc/ffmpeg.texi @@ -897,6 +897,35 @@ If used together with @option{-vcodec copy}, it will affect the aspect ratio stored at container level, but not the aspect ratio stored in encoded frames, if it exists. +@item -display_rotation[:@var{stream_specifier}] @var{rotation} (@emph{input/output,per-stream}) +Set the video display rotation in degrees specified by @var{rotation}. + +@var{rotation} is a floating point number that describes a pure +counter-clockwise rotation in degrees. + +When setting this for input streams, @code{-autorotate} logic will be affected. +For additional parameters affecting display matrix side data into which this +information is saved, see @code{-display_hflip} and @code{-display_vflip}. + +These options work as a unit, so if only one of them is set, then the display +matrix will be overridden to that specific value with the rest being set to +default values. + +If unset, the default value if a display matrix is being defined is a rotation +of zero degrees. + +@item -display_hflip[:@var{stream_specifier}] (@emph{input/output,per-stream}) +Set whether on display the image should be horizontally flipped. + +If unset, the default value if a display matrix is being defined is that there +is no additional horizontal flip. See @code{-display_rotation}. + +@item -display_vflip[:@var{stream_specifier}] (@emph{input/output,per-stream}) +Set whether on display the image should be vertically flipped. + +If unset, the default value if a display matrix is being defined is that there +is no additional vertical flip. See @code{-display_rotation}. + @item -vn (@emph{input/output}) As an input option, blocks all video streams of a file from being filtered or being automatically selected or mapped for any output. See @code{-discard} diff --git a/fftools/ffmpeg.h b/fftools/ffmpeg.h index 9f0c093e34..0da01b0668 100644 --- a/fftools/ffmpeg.h +++ b/fftools/ffmpeg.h @@ -180,6 +180,12 @@ typedef struct OptionsContext { int nb_force_fps; SpecifierOpt *frame_aspect_ratios; int nb_frame_aspect_ratios; + SpecifierOpt *display_rotations; + int nb_display_rotations; + SpecifierOpt *display_hflips; + int nb_display_hflips; + SpecifierOpt *display_vflips; + int nb_display_vflips; SpecifierOpt *rc_overrides; int nb_rc_overrides; SpecifierOpt *intra_matrices; diff --git a/fftools/ffmpeg_opt.c b/fftools/ffmpeg_opt.c index 47e8b9b7bd..0d1c84d6df 100644 --- a/fftools/ffmpeg_opt.c +++ b/fftools/ffmpeg_opt.c @@ -20,6 +20,7 @@ #include "config.h" +#include <float.h> #include <stdint.h> #if HAVE_SYS_RESOURCE_H @@ -43,6 +44,7 @@ #include "libavutil/avutil.h" #include "libavutil/bprint.h" #include "libavutil/channel_layout.h" +#include "libavutil/display.h" #include "libavutil/intreadwrite.h" #include "libavutil/fifo.h" #include "libavutil/mathematics.h" @@ -82,6 +84,9 @@ static const char *const opt_name_qscale[] = {"q", "qscale", static const char *const opt_name_forced_key_frames[] = {"forced_key_frames", NULL}; static const char *const opt_name_force_fps[] = {"force_fps", NULL}; static const char *const opt_name_frame_aspect_ratios[] = {"aspect", NULL}; +static const char *const opt_name_display_rotations[] = {"display_rotation", NULL}; +static const char *const opt_name_display_hflips[] = {"display_hflip", NULL}; +static const char *const opt_name_display_vflips[] = {"display_vflip", NULL}; static const char *const opt_name_rc_overrides[] = {"rc_override", NULL}; static const char *const opt_name_intra_matrices[] = {"intra_matrix", NULL}; static const char *const opt_name_inter_matrices[] = {"inter_matrix", NULL}; @@ -739,6 +744,39 @@ static int opt_recording_timestamp(void *optctx, const char *opt, const char *ar return 0; } +static void add_display_matrix_to_stream(OptionsContext *o, + AVFormatContext *ctx, AVStream *st) +{ + double display_rotation = DBL_MAX; + int hflip = -1, vflip = -1, + hflip_set = 0, vflip_set = 0, display_rotation_set = 0; + uint8_t *buf = NULL; + + MATCH_PER_STREAM_OPT(display_rotations, dbl, display_rotation, ctx, st); + MATCH_PER_STREAM_OPT(display_hflips, i, hflip, ctx, st); + MATCH_PER_STREAM_OPT(display_vflips, i, vflip, ctx, st); + + display_rotation_set = display_rotation != DBL_MAX; + hflip_set = hflip != -1; + vflip_set = vflip != -1; + + if (!display_rotation_set && !hflip_set && !vflip_set) + return; + + if (!(buf = av_stream_new_side_data(st, AV_PKT_DATA_DISPLAYMATRIX, + sizeof(int32_t) * 9))) { + av_log(NULL, AV_LOG_FATAL, "Failed to generate a display matrix!\n"); + exit_program(1); + } + + av_display_rotation_set((int32_t *)buf, + display_rotation_set ? -display_rotation : + -0.0f); + av_display_matrix_flip((int32_t *)buf, + hflip_set ? hflip : 0, + vflip_set ? vflip : 0); +} + static const AVCodec *find_codec_or_die(const char *name, enum AVMediaType type, int encoder) { const AVCodecDescriptor *desc; @@ -893,6 +931,8 @@ static void add_input_streams(OptionsContext *o, AVFormatContext *ic) ist->top_field_first = -1; MATCH_PER_STREAM_OPT(top_field_first, i, ist->top_field_first, ic, st); + add_display_matrix_to_stream(o, ic, st); + MATCH_PER_STREAM_OPT(hwaccels, str, hwaccel, ic, st); MATCH_PER_STREAM_OPT(hwaccel_output_formats, str, hwaccel_output_format, ic, st); @@ -1752,6 +1792,8 @@ static OutputStream *new_video_stream(OptionsContext *o, AVFormatContext *oc, in ost->frame_aspect_ratio = q; } + add_display_matrix_to_stream(o, oc, st); + MATCH_PER_STREAM_OPT(filter_scripts, str, ost->filters_script, oc, st); MATCH_PER_STREAM_OPT(filters, str, ost->filters, oc, st); @@ -3731,6 +3773,16 @@ const OptionDef options[] = { { "aspect", OPT_VIDEO | HAS_ARG | OPT_STRING | OPT_SPEC | OPT_OUTPUT, { .off = OFFSET(frame_aspect_ratios) }, "set aspect ratio (4:3, 16:9 or 1.3333, 1.7777)", "aspect" }, + { "display_rotation", OPT_VIDEO | HAS_ARG | OPT_DOUBLE | OPT_SPEC | OPT_INPUT | + OPT_OUTPUT, { .off = OFFSET(display_rotations) }, + "set pure counter-clockwise rotation in degrees for stream(s)", + "rotation" }, + { "display_hflip", OPT_VIDEO | OPT_BOOL | OPT_SPEC | OPT_INPUT | OPT_OUTPUT, { .off = OFFSET(display_hflips) }, + "set display horizontal flip for stream(s) " + "(overrides any display rotation if it is not set)"}, + { "display_vflip", OPT_VIDEO | OPT_BOOL | OPT_SPEC | OPT_INPUT | OPT_OUTPUT, { .off = OFFSET(display_vflips) }, + "set display vertical flip for stream(s) " + "(overrides any display rotation if it is not set)"}, { "pix_fmt", OPT_VIDEO | HAS_ARG | OPT_EXPERT | OPT_STRING | OPT_SPEC | OPT_INPUT | OPT_OUTPUT, { .off = OFFSET(frame_pix_fmts) }, "set pixel format", "format" }, diff --git a/tests/fate/filter-video.mak b/tests/fate/filter-video.mak index 86408dd58c..ce6ae255b4 100644 --- a/tests/fate/filter-video.mak +++ b/tests/fate/filter-video.mak @@ -856,7 +856,7 @@ fate-filter-metadata-avf-aphase-meter-out-of-phase: SRC = $(TARGET_SAMPLES)/filt fate-filter-metadata-avf-aphase-meter-out-of-phase: CMD = run $(FILTER_METADATA_COMMAND) "amovie='$(SRC)',aphasemeter=video=0" FATE_FILTER_SAMPLES-$(call TRANSCODE, RAWVIDEO H264, MOV, ARESAMPLE_FILTER AAC_FIXED_DECODER) += fate-filter-meta-4560-rotate0 -fate-filter-meta-4560-rotate0: CMD = transcode mov $(TARGET_SAMPLES)/filter/sample-in-issue-505.mov mov "-c copy -metadata:s:v:0 rotate=0" "-af aresample" "" "" "-flags +bitexact -c:a aac_fixed" +fate-filter-meta-4560-rotate0: CMD = transcode "mov -display_rotation:v:0 0" $(TARGET_SAMPLES)/filter/sample-in-issue-505.mov mov "-c copy" "-af aresample" "" "" "-flags +bitexact -c:a aac_fixed" REFCMP_DEPS = FFMPEG LAVFI_INDEV TESTSRC2_FILTER AVGBLUR_FILTER METADATA_FILTER -- 2.36.1

4 10

[PATCH] swscale: add NV16 input/output
by Matthieu Bouron 02 Aug '22

02 Aug '22

--- libswscale/input.c | 1 + libswscale/utils.c | 1 + libswscale/version.h | 2 +- tests/ref/fate/filter-pixdesc-nv16 | 1 + tests/ref/fate/filter-pixfmts-copy | 1 + tests/ref/fate/filter-pixfmts-crop | 1 + tests/ref/fate/filter-pixfmts-field | 1 + tests/ref/fate/filter-pixfmts-fieldorder | 1 + tests/ref/fate/filter-pixfmts-hflip | 1 + tests/ref/fate/filter-pixfmts-il | 1 + tests/ref/fate/filter-pixfmts-null | 1 + tests/ref/fate/filter-pixfmts-pad | 1 + tests/ref/fate/filter-pixfmts-scale | 1 + tests/ref/fate/filter-pixfmts-vflip | 1 + 14 files changed, 14 insertions(+), 1 deletion(-) create mode 100644 tests/ref/fate/filter-pixdesc-nv16 diff --git a/libswscale/input.c b/libswscale/input.c index fe0c27d743..750367b28b 100644 --- a/libswscale/input.c +++ b/libswscale/input.c @@ -1101,6 +1101,7 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c) c->chrToYV12 = uyvyToUV_c; break; case AV_PIX_FMT_NV12: + case AV_PIX_FMT_NV16: case AV_PIX_FMT_NV24: c->chrToYV12 = nv12ToUV_c; break; diff --git a/libswscale/utils.c b/libswscale/utils.c index 105781c4f4..8298ae8e10 100644 --- a/libswscale/utils.c +++ b/libswscale/utils.c @@ -257,6 +257,7 @@ static const FormatEntry format_entries[] = { [AV_PIX_FMT_P216LE] = { 1, 1 }, [AV_PIX_FMT_P416BE] = { 1, 1 }, [AV_PIX_FMT_P416LE] = { 1, 1 }, + [AV_PIX_FMT_NV16] = { 1, 1 }, }; int ff_shuffle_filter_coefficients(SwsContext *c, int *filterPos, diff --git a/libswscale/version.h b/libswscale/version.h index f573bef6fc..0fa41f77d2 100644 --- a/libswscale/version.h +++ b/libswscale/version.h @@ -29,7 +29,7 @@ #include "version_major.h" #define LIBSWSCALE_VERSION_MINOR 6 -#define LIBSWSCALE_VERSION_MICRO 100 +#define LIBSWSCALE_VERSION_MICRO 101 #define LIBSWSCALE_VERSION_INT AV_VERSION_INT(LIBSWSCALE_VERSION_MAJOR, \ LIBSWSCALE_VERSION_MINOR, \ diff --git a/tests/ref/fate/filter-pixdesc-nv16 b/tests/ref/fate/filter-pixdesc-nv16 new file mode 100644 index 0000000000..4c4587c833 --- /dev/null +++ b/tests/ref/fate/filter-pixdesc-nv16 @@ -0,0 +1 @@ +pixdesc-nv16 cbbc5d904b8eebad3705a325c3ec5734 diff --git a/tests/ref/fate/filter-pixfmts-copy b/tests/ref/fate/filter-pixfmts-copy index f06fa1574e..3cd0002e4e 100644 --- a/tests/ref/fate/filter-pixfmts-copy +++ b/tests/ref/fate/filter-pixfmts-copy @@ -56,6 +56,7 @@ grayf32le fb6ea85bfbc8cd21c51fc0e110197294 monob 8b04f859fee6a0be856be184acd7a0b5 monow 54d16d2c01abfd72ecdb5e51e283937c nv12 8e24feb2c544dc26a20047a71e4c27aa +nv16 22b1916c0694c4e2979bab8eb71f3d6b nv21 335d85c9af6110f26ae9e187a82ed2cf nv24 f30fc8d0ac40af69e119ea919a314572 nv42 29a212f70f8780fe0eb99abcae81894d diff --git a/tests/ref/fate/filter-pixfmts-crop b/tests/ref/fate/filter-pixfmts-crop index 8b26ab9c53..1a0f0c79ed 100644 --- a/tests/ref/fate/filter-pixfmts-crop +++ b/tests/ref/fate/filter-pixfmts-crop @@ -54,6 +54,7 @@ gray9le 4d1932d4968a248584f5e39c25f1dd43 grayf32be cf40ec06a8abe54852b7f85a00549eec grayf32le b672526c9da9c8959ab881f242f6890a nv12 92cda427f794374731ec0321ee00caac +nv16 3264b16aaae554c21f052102b491c13b nv21 1bcfc197f4fb95de85ba58182d8d2f69 nv24 514c8f12082f0737e558778cbe7de258 nv42 ece9baae1c5de579dac2c66a89e08ef3 diff --git a/tests/ref/fate/filter-pixfmts-field b/tests/ref/fate/filter-pixfmts-field index c4838d1446..27a74eaef3 100644 --- a/tests/ref/fate/filter-pixfmts-field +++ b/tests/ref/fate/filter-pixfmts-field @@ -56,6 +56,7 @@ grayf32le 6b856bdbf2a2bfcd2bc7d50f109daaf0 monob 2129cc72a484d7e10a44de9117aa9f80 monow 03d783611d265cae78293f88ea126ea1 nv12 16f7a46708ef25ebd0b72e47920cc11e +nv16 34f36b03f5fccf4eac147b26bbc0a5e5 nv21 7294574037cc7f9373ef5695d8ebe809 nv24 3b100fb527b64ee2b2d7120da573faf5 nv42 1841ce853152d86b27c130f319ea0db2 diff --git a/tests/ref/fate/filter-pixfmts-fieldorder b/tests/ref/fate/filter-pixfmts-fieldorder index 32c06bae4c..ab080d1a37 100644 --- a/tests/ref/fate/filter-pixfmts-fieldorder +++ b/tests/ref/fate/filter-pixfmts-fieldorder @@ -53,6 +53,7 @@ gray9be ec877f5bcf0ea275a6f36c12cc9adf11 gray9le fba944fde7923d5089f4f52d12988b9e grayf32be 1aa7960131f880c54fe3c77f13448674 grayf32le 4029ac9d197f255794c1b9e416520fc7 +nv16 085deb984ab986eb5cc961fe265e30c0 nv24 4fdbef26042c77f012df114e666efdb2 nv42 59608290fece913e6b7d61edf581a529 p210be ca2ce2c25db43dcd14729b2a72a7c604 diff --git a/tests/ref/fate/filter-pixfmts-hflip b/tests/ref/fate/filter-pixfmts-hflip index 4d3efe3cdc..8c7a9d83c9 100644 --- a/tests/ref/fate/filter-pixfmts-hflip +++ b/tests/ref/fate/filter-pixfmts-hflip @@ -54,6 +54,7 @@ gray9le 424fc581947bc8c357c9ec5e3c1c04d1 grayf32be a69add7bbf892a71fe81b3b75982dbe2 grayf32le 4563e176a35dc8a8a07e0829fad5eb88 nv12 801e58f1be5fd0b5bc4bf007c604b0b4 +nv16 06ba714cb8b220c203f5898ef39abf93 nv21 9f10dfff8963dc327d3395af21f0554f nv24 f0c5b2f42970f8d4003621d8857a872f nv42 4dcf9aec82b110712b396a8b365dcb13 diff --git a/tests/ref/fate/filter-pixfmts-il b/tests/ref/fate/filter-pixfmts-il index 4623f2420c..15dbe868a6 100644 --- a/tests/ref/fate/filter-pixfmts-il +++ b/tests/ref/fate/filter-pixfmts-il @@ -56,6 +56,7 @@ grayf32le 8bf3d295c3ffd53da0e06d0702e7c1ca monob faba75df28033ba7ce3d82ff2a99ee68 monow 6e9cfb8d3a344c5f0c3e1d5e1297e580 nv12 3c3ba9b1b4c4dfff09c26f71b51dd146 +nv16 355d055f91793a171302021b3fc486b0 nv21 ab586d8781246b5a32d8760a61db9797 nv24 554153c71d142e3fd8e40b7dcaaec229 nv42 d699724c8deaeb4f87faf2766512eec3 diff --git a/tests/ref/fate/filter-pixfmts-null b/tests/ref/fate/filter-pixfmts-null index f06fa1574e..3cd0002e4e 100644 --- a/tests/ref/fate/filter-pixfmts-null +++ b/tests/ref/fate/filter-pixfmts-null @@ -56,6 +56,7 @@ grayf32le fb6ea85bfbc8cd21c51fc0e110197294 monob 8b04f859fee6a0be856be184acd7a0b5 monow 54d16d2c01abfd72ecdb5e51e283937c nv12 8e24feb2c544dc26a20047a71e4c27aa +nv16 22b1916c0694c4e2979bab8eb71f3d6b nv21 335d85c9af6110f26ae9e187a82ed2cf nv24 f30fc8d0ac40af69e119ea919a314572 nv42 29a212f70f8780fe0eb99abcae81894d diff --git a/tests/ref/fate/filter-pixfmts-pad b/tests/ref/fate/filter-pixfmts-pad index 519473032e..e340a76389 100644 --- a/tests/ref/fate/filter-pixfmts-pad +++ b/tests/ref/fate/filter-pixfmts-pad @@ -22,6 +22,7 @@ gray14le af3f2f911c71cb34a8179a3291b5c90f gray16le 468bda6155bdc7a7a20c34d6e599fd16 gray9le f8f3dfe31ca5fcba828285bceefdab9a nv12 381574979cb04be10c9168540310afad +nv16 d3a50501d2ea8535489fd5ec49e7866d nv21 0fdeb2cdd56cf5a7147dc273456fa217 nv24 193b9eadcc06ad5081609f76249b3e47 nv42 1738ad3c31c6c16e17679f5b09ce4677 diff --git a/tests/ref/fate/filter-pixfmts-scale b/tests/ref/fate/filter-pixfmts-scale index 43074b84a7..95a3f071b8 100644 --- a/tests/ref/fate/filter-pixfmts-scale +++ b/tests/ref/fate/filter-pixfmts-scale @@ -56,6 +56,7 @@ grayf32le 2ff1b84023e820307b1ba7a9550115bc monob f01cb0b623357387827902d9d0963435 monow 35c68b86c226d6990b2dcb573a05ff6b nv12 b118d24a3653fe66e5d9e079033aef79 +nv16 68e757396b62b84aad657274b8f6ce15 nv21 c74bb1c10dbbdee8a1f682b194486c4d nv24 2aa6e805bf6d4179ed8d7dea37d75db3 nv42 80714d1eb2d8bcaeab3abc3124df1abd diff --git a/tests/ref/fate/filter-pixfmts-vflip b/tests/ref/fate/filter-pixfmts-vflip index 3a53bb5837..7af28d3a8f 100644 --- a/tests/ref/fate/filter-pixfmts-vflip +++ b/tests/ref/fate/filter-pixfmts-vflip @@ -56,6 +56,7 @@ grayf32le 8e6c048a5b3b8b26d3a5ddfce255f3f6 monob 7810c4857822ccfc844d78f5e803269a monow 90a947bfcd5f2261e83b577f48ec57b1 nv12 261ebe585ae2aa4e70d39a10c1679294 +nv16 f20f3448c900847aaff74429196f5a00 nv21 2909feacd27bebb080c8e0fa41795269 nv24 334420b9d3df84499d2ca16bb66eed2b nv42 ba4063e2795c17fea3c8a646b01fd1f5 -- 2.36.1

3 8

[PATCH 1/3] Provided support for MPEG-5 EVC (Essential Video Coding) codec
by Dawid Kozinski 01 Aug '22

01 Aug '22

Prerequisites that must be met before adding new codec - Added new entry to codec IDs list - Added new entry to the codec descriptor list - Bumped libavcodec minor version - Changes in Changelog and MAINTAINERS files Signed-off-by: Dawid Kozinski <d.kozinski(a)samsung.com> --- Changelog | 3 ++- MAINTAINERS | 2 ++ libavcodec/codec_desc.c | 8 ++++++++ libavcodec/codec_id.h | 1 + libavcodec/profiles.c | 6 ++++++ libavcodec/profiles.h | 1 + libavcodec/version.h | 2 +- 7 files changed, 21 insertions(+), 2 deletions(-) diff --git a/Changelog b/Changelog index ef589705c4..0d230bde91 100644 --- a/Changelog +++ b/Changelog @@ -67,7 +67,8 @@ version 5.0: - VideoToolbox ProRes encoder - anlmf audio filter - IMF demuxer (experimental) - +- eXtra-fast Essential Video Encoder (XEVE) +- eXtra-fast Essential Video Decoder (XEVD) version 4.4: - AudioToolbox output device diff --git a/MAINTAINERS b/MAINTAINERS index 274fc89203..4b33d3c1b2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -205,6 +205,7 @@ Codecs: libvpx* James Zern libxavs.c Stefan Gehrer libxavs2.c Huiwen Ren + libxev*.c, evc_parser.c Dawid Kozinski libzvbi-teletextdec.c Marton Balint lzo.h, lzo.c Reimar Doeffinger mdec.c Michael Niedermayer @@ -425,6 +426,7 @@ Muxers/Demuxers: dv.c Roman Shaposhnik electronicarts.c Peter Ross epafdec.c Paul B Mahol + evcdec.c Dawid Kozinski ffm* Baptiste Coudurier flic.c Mike Melanson flvdec.c Michael Niedermayer diff --git a/libavcodec/codec_desc.c b/libavcodec/codec_desc.c index e2c1c67f5e..ea6f65ee9c 100644 --- a/libavcodec/codec_desc.c +++ b/libavcodec/codec_desc.c @@ -1886,6 +1886,14 @@ static const AVCodecDescriptor codec_descriptors[] = { .long_name = NULL_IF_CONFIG_SMALL("QOI (Quite OK Image)"), .props = AV_CODEC_PROP_INTRA_ONLY | AV_CODEC_PROP_LOSSLESS, }, + { + .id = AV_CODEC_ID_EVC, + .type = AVMEDIA_TYPE_VIDEO, + .name = "evc", + .long_name = NULL_IF_CONFIG_SMALL("MPEG-5 EVC (Essential Video Coding)"), + .props = AV_CODEC_PROP_LOSSY | AV_CODEC_PROP_REORDER, + .profiles = NULL_IF_CONFIG_SMALL(ff_evc_profiles), + }, /* various PCM "codecs" */ { diff --git a/libavcodec/codec_id.h b/libavcodec/codec_id.h index 93856a16f2..7ed4aed861 100644 --- a/libavcodec/codec_id.h +++ b/libavcodec/codec_id.h @@ -311,6 +311,7 @@ enum AVCodecID { AV_CODEC_ID_VBN, AV_CODEC_ID_JPEGXL, AV_CODEC_ID_QOI, + AV_CODEC_ID_EVC, /* various PCM "codecs" */ AV_CODEC_ID_FIRST_AUDIO = 0x10000, ///< A dummy id pointing at the start of audio codecs diff --git a/libavcodec/profiles.c b/libavcodec/profiles.c index 7af7fbeb13..a31244e0db 100644 --- a/libavcodec/profiles.c +++ b/libavcodec/profiles.c @@ -181,4 +181,10 @@ const AVProfile ff_arib_caption_profiles[] = { { FF_PROFILE_UNKNOWN } }; +const AVProfile ff_evc_profiles[] = { + { FF_PROFILE_EVC_BASELINE, "Baseline" }, + { FF_PROFILE_EVC_MAIN, "Main" }, + { FF_PROFILE_UNKNOWN }, +}; + #endif /* !CONFIG_SMALL */ diff --git a/libavcodec/profiles.h b/libavcodec/profiles.h index 41a19aa9ad..cf92b5f126 100644 --- a/libavcodec/profiles.h +++ b/libavcodec/profiles.h @@ -72,5 +72,6 @@ extern const AVProfile ff_sbc_profiles[]; extern const AVProfile ff_prores_profiles[]; extern const AVProfile ff_mjpeg_profiles[]; extern const AVProfile ff_arib_caption_profiles[]; +extern const AVProfile ff_evc_profiles[]; #endif /* AVCODEC_PROFILES_H */ diff --git a/libavcodec/version.h b/libavcodec/version.h index 2a08e42d7e..0ef6c991f3 100644 --- a/libavcodec/version.h +++ b/libavcodec/version.h @@ -29,7 +29,7 @@ #include "version_major.h" -#define LIBAVCODEC_VERSION_MINOR 33 +#define LIBAVCODEC_VERSION_MINOR 34 #define LIBAVCODEC_VERSION_MICRO 100 #define LIBAVCODEC_VERSION_INT AV_VERSION_INT(LIBAVCODEC_VERSION_MAJOR, \ -- 2.17.1

3 2