[FFmpeg-devel] [PATCH 3/4] vaapi_encode_h265: Query encoding block sizes and features

[Mark Thompson]

---
Requires <https://github.com/intel/libva/pull/385>.  That isn't upstream, so this will need to wait for that and then get at least a fix to the version numbering before applying.

 libavcodec/vaapi_encode_h265.c | 91 +++++++++++++++++++++++++++-------
 1 file changed, 74 insertions(+), 17 deletions(-)

diff --git a/libavcodec/vaapi_encode_h265.c b/libavcodec/vaapi_encode_h265.c
index dcc22eb610..59d150f503 100644
--- a/libavcodec/vaapi_encode_h265.c
+++ b/libavcodec/vaapi_encode_h265.c
@@ -56,6 +56,7 @@ typedef struct VAAPIEncodeH265Context {
     VAAPIEncodeContext common;
 
     // Encoder features.
+    uint32_t va_features;
     uint32_t ctu_size;
     uint32_t min_cb_size;
 
@@ -440,23 +441,54 @@ static int vaapi_encode_h265_init_sequence_params(AVCodecContext *avctx)
             vps->vps_max_latency_increase_plus1[i];
     }
 
-    // These have to come from the capabilities of the encoder.  We have no
-    // way to query them, so just hardcode parameters which work on the Intel
-    // driver.
-    // CTB size from 8x8 to 32x32.
-    sps->log2_min_luma_coding_block_size_minus3   = 0;
-    sps->log2_diff_max_min_luma_coding_block_size = 2;
-    // Transform size from 4x4 to 32x32.
-    sps->log2_min_luma_transform_block_size_minus2   = 0;
-    sps->log2_diff_max_min_luma_transform_block_size = 3;
-    // Full transform hierarchy allowed (2-5).
-    sps->max_transform_hierarchy_depth_inter = 3;
-    sps->max_transform_hierarchy_depth_intra = 3;
-    // AMP works.
-    sps->amp_enabled_flag = 1;
-    // SAO and temporal MVP do not work.
-    sps->sample_adaptive_offset_enabled_flag = 0;
-    sps->sps_temporal_mvp_enabled_flag       = 0;
+#if VA_CHECK_VERSION(1, 7, 0)
+    if (priv->va_features) {
+        VAConfigAttribValEncHEVCFeatures features = { .value = priv->va_features };
+
+        sps->log2_min_luma_coding_block_size_minus3 =
+            ff_ctz(priv->min_cb_size) - 3;
+        sps->log2_diff_max_min_luma_coding_block_size =
+            ff_ctz(priv->ctu_size) - ff_ctz(priv->min_cb_size);
+
+        sps->log2_min_luma_transform_block_size_minus2 =
+            features.bits.log2_min_luma_transform_block_size_minus2;
+        sps->log2_diff_max_min_luma_transform_block_size =
+            features.bits.log2_max_luma_transform_block_size_minus2 -
+            features.bits.log2_min_luma_transform_block_size_minus2;
+
+        sps->max_transform_hierarchy_depth_inter =
+            features.bits.max_transform_hierarchy_depth_inter;
+        sps->max_transform_hierarchy_depth_intra =
+            features.bits.max_transform_hierarchy_depth_intra;
+
+        sps->amp_enabled_flag =
+            features.bits.amp_supported;
+        sps->sample_adaptive_offset_enabled_flag =
+            features.bits.sao_supported;
+        sps->sps_temporal_mvp_enabled_flag =
+            features.bits.temporal_mvp_supported;
+    } else
+#endif
+    {
+        // These values come from the capabilities of the first encoder
+        // implementation in the i965 driver on Intel Skylake.  They may
+        // fail badly with other platforms or drivers.
+        // CTB size from 8x8 to 32x32.
+        sps->log2_min_luma_coding_block_size_minus3   = 0;
+        sps->log2_diff_max_min_luma_coding_block_size = 2;
+        // Transform size from 4x4 to 32x32.
+        sps->log2_min_luma_transform_block_size_minus2   = 0;
+        sps->log2_diff_max_min_luma_transform_block_size = 3;
+        // Full transform hierarchy allowed (2-5).
+        sps->max_transform_hierarchy_depth_inter = 3;
+        sps->max_transform_hierarchy_depth_intra = 3;
+        // AMP works.
+        sps->amp_enabled_flag = 1;
+        // SAO and temporal MVP do not work.
+        sps->sample_adaptive_offset_enabled_flag = 0;
+        sps->sps_temporal_mvp_enabled_flag       = 0;
+    }
+
 
     sps->pcm_enabled_flag = 0;
 
@@ -1073,6 +1105,31 @@ static av_cold void vaapi_encode_h265_block_size(AVCodecContext *avctx)
     VAAPIEncodeContext      *ctx = avctx->priv_data;
     VAAPIEncodeH265Context *priv = avctx->priv_data;
 
+#if VA_CHECK_VERSION(1, 7, 0)
+    {
+        VAConfigAttrib attr = { VAConfigAttribEncHEVCFeatures };
+        VAConfigAttribValEncHEVCFeatures features;
+        VAStatus vas;
+
+        vas = vaGetConfigAttributes(ctx->hwctx->display, ctx->va_profile,
+                                    ctx->va_entrypoint, &attr, 1);
+        if (vas != VA_STATUS_SUCCESS) {
+            av_log(avctx, AV_LOG_WARNING, "Failed to query encoder "
+                   "features, using guessed defaults.\n");
+        } else if (attr.value == VA_ATTRIB_NOT_SUPPORTED) {
+            av_log(avctx, AV_LOG_WARNING, "Driver does not advertise "
+                   "encoder features, using guessed defaults.\n");
+        } else {
+            features.value = priv->va_features = attr.value;
+
+            priv->ctu_size =
+                1 << features.bits.log2_max_coding_tree_block_size_minus3 + 3;
+            priv->min_cb_size =
+                1 << features.bits.log2_min_luma_coding_block_size_minus3 + 3;
+        }
+    }
+#endif
+
     if (!priv->ctu_size) {
         priv->ctu_size     = 32;
         priv->min_cb_size  = 16;
-- 
2.25.0