A Case Study of Energy Aware Scheduling on SuperMUC

Auweter, Axel; Bode, Arndt; Brehm, Matthias; Brochard, Luigi; Hammer, N. J.; Huber, Herbert; Panda, Raj; Thomas, Francois; Wilde, Torsten

doi:10.1007/978-3-319-07518-1_25

Cited by 69 publications

(63 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This will eventually result into faster power decrease when a powercap period is approaching and lower jobs' turnaround time after a powercap period is over. The optimal DVFS choice for the best power/performance tradeoffs could be also determined through a particular profiling run as proposed in [28].…”

Section: Discussionmentioning

confidence: 99%

Adaptive Resource and Job Management for Limited Power Consumption

Georgiou¹,

Glesser

Trystram

2015

2015 IEEE International Parallel and Distributed Processing Symposium Workshop

View full text Add to dashboard Cite

International audienceThe last decades have been characterized by anever growing requirement in terms of computing and storage resources.This tendency has recently put the pressure on the abilityto efficiently manage the power required to operate the hugeamount of electrical components associated with state-of-the-arthigh performance computing systems. The power consumption ofa supercomputer needs to be adjusted based on varying powerbudget or electricity availabilities. As a consequence, Resourceand Job Management Systems have to be adequately adaptedin order to efficiently schedule jobs with optimized performancewhile limiting power usage whenever needed.We introduce in this paper a new scheduling strategy thatcan adapt the executed workload to a limited power budget. Theoriginality of this approach relies upon a combination of speedscaling and node shutdown techniques for power reductions. It isimplemented into the widely used resource and job managementsystem SLURM. Finally, it is validated through large scale emulationsusing real production workload traces of the supercomputerCurie

show abstract

Section: Discussionmentioning

confidence: 99%

Adaptive Resource and Job Management for Limited Power Consumption

Georgiou¹,

Glesser

Trystram

2015

2015 IEEE International Parallel and Distributed Processing Symposium Workshop

View full text Add to dashboard Cite

show abstract

“…After discussing with people from the Leibniz Supercomputing Centre operating the SuperMUC HPC system on which S3 is available, we get quantitative indications stating that, the power consumption on S3 mode is about twice bigger than when regularly switched off, and the On‐Off and Off‐On sequences are close in terms of duration. Thus, based on an Orion calibration from our measurements (as presented in Table ), we assume that an envisioned node with S3 mode would present the energy calibration parameters shown in Table .…”

Section: Impact Of Future Energy‐aware Hardwarementioning

confidence: 99%

Quantifying the impact of shutdown techniques for energy‐efficient data centers

Raïs

Orgerie

Quinson

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary Current large‐scale systems, like datacenters and supercomputers, are facing an increasing electricity consumption. These infrastructures are often dimensioned according to the workload peak. However, as their consumption is not power‐proportional when the workload is low, the power consumption is still high. Shutdown techniques have been developed to adapt the number of switched‐on servers to the actual workload. However, datacenter operators are reluctant to adopt such approaches because of their potential impact on reactivity and hardware failures, and their energy gain is often largely misjudged. In this article, we evaluate the potential gain of shutdown techniques by taking into account shutdown and boot up costs in time and energy. This evaluation is made on recent server architectures and future energy‐aware architectures. Our simulations exploit real traces collected on production infrastructures under various machine configurations with several shutdown policies, with and without workload prediction. We study the impact of future's knowledge for saving energy with such policies. Finally, we examine the energy benefits brought by suspend‐to‐disk and suspend‐to‐RAM techniques, and we study the impact of shutdown techniques on the energy consumption of prospective hardware with heterogeneous processors (big‐medium‐little paradigm).

show abstract

“…ANTAREX focuses on a holistic approach towards nextgeneration energy-efficient Exascale supercomputers. While traditional design of green supercomputers relies on the integration of best-in-class energy-efficient components [19], recent works [20,21] show that as an effect of this design practice supercomputers are nowadays heterogeneous systems. Indeed, supercomputers are not only composed of heterogeneous computing architectures (GPGPUs and CPUs), but different instances of the same nominal component execute the same application with 15% of variation in the energy consumption.…”

Section: Runtime Resource and Power Managementmentioning

confidence: 99%

The ANTAREX tool flow for monitoring and autotuning energy efficient HPC systems

Silvano

Agosta

Barbosa

et al. 2017

2017 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS)

View full text Add to dashboard Cite

Designing and optimizing HPC applications are difficult and complex tasks, which require mastering specialized languages and tools for performance tuning. As this is incompatible with the current trend to open HPC infrastructures to a wider range of users, the availability of more sophisticated programming languages and tools to assist and automate the design stages is crucial to provide smoothly migration paths towards novel heterogeneous HPC platforms. The ANTAREX project intends to address these issues by providing a tool flow, a Domain Specific Launguage and APIs to provide application's adaptivity and to runtime manage and autotune applications for heterogeneous HPC systems. Our DSL provides a separation of concerns, where analysis, runtime adaptivity, performance tuning and energy strategies are specified separately from the application functionalities with the goal to increase productivity, significantly reduce time to solution, while making possible the deployment of substantially improved implementations. This paper presents the ANTAREX tool flow and shows the impact of optimization strategies in the context of one of the ANTAREX use cases related to personalized drug design. We show how simple strategies, not devised by typical compilers, can substantially speedup the execution and reduce energy consumption.

show abstract

A Case Study of Energy Aware Scheduling on SuperMUC

Cited by 69 publications

References 7 publications

Adaptive Resource and Job Management for Limited Power Consumption

Adaptive Resource and Job Management for Limited Power Consumption

Quantifying the impact of shutdown techniques for energy‐efficient data centers

The ANTAREX tool flow for monitoring and autotuning energy efficient HPC systems

Contact Info

Product

Resources

About