现在使用 CPU_CLK_UNHALTED 事件来评测同一个应用程序（可执行文件），这个事件基本上就是收集无停顿地运行的CPU周期数的采样。
Now, profile the same application (executable) with the event CPU_CLK_UNHALTED, which basically collects samples on the number of cycles the CPU runs without halting.
如果在用户界面周期内分配对象，就会强制一个周期性的垃圾回收，给用户体验增加小小的停顿间隙。
If you allocate objects in a user interface loop, you will force a periodic garbage collection, creating little "hiccups" in the user experience.
两个脉冲周期之间的停顿时间，称为循环间隔。
Pause time between the two pulse cycles is call as cycle interval.
在第2代收集时，用更多CPU周期和堆内存来换取更短的用户界面停顿时间。
This is done by trading a little bit more CPU cycles and heap memory usage for shorter UI pause time when doing gen 2 collections.
在第2代收集时，用更多CPU周期和堆内存来换取更短的用户界面停顿时间。
This is done by trading a little bit more CPU cycles and heap memory usage for shorter UI pause time when doing gen 2 collections.
应用推荐