Emprical study on Reducing Energy of Parallel Programs using Slack Reclamation by DVFS in a Power-scalable High Performance Cluster

Kimura, Hirokazu; Sato, Mitsuhisa; Hotta, Yasuaki; Boku, Taisuke; Takahashi, Daisuke

doi:10.1109/clustr.2006.311839

Cited by 74 publications

(68 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lee et al [22] propose an energy-conscious scheduling (ECS) heuristic for parallel tasks on heterogeneous computing systems. Kimura et al [21] use the same idea of extending task execution time by reclaiming slack times for non-critical jobs.…”

Section: Power Aware Task Schedulingmentioning

confidence: 99%

See 1 more Smart Citation

Energy-aware parallel task scheduling in a cluster

Wang

Khan

Chen

et al. 2013

Future Generation Computer Systems

185

View full text Add to dashboard Cite

Reducing energy consumption for high end computing can bring various benefits such as, reduce operating costs, increase system reliability, and environment respect. This paper aims to develop scheduling heuristics and to present application experience for reducing power consumption of parallel tasks in a cluster with the Dynamic Voltage Frequency Scaling (DVFS) technique. In this paper, formal models are presented for precedence-constrained parallel tasks, DVFS enabled clusters, and energy consumption. This paper studies the slack time for non-critical jobs, extends their execution time and reduces the energy consumption without increasing the task's execution time as a whole. Additionally, Green Service Level Agreement is also considered in this paper. By increasing task execution time within an affordable limit, this paper develops scheduling heuristics to reduce energy consumption of a tasks execution and discusses the relationship between energy consumption and task execution time. Models and scheduling heuristics are examined with a simulation study. Test results justify the design and implementation of proposed energy aware scheduling heuristics in the paper.

show abstract

Section: Power Aware Task Schedulingmentioning

confidence: 99%

“…However, EADUS & TEBUS do not use DVFS to reduce energy consumption, thus leading less energy savings. Compared with LEneS [16], Energy Reduction Algorithm [21], and ECS [22], the PATC and PALS can achieve more energy saving as…”

Section: Performance Study With Simulationmentioning

confidence: 99%

Energy-aware parallel task scheduling in a cluster

Wang

Khan

Chen

et al. 2013

Future Generation Computer Systems

185

View full text Add to dashboard Cite

show abstract

“…However, EADUS & TEBUS do not use DVFS to reduce energy consumption, thus leading less energy savings. Compared with LEneS [22], Energy Reduction Algorithm [31], and ECS [30], our algorithm can achieve more energy saving as 1) it reduces the energy consumption during the communication phase, 2) it reduces power consumption when a PE is idle, and 3) it tries to extend job slack time whenever it is possible. Figure 7 shows the energy savings in different scenarios of numbers of PEs and resource competition.…”

Section: Energy-performance Tradeoff Scheduling Algorithmmentioning

confidence: 99%

“…[31] uses the same idea of extending task execution time by reclaiming slack times for non-critical jobs. In our paper, we give a clear formulation of energy aware scheduling algorithm and a detailed discussion of slack time computation.…”

Section: Power Aware Task Schedulingmentioning

confidence: 99%

Towards Energy Aware Scheduling for Precedence Constrained Parallel Tasks in a Cluster with DVFS

Wang

Laszewski

Dayal

et al. 2010

2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing

189

108

View full text Add to dashboard Cite

Abstract-Reducing energy consumption for high end computing can bring various benefits such as, reduce operating costs, increase system reliability, and environment respect. This paper aims to develop scheduling heuristics and to present application experience for reducing power consumption of parallel tasks in a cluster with the Dynamic Voltage Frequency Scaling (DVFS) technique. In this paper, formal models are presented for precedence-constrained parallel tasks, DVFS enabled clusters, and energy consumption. This paper studies the slack time for non-critical jobs, extends their execution time and reduces the energy consumption without increasing the task's execution time as a whole. Additionally, Green Service Level Agreement is also considered in this paper. By increasing task execution time within an affordable limit, this paper develops scheduling heuristics to reduce energy consumption of a tasks execution and discusses the relationship between energy consumption and task execution time. Models and scheduling heuristics are examined with a simulation study. Test results justify the design and implementation of proposed energy aware scheduling heuristics in the paper.

show abstract

“…The first approach is to identify and exploit MPI inter-task load imbalance. The work done in [24] and [25] focuses on locating these imbalances and applying reduced frequencies to computation regions that are not on the application's criritcal path. By reducing the energy used on a non-critical path, overall energy can be reduced since power consumption is decreased with negligible performance loss.…”

Section: Related Workmentioning

confidence: 99%

Reducing Energy Usage with Memory and Computation-Aware Dynamic Frequency Scaling

Laurenzano

Meswani

Carrington

et al. 2011

Euro-Par 2011 Parallel Processing

View full text Add to dashboard Cite

Abstract. Over the life of a modern computer, the energy cost of running the system can exceed the cost of the original hardware purchase. This has driven the community to attempt to understand and minimize energy costs wherever possible. Towards these ends, we present an automated, fine-grained approach to selecting per-loop processor clock frequencies. The clock frequency selection criteria is established through a combination of lightweight static analysis and runtime tracing that automatically acquires application signatures -characterizations of the patterns of execution of each loop in an application. This application characterization is matched with a series of benchmark loops, which have been run on the target system and exercise it various ways. These benchmarks are intended to form a covering set, a machine characterization of the expected power consumption and performance traits of the machine over the space of execution patterns and clock frequencies. The frequency that confers the best power-delay product to the benchmark that most closely resembles each application loop is the one chosen for that loop. The application's frequency management strategy is then permanently integrated into the compiled executable via static binary instrumentation. This process is lightweight, only has to be done once per application (and the benchmarks just once per machine), and thus is much less laborious than running every application loop at every possible frequency on the machine to see what the optimal frequencies would be. Unlike most frequency management schemes, we toggle frequencies very frequently, potentially at every loop entry and exit, saving as much as 10% of the energy bill in the process. The set of tools that implement this scheme is fully automated, built on top of freely available open source software, and uses an inexpensive power measurement apparatus. We use these tools to show a measured, system-wide energy savings of up to 7.6% on an 8-core Intel Xeon E5530 and 10.6% on a 32-core AMD Opteron 8380 (a Sun X4600 Node) across a range of workloads.

show abstract

Emprical study on Reducing Energy of Parallel Programs using Slack Reclamation by DVFS in a Power-scalable High Performance Cluster

Cited by 74 publications

References 9 publications

Energy-aware parallel task scheduling in a cluster

Energy-aware parallel task scheduling in a cluster

Towards Energy Aware Scheduling for Precedence Constrained Parallel Tasks in a Cluster with DVFS

Reducing Energy Usage with Memory and Computation-Aware Dynamic Frequency Scaling

Contact Info

Product

Resources

About