[FFmpeg-devel] [PATCH V4 3/4] libavcodec/qsvenc: Add low latency P-pyramid support to qsv

[Wenbin Chen]

Add low latency P-pyramid support to qsv. This feature relates to
command line option "-p_strategy". To enable this flag, user also
need to set "-bf" to 0. P-strategy has two modes "1-simple" and
"2-pyramid". The details of the two models refer to
https://github.com/Intel-Media-SDK/MediaSDK/blob/master/doc/mediasdk-man.md#preftype

Signed-off-by: Wenbin Chen <wenbin.chen at intel.com>
---
 doc/encoders.texi   |  6 ++++++
 libavcodec/qsvenc.c | 36 ++++++++++++++++++++++++++++++++++++
 libavcodec/qsvenc.h |  3 +++
 3 files changed, 45 insertions(+)

diff --git a/doc/encoders.texi b/doc/encoders.texi
index 6fc94daa11..3d7c944fba 100644
--- a/doc/encoders.texi
+++ b/doc/encoders.texi
@@ -3296,6 +3296,9 @@ to allow changing of frame type from P and B to I.
 @item @var{adaptive_b}
 This flag controls changing of frame type from B to P.
 
+ at item @var{p_strategy}
+Enable P-pyramid: 0-default 1-simple 2-pyramid(bf need to be set to 0).
+
 @item @var{b_strategy}
 This option controls usage of B frames as reference.
 
@@ -3394,6 +3397,9 @@ Enable rate distortion optimization.
 @item @var{max_frame_size}
 Maximum encoded frame size in bytes.
 
+ at item @var{p_strategy}
+Enable P-pyramid: 0-default 1-simple 2-pyramid(bf need to be set to 0).
+
 @item @var{dblk_idc}
 This option disable deblocking. It has value in range 0~2.
 
diff --git a/libavcodec/qsvenc.c b/libavcodec/qsvenc.c
index e87b69369a..f2ba0241c6 100644
--- a/libavcodec/qsvenc.c
+++ b/libavcodec/qsvenc.c
@@ -315,6 +315,14 @@ static void dump_video_param(AVCodecContext *avctx, QSVEncContext *q,
     case MFX_B_REF_PYRAMID: av_log(avctx, AV_LOG_VERBOSE, "pyramid");   break;
     default:                av_log(avctx, AV_LOG_VERBOSE, "auto");      break;
     }
+
+    av_log(avctx, AV_LOG_VERBOSE, "; PRefType: ");
+    switch (co3->PRefType) {
+    case MFX_P_REF_DEFAULT: av_log(avctx, AV_LOG_VERBOSE, "default");   break;
+    case MFX_P_REF_SIMPLE:  av_log(avctx, AV_LOG_VERBOSE, "simple");    break;
+    case MFX_P_REF_PYRAMID: av_log(avctx, AV_LOG_VERBOSE, "pyramid");   break;
+    default:                av_log(avctx, AV_LOG_VERBOSE, "unknown");   break;
+    }
     av_log(avctx, AV_LOG_VERBOSE, "\n");
 #endif
 
@@ -934,6 +942,34 @@ static int init_video_param(AVCodecContext *avctx, QSVEncContext *q)
 #if QSV_HAVE_CO3
         q->extco3.Header.BufferId      = MFX_EXTBUFF_CODING_OPTION3;
         q->extco3.Header.BufferSz      = sizeof(q->extco3);
+
+        if (avctx->codec_id == AV_CODEC_ID_HEVC ||
+            avctx->codec_id == AV_CODEC_ID_H264) {
+#if QSV_HAVE_PREF
+            switch (q->p_strategy) {
+            case 0:
+                q->extco3.PRefType = MFX_P_REF_DEFAULT;
+                break;
+            case 1:
+                q->extco3.PRefType = MFX_P_REF_SIMPLE;
+                break;
+            case 2:
+                q->extco3.PRefType = MFX_P_REF_PYRAMID;
+                break;
+            default:
+                q->extco3.PRefType = MFX_P_REF_DEFAULT;
+                av_log(avctx, AV_LOG_WARNING,
+                       "invalid p_strategy, set to default\n");
+                break;
+            }
+            if (q->extco3.PRefType == MFX_P_REF_PYRAMID &&
+                avctx->max_b_frames != 0) {
+                av_log(avctx, AV_LOG_WARNING,
+                       "Please set max_b_frames(-bf) to 0 to enable P-pyramid\n");
+            }
+#endif
+        }
+
 #if QSV_HAVE_GPB
         if (avctx->codec_id == AV_CODEC_ID_HEVC)
             q->extco3.GPB              = q->gpb ? MFX_CODINGOPTION_ON : MFX_CODINGOPTION_OFF;
diff --git a/libavcodec/qsvenc.h b/libavcodec/qsvenc.h
index aa49b35f07..960604cb9a 100644
--- a/libavcodec/qsvenc.h
+++ b/libavcodec/qsvenc.h
@@ -51,6 +51,7 @@
 #define QSV_HAVE_LA_DS  QSV_VERSION_ATLEAST(1, 8)
 #define QSV_HAVE_LA_HRD QSV_VERSION_ATLEAST(1, 11)
 #define QSV_HAVE_VDENC  QSV_VERSION_ATLEAST(1, 15)
+#define QSV_HAVE_PREF   QSV_VERSION_ATLEAST(1, 16)
 
 #define QSV_HAVE_GPB    QSV_VERSION_ATLEAST(1, 18)
 
@@ -95,6 +96,7 @@
 { "extbrc",         "Extended bitrate control",               OFFSET(qsv.extbrc),         AV_OPT_TYPE_INT, { .i64 = -1 }, -1,          1, VE },                         \
 { "adaptive_i",     "Adaptive I-frame placement",             OFFSET(qsv.adaptive_i),     AV_OPT_TYPE_INT, { .i64 = -1 }, -1,          1, VE },                         \
 { "adaptive_b",     "Adaptive B-frame placement",             OFFSET(qsv.adaptive_b),     AV_OPT_TYPE_INT, { .i64 = -1 }, -1,          1, VE },                         \
+{ "p_strategy",     "Enable P-pyramid: 0-default 1-simple 2-pyramid(bf need to be set to 0).",    OFFSET(qsv.p_strategy), AV_OPT_TYPE_INT,    { .i64 = 0}, 0,    2, VE },                         \
 { "b_strategy",     "Strategy to choose between I/P/B-frames", OFFSET(qsv.b_strategy),    AV_OPT_TYPE_INT, { .i64 = -1 }, -1,          1, VE },                         \
 { "forced_idr",     "Forcing I frames as IDR frames",         OFFSET(qsv.forced_idr),     AV_OPT_TYPE_BOOL,{ .i64 = 0  },  0,          1, VE },                         \
 { "low_power", "enable low power mode(experimental: many limitations by mfx version, BRC modes, etc.)", OFFSET(qsv.low_power), AV_OPT_TYPE_BOOL, { .i64 = -1}, -1, 1, VE},\
@@ -187,6 +189,7 @@ typedef struct QSVEncContext {
     int adaptive_i;
     int adaptive_b;
     int b_strategy;
+    int p_strategy;
     int cavlc;
 
     int int_ref_type;
-- 
2.25.1