Comparative analysis of periodic state saving techniques in time warp simulators
Comparative analysis of periodic state saving techniques in time warp simulators
复制标题
时间扭曲模拟器中周期状态保存技术的比较分析
DOI：
--
复制
发表时间：
1995
期刊：
影响因子：
--
通讯作者：
P. Wilsey
中科院分区：
文献类型：
--
作者：
Josef Fleischmann;P. Wilsey
在时间扭曲同步并行模拟器中设置检查点是一项必要且可能代价高昂的操作。在简单的情况下，时间扭曲模拟器每隔/spl chi/事件设置检查点，以获取一些触发值/spl chi/。对于较大的/spl chi/值，模拟器保存状态所需的开销较少，但在回滚期间会导致延迟增加。因此，问题是如何在保存状态的时间和回滚时向前滑动的时间之间取得平衡。不幸的是，静态确定/SPL chi/的最佳值是非常困难的，甚至在时间扭曲模拟器的密切相关的实例之间也可能变化很大。此外，在模拟的整个生命周期中，最佳检查点间隔实际上可能会有所不同。为了解决这些问题，一些研究人员建议随着模拟的进行动态调整检查点间隔/SPL chi/。本文分析了以往三种动态调整检查点间隔的技术，并提出了一种新的启发式算法。所有四种技术都在一个共同的应用领域(来自VHDL语言描述的数字系统仿真)中实现，并在算法之间进行直接比较。结果表明，所实现的算法在性能上存在显著差异。然而，在几乎所有情况下，动态算法的性能都接近或好于最佳静态值。此外，最好的算法性能比最好的静态值高出12%。
Checkpointing in a time warp synchronized parallel simulator is a necessary and potentially expensive operation. In the simple case, a time warp simulator checkpoints every /spl chi/ events, for some fired value /spl chi/. For larger values of /spl chi/, the simulator requires less overhead for saving the state, but incurs an increased latency during rollback. Thus, the problem is to balance the time to save states against the time to coast forward upon rollback. Unfortunately, a static determination of an optimal value for /spl chi/ is very difficult and can vary widely, even between closely related instances of a time warp simulator. Furthermore, the optimal checkpoint interval may actually vary over the lifetime of the simulation. To address these problems, several investigators have proposed dynamically adjusting the checkpoint interval /spl chi/ as the simulation progresses. This paper analyzes three previous techniques for dynamically sizing checkpoint intervals and presents a new, heuristic algorithm for this purpose. All four techniques are implemented in a common application domain (digital system simulation from VHDL descriptions) and a direct comparison between the algorithms is performed. The results show a significant difference in the performance of the implemented algorithms. However, in virtually all cases, the dynamic algorithms performed near or better than the best static value. Furthermore, the best algorithms performed as much as 12% better than the best static value.<<ETX>>