OpenSubDiv: add support for an OpenGL evaluator

This evaluator is used in order to evaluate subdivision at render time, allowing for
faster renders of meshes with a subdivision surface modifier placed at the last
position in the modifier list.

When evaluating the subsurf modifier, we detect whether we can delegate evaluation
to the draw code. If so, the subdivision is first evaluated on the GPU using our own
custom evaluator (only the coarse data needs to be initially sent to the GPU), then,
buffers for the final `MeshBufferCache` are filled on the GPU using a set of
compute shaders. However, some buffers are still filled on the CPU side, if doing so
on the GPU is impractical (e.g. the line adjacency buffer used for x-ray, whose
logic is hardly GPU compatible).

This is done at the mesh buffer extraction level so that the result can be readily used
in the various OpenGL engines, without having to write custom geometry or tesselation
shaders.

We use our own subdivision evaluation shaders, instead of OpenSubDiv's vanilla one, in
order to control the data layout, and interpolation. For example, we store vertex colors
as compressed 16-bit integers, while OpenSubDiv's default evaluator only work for float
types.

In order to still access the modified geometry on the CPU side, for use in modifiers
or transform operators, a dedicated wrapper type is added `MESH_WRAPPER_TYPE_SUBD`.
Subdivision will be lazily evaluated via `BKE_object_get_evaluated_mesh` which will
create such a wrapper if possible. If the final subdivision surface is not needed on
the CPU side, `BKE_object_get_evaluated_mesh_no_subsurf` should be used.

Enabling or disabling GPU subdivision can be done through the user preferences (under
Viewport -> Subdivision).

See patch description for benchmarks.

Reviewed By: campbellbarton, jbakker, fclem, brecht, #eevee_viewport

Differential Revision: https://developer.blender.org/D12406

1 files changed, 30 insertions, 0 deletions

diff --git a/source/blender/draw/intern/draw_cache_impl_mesh.c b/source/blender/draw/intern/draw_cache_impl_mesh.c
index 82b3b5aee41..1e5ffc14911 100644
--- a/source/blender/draw/intern/draw_cache_impl_mesh.c
+++ b/source/blender/draw/intern/draw_cache_impl_mesh.c
@@ -54,6 +54,7 @@
 #include "BKE_object_deform.h"
 #include "BKE_paint.h"
 #include "BKE_pbvh.h"
+#include "BKE_subdiv_modifier.h"
 
 #include "atomic_ops.h"
 
@@ -69,6 +70,7 @@
 
 #include "draw_cache_extract.h"
 #include "draw_cache_inline.h"
+#include "draw_subdivision.h"
 
 #include "draw_cache_impl.h" /* own include */
 
@@ -380,6 +382,7 @@ static void drw_mesh_attributes_add_request(DRW_MeshAttributes *attrs,
 BLI_INLINE const CustomData *mesh_cd_ldata_get_from_mesh(const Mesh *me)
 {
   switch ((eMeshWrapperType)me->runtime.wrapper_type) {
+    case ME_WRAPPER_TYPE_SUBD:
     case ME_WRAPPER_TYPE_MDATA:
       return &me->ldata;
       break;
@@ -395,6 +398,7 @@ BLI_INLINE const CustomData *mesh_cd_ldata_get_from_mesh(const Mesh *me)
 BLI_INLINE const CustomData *mesh_cd_pdata_get_from_mesh(const Mesh *me)
 {
   switch ((eMeshWrapperType)me->runtime.wrapper_type) {
+    case ME_WRAPPER_TYPE_SUBD:
     case ME_WRAPPER_TYPE_MDATA:
       return &me->pdata;
       break;
@@ -410,6 +414,7 @@ BLI_INLINE const CustomData *mesh_cd_pdata_get_from_mesh(const Mesh *me)
 BLI_INLINE const CustomData *mesh_cd_edata_get_from_mesh(const Mesh *me)
 {
   switch ((eMeshWrapperType)me->runtime.wrapper_type) {
+    case ME_WRAPPER_TYPE_SUBD:
     case ME_WRAPPER_TYPE_MDATA:
       return &me->edata;
       break;
@@ -425,6 +430,7 @@ BLI_INLINE const CustomData *mesh_cd_edata_get_from_mesh(const Mesh *me)
 BLI_INLINE const CustomData *mesh_cd_vdata_get_from_mesh(const Mesh *me)
 {
   switch ((eMeshWrapperType)me->runtime.wrapper_type) {
+    case ME_WRAPPER_TYPE_SUBD:
     case ME_WRAPPER_TYPE_MDATA:
       return &me->vdata;
       break;
@@ -1037,6 +1043,15 @@ static void mesh_buffer_cache_clear(MeshBufferCache *mbc)
   mbc->poly_sorted.visible_tri_len = 0;
 }
 
+static void mesh_batch_cache_free_subdiv_cache(MeshBatchCache *cache)
+{
+  if (cache->subdiv_cache) {
+    draw_subdiv_cache_free(cache->subdiv_cache);
+    MEM_freeN(cache->subdiv_cache);
+    cache->subdiv_cache = NULL;
+  }
+}
+
 static void mesh_batch_cache_clear(Mesh *me)
 {
   MeshBatchCache *cache = me->runtime.batch_cache;
@@ -1064,6 +1079,8 @@ static void mesh_batch_cache_clear(Mesh *me)
 
   cache->batch_ready = 0;
   drw_mesh_weight_state_clear(&cache->weight_state);
+
+  mesh_batch_cache_free_subdiv_cache(cache);
 }
 
 void DRW_mesh_batch_cache_free(Mesh *me)
@@ -1693,6 +1710,10 @@ void DRW_mesh_batch_cache_create_requested(struct TaskGraph *task_graph,
 
   const bool do_uvcage = is_editmode && !me->edit_mesh->mesh_eval_final->runtime.is_original;
 
+  const int required_mode = BKE_subsurf_modifier_eval_required_mode(DRW_state_is_scene_render(),
+                                                                    is_editmode);
+  const bool do_subdivision = BKE_subsurf_modifier_can_do_gpu_subdiv(scene, ob, required_mode);
+
   MeshBufferList *mbuflist = &cache->final.buff;
 
   /* Initialize batches and request VBO's & IBO's. */
@@ -2038,6 +2059,15 @@ void DRW_mesh_batch_cache_create_requested(struct TaskGraph *task_graph,
                                        true);
   }
 
+  if (do_subdivision) {
+    DRW_create_subdivision(scene, ob, me, cache, &cache->final, ts);
+  }
+  else {
+    /* The subsurf modifier may have been recently removed, or another modifier was added after it,
+     * so free any potential subdivision cache as it is not needed anymore. */
+    mesh_batch_cache_free_subdiv_cache(cache);
+  }
+
   mesh_buffer_cache_create_requested(task_graph,
                                      cache,
                                      &cache->final,