#include "libavutil/opt.h"
#include "libavutil/pixdesc.h"
+#include "av1.h"
#include "avcodec.h"
#include "internal.h"
#include "profiles.h"
unsigned long duration; /**< duration to show frame
(in timebase units) */
uint32_t flags; /**< flags for this frame */
+ uint64_t sse[4];
+ int have_sse; /**< true if we have pending sse[] */
+ uint64_t frame_number;
struct FrameListData *next;
};
typedef struct AOMEncoderContext {
AVClass *class;
+ AVBSFContext *bsf;
struct aom_codec_ctx encoder;
struct aom_image rawimg;
struct aom_fixed_buf twopass_stats;
int crf;
int static_thresh;
int drop_threshold;
- int noise_sensitivity;
+ uint64_t sse[4];
+ int have_sse; /**< true if we have pending sse[] */
+ uint64_t frame_number;
+ int tile_cols, tile_rows;
+ int tile_cols_log2, tile_rows_log2;
+ aom_superblock_size_t superblock_size;
+ int uniform_tiles;
+ int row_mt;
} AOMContext;
static const char *const ctlidstr[] = {
[AV1E_SET_COLOR_PRIMARIES] = "AV1E_SET_COLOR_PRIMARIES",
[AV1E_SET_MATRIX_COEFFICIENTS] = "AV1E_SET_MATRIX_COEFFICIENTS",
[AV1E_SET_TRANSFER_CHARACTERISTICS] = "AV1E_SET_TRANSFER_CHARACTERISTICS",
+ [AV1E_SET_SUPERBLOCK_SIZE] = "AV1E_SET_SUPERBLOCK_SIZE",
+ [AV1E_SET_TILE_COLUMNS] = "AV1E_SET_TILE_COLUMNS",
+ [AV1E_SET_TILE_ROWS] = "AV1E_SET_TILE_ROWS",
+#ifdef AOM_CTRL_AV1E_SET_ROW_MT
+ [AV1E_SET_ROW_MT] = "AV1E_SET_ROW_MT",
+#endif
};
static av_cold void log_encoder_error(AVCodecContext *avctx, const char *desc)
width, "kf_mode:", cfg->kf_mode,
width, "kf_min_dist:", cfg->kf_min_dist,
width, "kf_max_dist:", cfg->kf_max_dist);
+ av_log(avctx, level, "tile settings\n"
+ " %*s%d\n %*s%d\n",
+ width, "tile_width_count:", cfg->tile_width_count,
+ width, "tile_height_count:", cfg->tile_height_count);
av_log(avctx, level, "\n");
}
}
static av_cold int codecctl_int(AVCodecContext *avctx,
- enum aome_enc_control_id id, int val)
+#ifdef UENUM1BYTE
+ aome_enc_control_id id,
+#else
+ enum aome_enc_control_id id,
+#endif
+ int val)
{
AOMContext *ctx = avctx->priv_data;
char buf[80];
av_freep(&ctx->twopass_stats.buf);
av_freep(&avctx->stats_out);
free_frame_list(ctx->coded_frame_list);
+ av_bsf_free(&ctx->bsf);
return 0;
}
static void set_color_range(AVCodecContext *avctx)
{
- enum aom_color_range aom_cr;
+ aom_color_range_t aom_cr;
switch (avctx->color_range) {
case AVCOL_RANGE_UNSPECIFIED:
case AVCOL_RANGE_MPEG: aom_cr = AOM_CR_STUDIO_RANGE; break;
codecctl_int(avctx, AV1E_SET_COLOR_RANGE, aom_cr);
}
+static int count_uniform_tiling(int dim, int sb_size, int tiles_log2)
+{
+ int sb_dim = (dim + sb_size - 1) / sb_size;
+ int tile_dim = (sb_dim + (1 << tiles_log2) - 1) >> tiles_log2;
+ av_assert0(tile_dim > 0);
+ return (sb_dim + tile_dim - 1) / tile_dim;
+}
+
+static int choose_tiling(AVCodecContext *avctx,
+ struct aom_codec_enc_cfg *enccfg)
+{
+ AOMContext *ctx = avctx->priv_data;
+ int sb_128x128_possible, sb_size, sb_width, sb_height;
+ int uniform_rows, uniform_cols;
+ int uniform_64x64_possible, uniform_128x128_possible;
+ int tile_size, rounding, i;
+
+ if (ctx->tile_cols_log2 >= 0)
+ ctx->tile_cols = 1 << ctx->tile_cols_log2;
+ if (ctx->tile_rows_log2 >= 0)
+ ctx->tile_rows = 1 << ctx->tile_rows_log2;
+
+ if (ctx->tile_cols == 0) {
+ ctx->tile_cols = (avctx->width + AV1_MAX_TILE_WIDTH - 1) /
+ AV1_MAX_TILE_WIDTH;
+ if (ctx->tile_cols > 1) {
+ av_log(avctx, AV_LOG_DEBUG, "Automatically using %d tile "
+ "columns to fill width.\n", ctx->tile_cols);
+ }
+ }
+ av_assert0(ctx->tile_cols > 0);
+ if (ctx->tile_rows == 0) {
+ int max_tile_width =
+ FFALIGN((FFALIGN(avctx->width, 128) +
+ ctx->tile_cols - 1) / ctx->tile_cols, 128);
+ ctx->tile_rows =
+ (max_tile_width * FFALIGN(avctx->height, 128) +
+ AV1_MAX_TILE_AREA - 1) / AV1_MAX_TILE_AREA;
+ if (ctx->tile_rows > 1) {
+ av_log(avctx, AV_LOG_DEBUG, "Automatically using %d tile "
+ "rows to fill area.\n", ctx->tile_rows);
+ }
+ }
+ av_assert0(ctx->tile_rows > 0);
+
+ if ((avctx->width + 63) / 64 < ctx->tile_cols ||
+ (avctx->height + 63) / 64 < ctx->tile_rows) {
+ av_log(avctx, AV_LOG_ERROR, "Invalid tile sizing: frame not "
+ "large enough to fit specified tile arrangement.\n");
+ return AVERROR(EINVAL);
+ }
+ if (ctx->tile_cols > AV1_MAX_TILE_COLS ||
+ ctx->tile_rows > AV1_MAX_TILE_ROWS) {
+ av_log(avctx, AV_LOG_ERROR, "Invalid tile sizing: AV1 does "
+ "not allow more than %dx%d tiles.\n",
+ AV1_MAX_TILE_COLS, AV1_MAX_TILE_ROWS);
+ return AVERROR(EINVAL);
+ }
+ if (avctx->width / ctx->tile_cols > AV1_MAX_TILE_WIDTH) {
+ av_log(avctx, AV_LOG_ERROR, "Invalid tile sizing: AV1 does "
+ "not allow tiles of width greater than %d.\n",
+ AV1_MAX_TILE_WIDTH);
+ return AVERROR(EINVAL);
+ }
+
+ ctx->superblock_size = AOM_SUPERBLOCK_SIZE_DYNAMIC;
+
+ if (ctx->tile_cols == 1 && ctx->tile_rows == 1) {
+ av_log(avctx, AV_LOG_DEBUG, "Using a single tile.\n");
+ return 0;
+ }
+
+ sb_128x128_possible =
+ (avctx->width + 127) / 128 >= ctx->tile_cols &&
+ (avctx->height + 127) / 128 >= ctx->tile_rows;
+
+ ctx->tile_cols_log2 = ctx->tile_cols == 1 ? 0 :
+ av_log2(ctx->tile_cols - 1) + 1;
+ ctx->tile_rows_log2 = ctx->tile_rows == 1 ? 0 :
+ av_log2(ctx->tile_rows - 1) + 1;
+
+ uniform_cols = count_uniform_tiling(avctx->width,
+ 64, ctx->tile_cols_log2);
+ uniform_rows = count_uniform_tiling(avctx->height,
+ 64, ctx->tile_rows_log2);
+ av_log(avctx, AV_LOG_DEBUG, "Uniform with 64x64 superblocks "
+ "-> %dx%d tiles.\n", uniform_cols, uniform_rows);
+ uniform_64x64_possible = uniform_cols == ctx->tile_cols &&
+ uniform_rows == ctx->tile_rows;
+
+ if (sb_128x128_possible) {
+ uniform_cols = count_uniform_tiling(avctx->width,
+ 128, ctx->tile_cols_log2);
+ uniform_rows = count_uniform_tiling(avctx->height,
+ 128, ctx->tile_rows_log2);
+ av_log(avctx, AV_LOG_DEBUG, "Uniform with 128x128 superblocks "
+ "-> %dx%d tiles.\n", uniform_cols, uniform_rows);
+ uniform_128x128_possible = uniform_cols == ctx->tile_cols &&
+ uniform_rows == ctx->tile_rows;
+ } else {
+ av_log(avctx, AV_LOG_DEBUG, "128x128 superblocks not possible.\n");
+ uniform_128x128_possible = 0;
+ }
+
+ ctx->uniform_tiles = 1;
+ if (uniform_64x64_possible && uniform_128x128_possible) {
+ av_log(avctx, AV_LOG_DEBUG, "Using uniform tiling with dynamic "
+ "superblocks (tile_cols_log2 = %d, tile_rows_log2 = %d).\n",
+ ctx->tile_cols_log2, ctx->tile_rows_log2);
+ return 0;
+ }
+ if (uniform_64x64_possible && !sb_128x128_possible) {
+ av_log(avctx, AV_LOG_DEBUG, "Using uniform tiling with 64x64 "
+ "superblocks (tile_cols_log2 = %d, tile_rows_log2 = %d).\n",
+ ctx->tile_cols_log2, ctx->tile_rows_log2);
+ ctx->superblock_size = AOM_SUPERBLOCK_SIZE_64X64;
+ return 0;
+ }
+ if (uniform_128x128_possible) {
+ av_log(avctx, AV_LOG_DEBUG, "Using uniform tiling with 128x128 "
+ "superblocks (tile_cols_log2 = %d, tile_rows_log2 = %d).\n",
+ ctx->tile_cols_log2, ctx->tile_rows_log2);
+ ctx->superblock_size = AOM_SUPERBLOCK_SIZE_128X128;
+ return 0;
+ }
+ ctx->uniform_tiles = 0;
+
+ if (sb_128x128_possible) {
+ sb_size = 128;
+ ctx->superblock_size = AOM_SUPERBLOCK_SIZE_128X128;
+ } else {
+ sb_size = 64;
+ ctx->superblock_size = AOM_SUPERBLOCK_SIZE_64X64;
+ }
+ av_log(avctx, AV_LOG_DEBUG, "Using fixed tiling with %dx%d "
+ "superblocks (tile_cols = %d, tile_rows = %d).\n",
+ sb_size, sb_size, ctx->tile_cols, ctx->tile_rows);
+
+ enccfg->tile_width_count = ctx->tile_cols;
+ enccfg->tile_height_count = ctx->tile_rows;
+
+ sb_width = (avctx->width + sb_size - 1) / sb_size;
+ sb_height = (avctx->height + sb_size - 1) / sb_size;
+
+ tile_size = sb_width / ctx->tile_cols;
+ rounding = sb_width % ctx->tile_cols;
+ for (i = 0; i < ctx->tile_cols; i++) {
+ enccfg->tile_widths[i] = tile_size +
+ (i < rounding / 2 ||
+ i > ctx->tile_cols - 1 - (rounding + 1) / 2);
+ }
+
+ tile_size = sb_height / ctx->tile_rows;
+ rounding = sb_height % ctx->tile_rows;
+ for (i = 0; i < ctx->tile_rows; i++) {
+ enccfg->tile_heights[i] = tile_size +
+ (i < rounding / 2 ||
+ i > ctx->tile_rows - 1 - (rounding + 1) / 2);
+ }
+
+ return 0;
+}
+
static av_cold int aom_init(AVCodecContext *avctx,
const struct aom_codec_iface *iface)
{
AOMContext *ctx = avctx->priv_data;
struct aom_codec_enc_cfg enccfg = { 0 };
+#ifdef AOM_FRAME_IS_INTRAONLY
+ aom_codec_flags_t flags =
+ (avctx->flags & AV_CODEC_FLAG_PSNR) ? AOM_CODEC_USE_PSNR : 0;
+#else
aom_codec_flags_t flags = 0;
+#endif
AVCPBProperties *cpb_props;
int res;
aom_img_fmt_t img_fmt;
enccfg.g_h = avctx->height;
enccfg.g_timebase.num = avctx->time_base.num;
enccfg.g_timebase.den = avctx->time_base.den;
- enccfg.g_threads = avctx->thread_count;
+ enccfg.g_threads =
+ FFMIN(avctx->thread_count ? avctx->thread_count : av_cpu_count(), 64);
if (ctx->lag_in_frames >= 0)
enccfg.g_lag_in_frames = ctx->lag_in_frames;
enccfg.g_error_resilient = ctx->error_resilient;
+ res = choose_tiling(avctx, &enccfg);
+ if (res < 0)
+ return res;
+
dump_enc_cfg(avctx, &enccfg);
/* Construct Encoder Context */
res = aom_codec_enc_init(&ctx->encoder, iface, &enccfg, flags);
codecctl_int(avctx, AV1E_SET_TRANSFER_CHARACTERISTICS, avctx->color_trc);
set_color_range(avctx);
+ codecctl_int(avctx, AV1E_SET_SUPERBLOCK_SIZE, ctx->superblock_size);
+ if (ctx->uniform_tiles) {
+ codecctl_int(avctx, AV1E_SET_TILE_COLUMNS, ctx->tile_cols_log2);
+ codecctl_int(avctx, AV1E_SET_TILE_ROWS, ctx->tile_rows_log2);
+ }
+
+#ifdef AOM_CTRL_AV1E_SET_ROW_MT
+ codecctl_int(avctx, AV1E_SET_ROW_MT, ctx->row_mt);
+#endif
+
// provide dummy value to initialize wrapper, values will be updated each _encode()
aom_img_wrap(&ctx->rawimg, img_fmt, avctx->width, avctx->height, 1,
(unsigned char*)1);
if (!cpb_props)
return AVERROR(ENOMEM);
+ if (avctx->flags & AV_CODEC_FLAG_GLOBAL_HEADER) {
+ const AVBitStreamFilter *filter = av_bsf_get_by_name("extract_extradata");
+ int ret;
+
+ if (!filter) {
+ av_log(avctx, AV_LOG_ERROR, "extract_extradata bitstream filter "
+ "not found. This is a bug, please report it.\n");
+ return AVERROR_BUG;
+ }
+ ret = av_bsf_alloc(filter, &ctx->bsf);
+ if (ret < 0)
+ return ret;
+
+ ret = avcodec_parameters_from_context(ctx->bsf->par_in, avctx);
+ if (ret < 0)
+ return ret;
+
+ ret = av_bsf_init(ctx->bsf);
+ if (ret < 0)
+ return ret;
+ }
+
if (enccfg.rc_end_usage == AOM_CBR ||
enccfg.g_pass != AOM_RC_ONE_PASS) {
cpb_props->max_bitrate = avctx->rc_max_rate;
return 0;
}
-static inline void cx_pktcpy(struct FrameListData *dst,
+static inline void cx_pktcpy(AOMContext *ctx,
+ struct FrameListData *dst,
const struct aom_codec_cx_pkt *src)
{
dst->pts = src->data.frame.pts;
dst->flags = src->data.frame.flags;
dst->sz = src->data.frame.sz;
dst->buf = src->data.frame.buf;
+#ifdef AOM_FRAME_IS_INTRAONLY
+ dst->have_sse = 0;
+ dst->frame_number = ++ctx->frame_number;
+ dst->have_sse = ctx->have_sse;
+ if (ctx->have_sse) {
+ /* associate last-seen SSE to the frame. */
+ /* Transfers ownership from ctx to dst. */
+ memcpy(dst->sse, ctx->sse, sizeof(dst->sse));
+ ctx->have_sse = 0;
+ }
+#endif
}
/**
static int storeframe(AVCodecContext *avctx, struct FrameListData *cx_frame,
AVPacket *pkt)
{
+ AOMContext *ctx = avctx->priv_data;
+ int pict_type;
int ret = ff_alloc_packet2(avctx, pkt, cx_frame->sz, 0);
if (ret < 0) {
av_log(avctx, AV_LOG_ERROR,
memcpy(pkt->data, cx_frame->buf, pkt->size);
pkt->pts = pkt->dts = cx_frame->pts;
- if (!!(cx_frame->flags & AOM_FRAME_IS_KEY))
+ if (!!(cx_frame->flags & AOM_FRAME_IS_KEY)) {
pkt->flags |= AV_PKT_FLAG_KEY;
+#ifdef AOM_FRAME_IS_INTRAONLY
+ pict_type = AV_PICTURE_TYPE_I;
+ } else if (cx_frame->flags & AOM_FRAME_IS_INTRAONLY) {
+ pict_type = AV_PICTURE_TYPE_I;
+ } else {
+ pict_type = AV_PICTURE_TYPE_P;
+ }
+
+ ff_side_data_set_encoder_stats(pkt, 0, cx_frame->sse + 1,
+ cx_frame->have_sse ? 3 : 0, pict_type);
+
+ if (cx_frame->have_sse) {
+ int i;
+ for (i = 0; i < 3; ++i) {
+ avctx->error[i] += cx_frame->sse[i + 1];
+ }
+ cx_frame->have_sse = 0;
+#endif
+ }
+
+ if (avctx->flags & AV_CODEC_FLAG_GLOBAL_HEADER) {
+ ret = av_bsf_send_packet(ctx->bsf, pkt);
+ if (ret < 0) {
+ av_log(avctx, AV_LOG_ERROR, "extract_extradata filter "
+ "failed to send input packet\n");
+ return ret;
+ }
+ ret = av_bsf_receive_packet(ctx->bsf, pkt);
+
+ if (ret < 0) {
+ av_log(avctx, AV_LOG_ERROR, "extract_extradata filter "
+ "failed to receive output packet\n");
+ return ret;
+ }
+ }
return pkt->size;
}
/* avoid storing the frame when the list is empty and we haven't yet
* provided a frame for output */
av_assert0(!ctx->coded_frame_list);
- cx_pktcpy(&cx_frame, pkt);
+ cx_pktcpy(ctx, &cx_frame, pkt);
size = storeframe(avctx, &cx_frame, pkt_out);
if (size < 0)
return size;
"Frame queue element alloc failed\n");
return AVERROR(ENOMEM);
}
- cx_pktcpy(cx_frame, pkt);
+ cx_pktcpy(ctx, cx_frame, pkt);
cx_frame->buf = av_malloc(cx_frame->sz);
if (!cx_frame->buf) {
stats->sz += pkt->data.twopass_stats.sz;
break;
}
- case AOM_CODEC_PSNR_PKT: // FIXME add support for AV_CODEC_FLAG_PSNR
+#ifdef AOM_FRAME_IS_INTRAONLY
+ case AOM_CODEC_PSNR_PKT:
+ {
+ av_assert0(!ctx->have_sse);
+ ctx->sse[0] = pkt->data.psnr.sse[0];
+ ctx->sse[1] = pkt->data.psnr.sse[1];
+ ctx->sse[2] = pkt->data.psnr.sse[2];
+ ctx->sse[3] = pkt->data.psnr.sse[3];
+ ctx->have_sse = 1;
+ break;
+ }
+#endif
case AOM_CODEC_CUSTOM_PKT:
// ignore unsupported/unrecognized packet types
break;
#define OFFSET(x) offsetof(AOMContext, x)
#define VE AV_OPT_FLAG_VIDEO_PARAM | AV_OPT_FLAG_ENCODING_PARAM
static const AVOption options[] = {
- { "cpu-used", "Quality/Speed ratio modifier", OFFSET(cpu_used), AV_OPT_TYPE_INT, {.i64 = 1}, -8, 8, VE},
+ { "cpu-used", "Quality/Speed ratio modifier", OFFSET(cpu_used), AV_OPT_TYPE_INT, {.i64 = 1}, 0, 8, VE},
{ "auto-alt-ref", "Enable use of alternate reference "
"frames (2-pass only)", OFFSET(auto_alt_ref), AV_OPT_TYPE_INT, {.i64 = -1}, -1, 2, VE},
{ "lag-in-frames", "Number of frames to look ahead at for "
"alternate reference frame selection", OFFSET(lag_in_frames), AV_OPT_TYPE_INT, {.i64 = -1}, -1, INT_MAX, VE},
{ "error-resilience", "Error resilience configuration", OFFSET(error_resilient), AV_OPT_TYPE_FLAGS, {.i64 = 0}, INT_MIN, INT_MAX, VE, "er"},
{ "default", "Improve resiliency against losses of whole frames", 0, AV_OPT_TYPE_CONST, {.i64 = AOM_ERROR_RESILIENT_DEFAULT}, 0, 0, VE, "er"},
- { "partitions", "The frame partitions are independently decodable "
- "by the bool decoder, meaning that partitions can be decoded even "
- "though earlier partitions have been lost. Note that intra predicition"
- " is still done over the partition boundary.", 0, AV_OPT_TYPE_CONST, {.i64 = AOM_ERROR_RESILIENT_PARTITIONS}, 0, 0, VE, "er"},
{ "crf", "Select the quality for constant quality mode", offsetof(AOMContext, crf), AV_OPT_TYPE_INT, {.i64 = -1}, -1, 63, VE },
{ "static-thresh", "A change threshold on blocks below which they will be skipped by the encoder", OFFSET(static_thresh), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, INT_MAX, VE },
{ "drop-threshold", "Frame drop threshold", offsetof(AOMContext, drop_threshold), AV_OPT_TYPE_INT, {.i64 = 0 }, INT_MIN, INT_MAX, VE },
- { "noise-sensitivity", "Noise sensitivity", OFFSET(noise_sensitivity), AV_OPT_TYPE_INT, {.i64 = 0 }, 0, 4, VE},
+ { "tiles", "Tile columns x rows", OFFSET(tile_cols), AV_OPT_TYPE_IMAGE_SIZE, { .str = NULL }, 0, 0, VE },
+ { "tile-columns", "Log2 of number of tile columns to use", OFFSET(tile_cols_log2), AV_OPT_TYPE_INT, {.i64 = -1}, -1, 6, VE},
+ { "tile-rows", "Log2 of number of tile rows to use", OFFSET(tile_rows_log2), AV_OPT_TYPE_INT, {.i64 = -1}, -1, 6, VE},
+ { "row-mt", "Enable row based multi-threading", OFFSET(row_mt), AV_OPT_TYPE_BOOL, {.i64 = 0}, 0, 1, VE},
{ NULL }
};
static const AVCodecDefault defaults[] = {
+ { "b", "256*1000" },
{ "qmin", "-1" },
{ "qmax", "-1" },
{ "g", "-1" },