当前位置: X-MOL 学术Future Gener. Comput. Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Evolutionary game for task mapping in resource constrained heterogeneous environments
Future Generation Computer Systems ( IF 6.2 ) Pub Date : 2020-03-16 , DOI: 10.1016/j.future.2020.03.026
Dario Madeo , Somnath Mazumdar , Chiara Mocenni , Roberto Zingone

Power-aware computing is becoming popular using heterogeneous ecosystem. For recent execution units, the heterogeneity is exhibited via the hybrid cores, as well as via virtual and physical asymmetric cores. The inherent performance disparity between different types of execution units at their different clock frequencies offers a great resources scheduling challenge. Multiple metrics (such as throughput, latency, energy cost) are used to decide whether the scheduling is an optimal solution or not. However, in heterogeneous ecosystem, tasks distribution aiming at optimizing costs is not trivial. During the task mapping, one of the primary challenges is to dynamically identify and map the inherent advantages/features of the heterogeneous or hybrid architectures for each individual task. In this work we deal with the task mapping problem using a multi-objective formulation based on evolutionary game theory to optimize a suitable payoff function. This payoff accounts for the power, workload imbalance, task resource affinity and data offloading costs (from host to accelerator). Here, we report that in a very restrictive resource usage scenario (supporting both over and under subscription), the proposed formulation based on Evolutionary Games on Network equation (EGN) can outperform the traditional resource allocation heuristics (such as best-fit, first-fit). Using an extensive set of simulations, we show that our proposed model can outperform first-fit algorithm from more than 5% up to 34.6% and best-fit algorithm from 4% up to 35.7%.



中文翻译:

资源受限的异构环境中用于任务映射的进化游戏

使用异构生态系统的功率感知计算正变得越来越流行。对于最近的执行单元,异质性通过混合核心以及虚拟和物理非对称核心展现出来。不同类型的执行单元在其不同时钟频率之间固有的性能差异为资源调度带来了巨大挑战。多个指标(例如吞吐量,延迟,能源成本)用于确定调度是否是最佳解决方案。但是,在异构生态系统中,旨在优化成本的任务分配并非易事。在任务映射过程中,主要挑战之一是为每个任务动态识别和映射异构或混合体系结构的固有优势/特征。在这项工作中,我们使用基于演化博弈论的多目标公式来处理任务映射问题,以优化合适的收益函数。这种收益解决了功耗,工作负载不平衡,任务资源亲和力和数据卸载成本(从主机到加速器)的问题。在这里,我们报告说,在资源使用非常严格的情况下(支持超额订阅和不足订阅),基于网络演化博弈方程(EGN)的拟议公式可以胜过传统的资源分配试探法(例如最佳拟合,适合)。通过广泛的仿真,我们证明了我们提出的模型的性能优于首次拟合算法(从5%到34.6%)和最佳拟合算法(从4%到35.7%)。这种收益解决了功耗,工作负载不平衡,任务资源亲和力和数据卸载成本(从主机到加速器)的问题。在这里,我们报告说,在资源使用非常严格的情况下(支持超额订阅和不足订阅),基于网络演化博弈方程(EGN)的拟议公式可以胜过传统的资源分配试探法(例如最佳拟合,适合)。通过广泛的仿真,我们证明了我们提出的模型的性能优于首次拟合算法(从5%到34.6%)和最佳拟合算法(从4%到35.7%)。这种收益解决了功耗,工作负载不平衡,任务资源亲和力和数据卸载成本(从主机到加速器)的问题。在这里,我们报告说,在资源使用非常严格的情况下(支持超额订阅和不足订阅),基于网络演化博弈方程(EGN)的拟议公式可以胜过传统的资源分配试探法(例如最佳拟合,适合)。通过广泛的仿真,我们证明了我们提出的模型的性能优于首次拟合算法(从5%到34.6%)和最佳拟合算法(从4%到35.7%)。基于网络方程进化博弈(EGN)的拟议公式可以优于传统的资源分配启发法(例如最佳拟合,优先拟合)。通过广泛的仿真,我们证明了我们提出的模型的性能优于首次拟合算法(从5%到34.6%)和最佳拟合算法(从4%到35.7%)。基于网络方程进化博弈(EGN)的拟议公式可以优于传统的资源分配启发法(例如最佳拟合,优先拟合)。通过广泛的仿真,我们证明了我们提出的模型的性能优于首次拟合算法(从5%到34.6%)和最佳拟合算法(从4%到35.7%)。

更新日期:2020-03-16
down
wechat
bug