Edit Mesh: multi-thread auto-smooth & custom normal calculations

Supported multi-threading for bm_mesh_loops_calc_normals.

This is done by operating on vertex-loops instead of face-loops.

Single threaded operation still loops over faces since iterating
over vertices adds some overhead in the case of custom-normals
as the order used for accessing loops must be the same as iterating
of a faces loops.

From isolated timing tests of bm_mesh_loops_calc_normals on high
poly models, this gives between 3.5x to 10x speedup,
with larger gains for meshes with custom-normals.

NOTE: this is part one of two patches for multi-threaded auto-smooth,
tagging edges as sharp is still single threaded.

Reviewed By: mont29

Ref D11928

2 files changed, 36 insertions, 0 deletions

diff --git a/source/blender/blenkernel/BKE_mesh.h b/source/blender/blenkernel/BKE_mesh.h
index 7846619577e..e3be9cd8ef8 100644
--- a/source/blender/blenkernel/BKE_mesh.h
+++ b/source/blender/blenkernel/BKE_mesh.h
@@ -399,6 +399,12 @@ void BKE_lnor_spacearr_init(MLoopNorSpaceArray *lnors_spacearr,
                             const char data_type);
 void BKE_lnor_spacearr_clear(MLoopNorSpaceArray *lnors_spacearr);
 void BKE_lnor_spacearr_free(MLoopNorSpaceArray *lnors_spacearr);
+
+void BKE_lnor_spacearr_tls_init(MLoopNorSpaceArray *lnors_spacearr,
+                                MLoopNorSpaceArray *lnors_spacearr_tls);
+void BKE_lnor_spacearr_tls_join(MLoopNorSpaceArray *lnors_spacearr,
+                                MLoopNorSpaceArray *lnors_spacearr_tls);
+
 MLoopNorSpace *BKE_lnor_space_create(MLoopNorSpaceArray *lnors_spacearr);
 void BKE_lnor_space_define(MLoopNorSpace *lnor_space,
                            const float lnor[3],
diff --git a/source/blender/blenkernel/intern/mesh_normals.cc b/source/blender/blenkernel/intern/mesh_normals.cc
index 2fe132fc684..f496d6eada1 100644
--- a/source/blender/blenkernel/intern/mesh_normals.cc
+++ b/source/blender/blenkernel/intern/mesh_normals.cc
@@ -530,6 +530,36 @@ void BKE_lnor_spacearr_init(MLoopNorSpaceArray *lnors_spacearr,
   lnors_spacearr->data_type = data_type;
 }
 
+/**
+ * Utility for multi-threaded calculation that ensures
+ * `lnors_spacearr_tls` doesn't share memory with `lnors_spacearr`
+ * that would cause it not to be thread safe.
+ *
+ * \note This works as long as threads never operate on the same loops at once.
+ */
+void BKE_lnor_spacearr_tls_init(MLoopNorSpaceArray *lnors_spacearr,
+                                MLoopNorSpaceArray *lnors_spacearr_tls)
+{
+  *lnors_spacearr_tls = *lnors_spacearr;
+  lnors_spacearr_tls->mem = BLI_memarena_new(BLI_MEMARENA_STD_BUFSIZE, __func__);
+}
+
+/**
+ * Utility for multi-threaded calculation
+ * that merges `lnors_spacearr_tls` into `lnors_spacearr`.
+ */
+void BKE_lnor_spacearr_tls_join(MLoopNorSpaceArray *lnors_spacearr,
+                                MLoopNorSpaceArray *lnors_spacearr_tls)
+{
+  BLI_assert(lnors_spacearr->data_type == lnors_spacearr_tls->data_type);
+  BLI_assert(lnors_spacearr->mem != lnors_spacearr_tls->mem);
+  lnors_spacearr->num_spaces += lnors_spacearr_tls->num_spaces;
+  BLI_memarena_merge(lnors_spacearr->mem, lnors_spacearr_tls->mem);
+  BLI_memarena_free(lnors_spacearr_tls->mem);
+  lnors_spacearr_tls->mem = nullptr;
+  BKE_lnor_spacearr_clear(lnors_spacearr_tls);
+}
+
 void BKE_lnor_spacearr_clear(MLoopNorSpaceArray *lnors_spacearr)
 {
   lnors_spacearr->num_spaces = 0;