avcodec/v210dec: add support for frame and slice threading

1, Test server configure:
[root@localhost ~]# cat /proc/cpuinfo  |grep "model name"
 model name      : Intel(R) Xeon(R) CPU E5-2650 v2 @ 2.60GHz
 model name      : Intel(R) Xeon(R) CPU E5-2650 v2 @ 2.60GHz
 ...

[root@localhost ~]# free -h
              total        used        free      shared  buff/cache   available
              Mem:           102G        1.1G        100G         16M        657M        100G
              Swap:          4.0G          0B        4.0G

2, Test result:
encode the v210 input data for testing:
./ffmpeg -y -i 4k_422.ts  -c:v v210 -vframes 10 test.avi

master:
./ffmpeg -y -threads 1 -stream_loop 1000 -i ./test.avi -benchmark -f null -
frame=10010 fps= 60 q=-0.0 Lsize=N/A time=00:38:26.30 bitrate=N/A speed=13.7x
video:5240kB audio:432432kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown
bench: utime=101.869s stime=66.181s rtime=167.996s
bench: maxrss=186552kB

patch applied:
./ffmpeg -y -threads 2 -thread_type slice -stream_loop 1000 -i ./test.avi -benchmark -f null -
frame=10010 fps= 72 q=-0.0 Lsize=N/A time=00:38:26.30 bitrate=N/A speed=16.5x
video:5240kB audio:432432kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown
bench: utime=103.562s stime=74.858s rtime=139.599s
bench: maxrss=188616kB

./ffmpeg -y -threads 2 -thread_type frame -stream_loop 1000 -i ./test.avi -benchmark -f null -
frame=10010 fps= 85 q=-0.0 Lsize=N/A time=00:38:26.30 bitrate=N/A speed=19.6x
video:5240kB audio:432432kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown
bench: utime=114.310s stime=92.685s rtime=117.693s
bench: maxrss=231896kB

Signed-off-by: Limin Wang <lance.lmwang@gmail.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>

1 files changed, 78 insertions, 48 deletions

diff --git a/libavcodec/v210dec.c b/libavcodec/v210dec.c
index 5a33d8c089..8483023815 100644
--- 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;
@@ -64,21 +71,81 @@ static av_cold int decode_init(AVCodecContext *avctx)
     avctx->pix_fmt             = AV_PIX_FMT_YUV422P10;
     avctx->bits_per_raw_sample = 10;
 
+    s->thread_count  = av_clip(avctx->thread_count, 1, avctx->height/4);
     s->aligned_input = 0;
     ff_v210dec_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;
+}
+
 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;
@@ -86,6 +153,7 @@ static int decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
         int aligned_width = ((avctx->width + 47) / 48) * 48;
         stride = aligned_width * 8 / 3;
     }
+    td.stride = stride;
 
     if (avpkt->size < stride * avctx->height) {
         if ((((avctx->width + 23) / 24) * 24 * 8) / 3 * avctx->height == avpkt->size) {
@@ -110,55 +178,15 @@ static int decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
         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 / 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 += 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 */
@@ -194,6 +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,
 };