|
largewc 发表于 2013-10-18 10:36
其实也就是a7对流处理有大量优化,对于逻辑部分加成有限。
错,对逻辑部分是大大的加成
If you pull this function out of Bullet and bench it separately, you do see a 2x speed increase.
The result seems to be that if the soft bodies are arranged in memory so that the CPU can access them in a sequential fashion, you get a 2x to 3x increase in speed |
|