[FFmpeg-devel] [PATCH] lavc/vaapi_encode: Async the encoding and output procedure of encoder

[Linjie Fu]

Currently, vaapi encodes a pic if all its references are ready,
and then outputs it immediately by calling vaapi_encode_output.

However, while working on output procedure, hardware is be able to
cope with encoding tasks in the meantime to have the better performance.

So a more efficient way is to send all the pics with available refs to
hardware to allow encoding while output.

It's what vaapi originally did before the regression, and the performance
could be improved for ~20%.

CMD:
ffmpeg -hwaccel vaapi -vaapi_device /dev/dri/renderD128
-hwaccel_output_format vaapi -i bbb_sunflower_1080p_30fps_normal.mp4
-c:v h264_vaapi -f h264 -y /dev/null

Source:
https://download.blender.org/demo/movies/BBB/

Before:
    ~164 fps
After:
    ~198 fps

Fix #7706.

Signed-off-by: Linjie Fu <linjie.fu at intel.com>
---
 libavcodec/vaapi_encode.c | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/libavcodec/vaapi_encode.c b/libavcodec/vaapi_encode.c
index 3be9159d37..aceb268315 100644
--- a/libavcodec/vaapi_encode.c
+++ b/libavcodec/vaapi_encode.c
@@ -1109,17 +1109,28 @@ int ff_vaapi_encode_receive_packet(AVCodecContext *avctx, AVPacket *pkt)
             return AVERROR(EAGAIN);
     }
 
+pick_next:
     pic = NULL;
     err = vaapi_encode_pick_next(avctx, &pic);
-    if (err < 0)
-        return err;
-    av_assert0(pic);
+    if (!err) {
+        av_assert0(pic);
 
-    pic->encode_order = ctx->encode_order++;
+        pic->encode_order = ctx->encode_order++;
 
-    err = vaapi_encode_issue(avctx, pic);
-    if (err < 0) {
-        av_log(avctx, AV_LOG_ERROR, "Encode failed: %d.\n", err);
+        err = vaapi_encode_issue(avctx, pic);
+        if (err < 0) {
+            av_log(avctx, AV_LOG_ERROR, "Encode failed: %d.\n", err);
+            return err;
+        }
+        goto pick_next;
+    } else if (err == AVERROR(EAGAIN)) {
+        for (pic = ctx->pic_start; pic; pic = pic->next)
+            if (pic->encode_issued && !pic->encode_complete &&
+                pic->encode_order == ctx->output_order)
+                break;
+        if (!pic)
+            return err;
+    } else {
         return err;
     }
 
@@ -1143,7 +1154,7 @@ int ff_vaapi_encode_receive_packet(AVCodecContext *avctx, AVPacket *pkt)
     av_log(avctx, AV_LOG_DEBUG, "Output packet: pts %"PRId64" dts %"PRId64".\n",
            pkt->pts, pkt->dts);
 
-    ctx->output_order = pic->encode_order;
+    ctx->output_order++;
     vaapi_encode_clear_old(avctx);
 
     return 0;
-- 
2.17.1