Various Exact Boolean parallelizations and optimizations.

From patch D11780 from Erik Abrahamsson.
It parallelizes making the vertices, destruction of map entries,
finding if the result is PWN, finding triangle adjacencies,
and finding the ambient cell.
The latter needs a parallel_reduce from tbb, so added one into
BLI_task.hh so that if WITH_TBB is false, the code will still work.

On Erik's 6-core machine, the elapsed time went from 17.5s to 11.8s
(33% faster) on an intersection of two spheres with 3.1M faces.
On Howard's 24-core machine, the elapsed time went from 18.7s to 10.8s
for the same test.

1 files changed, 22 insertions, 0 deletions

diff --git a/source/blender/blenlib/BLI_task.hh b/source/blender/blenlib/BLI_task.hh
index 5f5a17f6b58..e2446ad143e 100644
--- a/source/blender/blenlib/BLI_task.hh
+++ b/source/blender/blenlib/BLI_task.hh
@@ -28,6 +28,7 @@
 #    define NOMINMAX
 #    define TBB_MIN_MAX_CLEANUP
 #  endif
+#  include "tbb/parallel_reduce.h"
 #  include <tbb/blocked_range.h>
 #  include <tbb/parallel_for.h>
 #  include <tbb/parallel_for_each.h>
@@ -76,6 +77,27 @@ void parallel_for(IndexRange range, int64_t grain_size, const Function &function
 #endif
 }
 
+template<typename Value, typename Function, typename Reduction>
+Value parallel_reduce(IndexRange range,
+                      int64_t grain_size,
+                      const Value &identity,
+                      const Function &function,
+                      const Reduction &reduction)
+{
+#ifdef WITH_TBB
+  return tbb::parallel_reduce(
+      tbb::blocked_range<int64_t>(range.first(), range.one_after_last(), grain_size),
+      identity,
+      [&](const tbb::blocked_range<int64_t> &subrange, const Value &ident) {
+        return function(IndexRange(subrange.begin(), subrange.size()), ident);
+      },
+      reduction);
+#else
+  UNUSED_VARS(grain_size, reduction);
+  return function(range, identity);
+#endif
+}
+
 /** See #BLI_task_isolate for a description of what isolating a task means. */
 template<typename Function> void isolate_task(const Function &function)
 {