Kelsi
80e76aa3e8
Parallelize M2 bone matrix computation across worker threads
...
Split the M2 animation update loop into three phases: sequential animation state update, parallel bone matrix computation via std::async (when 32+ animated instances), and sequential particle update. Each thread processes a disjoint slice of instances so no synchronization is needed.
2026-02-07 14:28:14 -08:00
..
2026-02-06 13:47:03 -08:00
2026-02-03 16:04:21 -08:00
2026-02-02 13:03:22 -08:00
2026-02-06 14:24:38 -08:00
2026-02-06 18:34:45 -08:00
2026-02-02 13:03:22 -08:00
2026-02-02 13:03:22 -08:00
2026-02-02 13:03:22 -08:00
2026-02-02 13:03:22 -08:00
2026-02-06 14:43:18 -08:00
2026-02-07 14:28:14 -08:00
2026-02-02 13:03:22 -08:00
2026-02-02 13:03:22 -08:00
2026-02-04 22:27:45 -08:00
2026-02-04 10:31:03 -08:00
2026-02-07 13:56:58 -08:00
2026-02-02 13:03:22 -08:00
2026-02-04 16:08:35 -08:00
2026-02-02 13:03:22 -08:00
2026-02-02 13:03:22 -08:00
2026-02-02 13:03:22 -08:00
2026-02-06 18:52:28 -08:00
2026-02-04 16:08:35 -08:00
2026-02-04 15:05:46 -08:00
2026-02-05 15:34:29 -08:00
2026-02-03 20:40:59 -08:00
2026-02-02 13:03:22 -08:00
2026-02-05 17:35:17 -08:00
2026-02-04 22:27:45 -08:00