Blender Git Loki
Git Commits -> Revision f29e0a3
Revision f29e0a3 by Bastien Montagne (temp_custom_loop_normals) August 17, 2014, 21:13 (GMT) |
Much better handling of multithreading - at least 80% quicker than previous code, more than two times quicker than without any threading... Main idea was to make bigger chunks of tasks (currently, 1024 at once), saves a bunch of mem management (alloc, copy, etc.) and spinlock locking. |
Commit Details:
Full Hash: f29e0a3f6db6e7f275aee118e7a11f4ff04e2160
Parent Commit: 5c880d1
Lines Changed: +89, -64
1 Modified Path:
/source/blender/blenkernel/intern/mesh_evaluate.c (+89, -64) (Diff)