PowerPack: Energy Profiling and Analysis of High-Performance Systems and Applications

Ge, Rong; Feng, Xueyang; Song, Shuaiwen Leon; Chang, Hung-Ching; Liu, Dong; Cameron, Kirk W.

doi:10.1109/tpds.2009.76

Cited by 325 publications

(195 citation statements)

References 22 publications

Supporting

Mentioning

183

Contrasting

Order By: Relevance

“…Powerpack [13] is one such instrumented x86 cluster. The PowerMon2 [14] project describes small boards that can be used to instrument a large x86 cluster.…”

Section: Cluster Power Measurementmentioning

confidence: 99%

A Raspberry Pi Cluster Instrumented for Fine-Grained Power Measurement

2016

View full text Add to dashboard Cite

Abstract:Power consumption has become an increasingly important metric when building large supercomputing clusters. One way to reduce power usage in large clusters is to use low-power embedded processors rather than the more typical high-end server CPUs (central processing units). We investigate various power-related metrics for seventeen different embedded ARM development boards in order to judge the appropriateness of using them in a computing cluster. We then build a custom cluster out of Raspberry Pi boards, which is specially designed for per-node detailed power measurement. In addition to serving as an embedded cluster testbed, our cluster's power measurement, visualization and thermal features make it an excellent low-cost platform for education and experimentation.

show abstract

“…Powerpack [13] is one such instrumented x86 cluster. The PowerMon2 [14] project describes small boards that can be used to instrument a large x86 cluster.…”

Section: Cluster Power Measurementmentioning

confidence: 99%

A Raspberry Pi Cluster Instrumented for Fine-Grained Power Measurement

2016

View full text Add to dashboard Cite

show abstract

“…Most previous research on power optimization uses architectural simulation to estimate power or energy usage by different components of the compute system [6]. More recently, direct power and energy measurement hardware and software have been developed [4,13,15]. Bedard et.…”

Section: Related Workmentioning

confidence: 99%

“…Pro [3] or more customized frameworks such as PowerMon2 [4] or PowerPack [13] can help measure power and energy consumption. Modeling energy usage through combinations of architectural parameters with performance counters [26] or other resource usage information [21] also fall in this category.…”

Section: Introductionmentioning

confidence: 99%

Auto-tuning for Energy Usage in Scientific Applications

Tiwari

Laurenzano

Carrington

et al. 2012

Euro-Par 2011: Parallel Processing Workshops

View full text Add to dashboard Cite

Abstract. The power wall has become a dominant impeding factor in the realm of exascale system design. It is therefore important to understand how to most effectively create application software in order to minimize its power usage while maintaining satisfactory levels of performance. In this work, we use existing software and hardware facilities in order to tune applications to minimize for several combinations of power and performance. The tuning is done with respect to software level performance-related tunables (cache tiling factors and loop unrolling factors) as well as for processor clock frequency. These tunable parameters are explored via an offline search in order to find the parameter combinations that are optimal with respect to performance (or delay, D), energy (E), energy×delay (E × D) and energy×delay×delay (E × D 2 ). These searches are employed on a parallel application that solves Poisson's equation using stencil computations. Stencil (nearestneighbor) computations are very common operations in today's scientific applications. We show that the parameter configuration that minimizes energy consumption can save, on average, 5.4% energy with a performance loss of 4% when compared to the configuration that minimizes runtime. Furthermore, with the work presented in this paper, we provide evidence for the existence of opportunities to auto-tune for energy in parallel applications.

show abstract

“…Certainly the largest body of work has been done in collaboration by Ge, Feng and Cameron (in some cases in association with other researchers). In [6] and [7] the authors introduce PowerPack. PowerPack is a framework for profiling and analyzing scientific applications on distributed systems.…”

Section: Related Workmentioning

confidence: 99%

“…In [11] the authors improve on the single node sampling technique described in [6] and [7] by expanding their collection capability to 16 nodes (this seems to remain the limit on node count in the remaining publications). The NEMO power aware cluster is comprised of laptops which allow the necessary measurements to be taken.…”

Section: Related Workmentioning

confidence: 99%

Measuring and tuning energy efficiency on large scale high performance computing platforms.

Laros¹

2011

View full text Add to dashboard Cite

Recognition of the importance of power in the field of High Performance Computing, whether it be as an obstacle, expense or design consideration, has never been greater and more pervasive. While research has been conducted on many related aspects, there is a stark absence of work focused on large scale High Performance Computing. Part of the reason is the lack of measurement capability currently available on small or large platforms. Typically, research is conducted using coarse methods of measurement such as inserting a power meter between the power source and the platform, or fine grained measurements using custom instrumented boards (with obvious limitations in scale). To collect the measurements necessary to analyze real scientific computing applications at large scale, an in-situ measurement capability must exist on a large scale capability class platform.In response to this challenge, we exploit the unique power measurement capabilities of the Cray XT architecture to gain an understanding of power use and the effects of tuning. We apply these capabilities at the operating system level by deterministically halting cores when idle. At the application level, we gain an understanding of the power requirements of a range of important DOE/NNSA production scientific computing applications running at large scale (thousands of nodes), while simultaneously collecting current and voltage measurements on the hosting nodes. We examine the effects of both CPU and network bandwidth tuning and demonstrate energy savings opportunities of up to 39% with little or no impact on run-time performance. Capturing scale effects in our 3 experimental results was key. Our results provide strong evidence that next generation large-scale platforms should not only approach CPU frequency scaling differently, but could also benefit from the capability to tune other platform components, such as the network, to achieve energy efficient performance. 5Acknowledgments I would like to acknowledge the following people who have contributed in various ways, all of which significant, to the successful completion of this work: Dr.

show abstract

PowerPack: Energy Profiling and Analysis of High-Performance Systems and Applications

Cited by 325 publications

References 22 publications

A Raspberry Pi Cluster Instrumented for Fine-Grained Power Measurement

A Raspberry Pi Cluster Instrumented for Fine-Grained Power Measurement

Auto-tuning for Energy Usage in Scientific Applications

Measuring and tuning energy efficiency on large scale high performance computing platforms.

Contact Info

Product

Resources

About