avformat/avio: Add Metacube support

[ffmpeg] / libavcodec / v210dec.c

diff --git a/libavcodec/v210dec.c b/libavcodec/v210dec.c
index ddc5dbe8be6c5608b692683939fc4779b6e5ab28..868822e298ca745b48338db485e1ea4c43f3718a 100644 (file)
--- a/libavcodec/v210dec.c
+++ b/libavcodec/v210dec.c
@@ -28,6 +28,7 @@
 #include "libavutil/internal.h"
 #include "libavutil/mem.h"
 #include "libavutil/intreadwrite.h"
+#include "thread.h"
 
 #define READ_PIXELS(a, b, c)         \
     do {                             \
@@ -37,6 +38,12 @@
         *c++ = (val >> 20) & 0x3FF;  \
     } while (0)
 
+typedef struct ThreadData {
+    AVFrame *frame;
+    uint8_t *buf;
+    int stride;
+} ThreadData;
+
 static void v210_planar_unpack_c(const uint32_t *src, uint16_t *y, uint16_t *u, uint16_t *v, int width)
 {
     uint32_t val;
@@ -50,6 +57,13 @@ static void v210_planar_unpack_c(const uint32_t *src, uint16_t *y, uint16_t *u,
     }
 }
 
+av_cold void ff_v210dec_init(V210DecContext *s)
+{
+    s->unpack_frame = v210_planar_unpack_c;
+    if (ARCH_X86)
+        ff_v210_x86_init(s);
+}
+
 static av_cold int decode_init(AVCodecContext *avctx)
 {
     V210DecContext *s = avctx->priv_data;
@@ -57,10 +71,68 @@ static av_cold int decode_init(AVCodecContext *avctx)
     avctx->pix_fmt             = AV_PIX_FMT_YUV422P10;
     avctx->bits_per_raw_sample = 10;
 
-    s->unpack_frame            = v210_planar_unpack_c;
+    s->thread_count  = av_clip(avctx->thread_count, 1, avctx->height/4);
+    s->aligned_input = 0;
+    ff_v210dec_init(s);
 
-    if (HAVE_MMX)
-        ff_v210_x86_init(s);
+    return 0;
+}
+
+static int v210_decode_slice(AVCodecContext *avctx, void *arg, int jobnr, int threadnr)
+{
+    V210DecContext *s = avctx->priv_data;
+    int h, w;
+    ThreadData *td = arg;
+    AVFrame *frame = td->frame;
+    int stride = td->stride;
+    int slice_start = (avctx->height *  jobnr) / s->thread_count;
+    int slice_end = (avctx->height * (jobnr+1)) / s->thread_count;
+    uint8_t *psrc = td->buf + stride * slice_start;
+    uint16_t *y, *u, *v;
+
+    y = (uint16_t*)frame->data[0] + slice_start * frame->linesize[0] / 2;
+    u = (uint16_t*)frame->data[1] + slice_start * frame->linesize[1] / 2;
+    v = (uint16_t*)frame->data[2] + slice_start * frame->linesize[2] / 2;
+    for (h = slice_start; h < slice_end; h++) {
+        const uint32_t *src = (const uint32_t*)psrc;
+        uint32_t val;
+
+        w = (avctx->width / 12) * 12;
+        s->unpack_frame(src, y, u, v, w);
+
+        y += w;
+        u += w >> 1;
+        v += w >> 1;
+        src += (w << 1) / 3;
+
+        if (w < avctx->width - 5) {
+            READ_PIXELS(u, y, v);
+            READ_PIXELS(y, u, y);
+            READ_PIXELS(v, y, u);
+            READ_PIXELS(y, v, y);
+            w += 6;
+        }
+
+        if (w < avctx->width - 1) {
+            READ_PIXELS(u, y, v);
+
+            val  = av_le2ne32(*src++);
+            *y++ =  val & 0x3FF;
+            if (w < avctx->width - 3) {
+                *u++ = (val >> 10) & 0x3FF;
+                *y++ = (val >> 20) & 0x3FF;
+
+                val  = av_le2ne32(*src++);
+                *v++ =  val & 0x3FF;
+                *y++ = (val >> 10) & 0x3FF;
+            }
+        }
+
+        psrc += stride;
+        y += frame->linesize[0] / 2 - avctx->width + (avctx->width & 1);
+        u += frame->linesize[1] / 2 - avctx->width / 2;
+        v += frame->linesize[2] / 2 - avctx->width / 2;
+    }
 
     return 0;
 }
@@ -69,11 +141,11 @@ static int decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
                         AVPacket *avpkt)
 {
     V210DecContext *s = avctx->priv_data;
-
-    int h, w, ret, stride, aligned_input;
+    ThreadData td;
+    int ret, stride, aligned_input;
+    ThreadFrame frame = { .f = data };
     AVFrame *pic = data;
     const uint8_t *psrc = avpkt->data;
-    uint16_t *y, *u, *v;
 
     if (s->custom_stride )
         stride = s->custom_stride;
@@ -93,60 +165,28 @@ static int decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
             return AVERROR_INVALIDDATA;
         }
     }
+    td.stride = stride;
     if (   avctx->codec_tag == MKTAG('C', '2', '1', '0')
         && avpkt->size > 64
         && AV_RN32(psrc) == AV_RN32("INFO")
         && avpkt->size - 64 >= stride * avctx->height)
         psrc += 64;
 
-    aligned_input = !((uintptr_t)psrc & 0xf) && !(stride & 0xf);
+    aligned_input = !((uintptr_t)psrc & 0x1f) && !(stride & 0x1f);
     if (aligned_input != s->aligned_input) {
         s->aligned_input = aligned_input;
-        if (HAVE_MMX)
-            ff_v210_x86_init(s);
+        ff_v210dec_init(s);
     }
 
-    if ((ret = ff_get_buffer(avctx, pic, 0)) < 0)
+    if ((ret = ff_thread_get_buffer(avctx, &frame, 0)) < 0)
         return ret;
 
-    y = (uint16_t*)pic->data[0];
-    u = (uint16_t*)pic->data[1];
-    v = (uint16_t*)pic->data[2];
     pic->pict_type = AV_PICTURE_TYPE_I;
     pic->key_frame = 1;
 
-    for (h = 0; h < avctx->height; h++) {
-        const uint32_t *src = (const uint32_t*)psrc;
-        uint32_t val;
-
-        w = (avctx->width / 6) * 6;
-        s->unpack_frame(src, y, u, v, w);
-
-        y += w;
-        u += w >> 1;
-        v += w >> 1;
-        src += (w << 1) / 3;
-
-        if (w < avctx->width - 1) {
-            READ_PIXELS(u, y, v);
-
-            val  = av_le2ne32(*src++);
-            *y++ =  val & 0x3FF;
-            if (w < avctx->width - 3) {
-                *u++ = (val >> 10) & 0x3FF;
-                *y++ = (val >> 20) & 0x3FF;
-
-                val  = av_le2ne32(*src++);
-                *v++ =  val & 0x3FF;
-                *y++ = (val >> 10) & 0x3FF;
-            }
-        }
-
-        psrc += stride;
-        y += pic->linesize[0] / 2 - avctx->width + (avctx->width & 1);
-        u += pic->linesize[1] / 2 - avctx->width / 2;
-        v += pic->linesize[2] / 2 - avctx->width / 2;
-    }
+    td.buf = (uint8_t*)psrc;
+    td.frame = pic;
+    avctx->execute2(avctx, v210_decode_slice, &td, NULL, s->thread_count);
 
     if (avctx->field_order > AV_FIELD_PROGRESSIVE) {
         /* we have interlaced material flagged in container */
@@ -174,7 +214,7 @@ static const AVClass v210dec_class = {
     .version    = LIBAVUTIL_VERSION_INT,
 };
 
-AVCodec ff_v210_decoder = {
+const AVCodec ff_v210_decoder = {
     .name           = "v210",
     .long_name      = NULL_IF_CONFIG_SMALL("Uncompressed 4:2:2 10-bit"),
     .type           = AVMEDIA_TYPE_VIDEO,
@@ -182,6 +222,8 @@ AVCodec ff_v210_decoder = {
     .priv_data_size = sizeof(V210DecContext),
     .init           = decode_init,
     .decode         = decode_frame,
-    .capabilities   = AV_CODEC_CAP_DR1,
+    .capabilities   = AV_CODEC_CAP_DR1 |
+                      AV_CODEC_CAP_SLICE_THREADS |
+                      AV_CODEC_CAP_FRAME_THREADS,
     .priv_class     = &v210dec_class,
 };