Penelope: Peer-to-peer Power Management

Penelope: Peer-to-peer Power Management
复制标题

Penelope:点对点电源管理

DOI:
10.1145/3545008.3545047
复制
发表时间:
2022
期刊:
ICPP 2022: 51st International Conference on Parallel Processing
影响因子:
--
通讯作者:
Hoffmann, Henry
Hoffmann, Henry
中科院分区:
--
文献类型:
--
作者:
Srivastava, Tapan;Zhang, Huazhe;Hoffmann, Henry

文献摘要

参考文献

被引文献

相似文献

大规模分布式计算设置依赖电源管理系统来执行紧张的电源预算。现有系统使用一个中央权威机构,将多余的电力重新分配给需要电力的节点。然而,这个中央权威既是一个单一的故障点,也是一个关键的瓶颈--特别是在大规模的情况下。为了解决这些限制,我们提出了Penelope,这是一个分布式电源管理系统,通过对等交易来转移电力,确保它在故障环境和大规模情况下保持健壮。我们实现了Penelope,并将其在不同功率预算下的性能与集中式电源管理器Slurm进行了比较。我们发现,在正常情况下,Slum和Penelope的性能几乎相同;然而,在故障环境中,Penelope的平均应用程序性能比Slurm提高了8%-15%。在大规模且消息频率不断增加的情况下,Penelope保持其性能,而集中式方法会降低性能并变得不可用。
Large scale distributed computing setups rely on power management systems to enforce tight power budgets. Existing systems use a central authority that redistributes excess power to power-hungry nodes. This central authority, however, is both a single point of failure and a critical bottleneck—especially at large scale. To address these limitations we propose Penelope, a distributed power management system which shifts power through peer-to-peer transactions, ensuring that it remains robust in faulty environments and at large scale. We implement Penelope and compare its achieved performance to SLURM, a centralized power manager, under a variety of power budgets. We find that under normal conditions SLURM and Penelope achieve almost equivalent performance; however in faulty environments, Penelope achieves 8–15% mean application performance gains over SLURM. At large scale and with increasing frequency of messages, Penelope maintains its performance in contrast to centralized approaches which degrade and become unusable.
DOI: 10.1145/1995896.1995927
发表时间: 2011-05
期刊: --
影响因子: --
作者:
Jing Chen;L. John
通讯作者: Jing Chen;L. John
DOI: 10.1109/ipdps47924.2020.00115
发表时间: 2020-05
期刊: 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS)
影响因子: --
作者:
Anwesha Das;F. Mueller;B. Rountree
通讯作者: Anwesha Das;F. Mueller;B. Rountree
分析硬件过度配置的超级计算机中的资源权衡
DOI: --
发表时间: 2018
期刊: IEEE International Parallel and Distributed Processing Symposium
影响因子: --
作者:
Ryuichi Sakamoto;Tapasya Patki;Thang Cao;Masaaki Kondo;Koji Inoue;M. Ueda;D. Ellsworth;B. Rountree;M. Schulz
通讯作者: M. Schulz
AEQUITAS:跨并行应用程序的协调能源管理
DOI: --
发表时间: 2016
期刊: International Conference on Supercomputing
影响因子: --
作者:
Haris Ribic;Yu David Liu
通讯作者: Yu David Liu
Xen 虚拟机管理程序中低级性能约束下的功耗管理
DOI: --
发表时间: 2020
期刊: SIGBED Rev.
影响因子: --
作者:
Rolando Brondolin;Marco Arnaboldi;M. D. Santambrogio
通讯作者: M. D. Santambrogio