A Path To Energy Efficient HPC Datacenters

By Hayk Shoukourian

October 29, 2013

Energy efficiency is rapidly becoming a key factor for many modern high-performance computing (HPC) datacenters. It poses various challenges, which need to be addressed holistically and in an integrated manner, covering the HPC system environment (system hardware and system software), the hosting facility and infrastructure (cooling technologies, energy re-use, power supply chain, etc.), and applications (algorithms, performance metrics, etc.).

Most of the management schemes present in current HPC datacenters do not allow data to be shared between the HPC system environment, hosting facility, and infrastructure. But, it is important to collect and correlate data from all aspects of the datacenter in order to: better understand the interactions between different components of the datacenter; spot the improvement possibilities; and assess any introduced improvements. There are currently no tools that support a complete collection and correlation of energy efficiency relevant data, allowing for a unified view of energy consumption present in the datacenter.

That’s why a new energy measuring and evaluation toolset is being developed at the Leibniz Supercomputing Centre of the Bavarian Academy of Sciences (BAdW-LRZ) which is capable of monitoring and analysing the energy consumption of a supercomputing site in a holistic way, combining the HPC systems with data from the cooling and building infrastructure. The tool, named Power Data Aggregation Monitor (PowerDAM), allows the collection and evaluation of sensor data independently from the source systems and is capable of monitoring not only HPC systems but any other infrastructure that can be represented as a hierarchical tree. It monitors physical sensors as well as virtual sensors which can represent different functional compositions of several physical sensors.

PowerDAM provides a plug-in framework for defining the desired monitored entities such as IT systems, building infrastructure, etc. Two plug-in interfaces for each monitored entity are provided: one for sensor data collection and one for collecting application relevant data (e.g., utilized compute nodes, starting and ending timestamps of application, etc.) from system resource management tools.

PowerDAM is an underlying framework for energy efficiency related research at BAdW-LRZ.

Evaluating and Reporting

Energy-to-Solution (EtS) is an important metric for PowerDAM which denotes the aggregated energy consumption of an application consisting of the energy consumption of utilized compute nodes and partial sub-system components (e.g., system networking and system cooling).

Figure 1 presents the EtS report for an application executed on CoolMUC MPP Linux cluster. The first part of the report (part I) shows the sensor measurements for all utilized components in the order of timestamp, sensor name, value and unit.

Figure 1: EtS Report for an application executed on CoolMUC MPP Linux Cluster

Part II shows all approximations of source measurement data which were considered to be invalid (missing measurements, out of bounds data, etc.). Part III shows the aggregated energy consumption (EtS) of the executed application and provides information on the consumption percentages of computation, networking, and cooling.

The ability to calculate the EtS of an application allows for the further understanding and tuning of the application internally (via change of algorithms, memory access patterns, etc.) as well as externally through hardware adaptation (e.g., static/dynamic voltage frequency scaling).

PowerDAM provides various visualization options such as: the power draw, utilization rate, and averaged CPU temperatures of utilized compute nodes; correlation between power and load for these nodes; different EtS reports; and system power consumption for a given time frame (e.g. day, month, and year). Figure 2 illustrates one of these options – the EtS report (encompassing in parallel to the EtS, the percentages for computation, infrastructure, cooling, and networking) for all executed applications by a given user.

Figure 2: EtS Report for All Jobs Submitted by Given User

PowerDAM “node-map” view displays the dynamic behavior of compute nodes for a given sensor type. This view updates automatically after a customized amount of time and uses a color mapping to classify the behavior of the compute nodes (Figure 3).

Figure 3: Utilization Map of Compute Nodes for CoolMUC Linux Cluster. The color green illustrates the 96% to 100% utilization range. The color white illustrates the 0% and 90% to 95% utilization range. The color red illustrates the 1% to 89% utilization range. (not all compute nodes of the cluster are depicted)

The “node-map” view can be essential for understanding the interconnection between different sensor types. For example, correlating utilization rate (Figure 3) with CPU temperature (Figure 4) allows the investigation of the interdependency between utilization rates and CPU temperatures of defined compute nodes (nodes lxa130 and lxa17).

Figure 4: Temperature Map of Compute Nodes for CoolMUC Linux Cluster (2×8-core AMD CPUs per compute node)
(not all compute nodes of the cluster are depicted)

Further development will allow PowerDAM to: classify applications according to power draw, runtime, performance, and energy consumption; provide data necessary for the enhancement of the resource management systems; and report on datacenter key performance indicators (KPIs) such as PUE, ERE, DCiE, WUE, etc.

More detailed information on PowerDAM is available in the Proceedings of the First International Conference on Information and Communication Technologies for Sustainability under “Towards a Unified Energy Efficiency Evaluation Toolset: An Approach and Its Implementation at Leibniz Supercomputing Centre (LRZ)” and is indexed under DOI 10.3929/ethz-a-007337628.

The development of PowerDAM was made possible by the PRACE Second Implementation Phase project PRACE- 2IP in the Work Package “Prototyping” which has received funding from the European Community’s Seventh Framework Program (FP7/2007-2013) under grant agreement no. RI-283493 and within the SIMOPEK project which has received funding from the German Federal Ministry of Education and Research (BMBF) under grand agreement no. 01IH13007A. The work was achieved using the PRACE Research Infrastructure resources at BAdW-LRZ with support of the State of Bavaria, Germany.

The authors would like to thank Jeanette Wilde for her valuable comments and support.

Author Affiliations

Hayk Shoukourian(1,2); Torsten Wilde(1); Axel Auweter(1); Arndt Bode(1,2)

1Leibniz Supercomputing Centre of the Bavarian Academy of Sciences and Humanities (BAdW-LRZ)

2Technische Universität München (TUM), Fakultät für Informatik

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

UCSD, AIST Forge Tighter Alliance with AI-Focused MOU

January 18, 2018

The rich history of collaboration between UC San Diego and AIST in Japan is getting richer. The organizations entered into a five-year memorandum of understanding on January 10. The MOU represents the continuation of a 1 Read more…

By Tiffany Trader

New Blueprint for Converging HPC, Big Data

January 18, 2018

After five annual workshops on Big Data and Extreme-Scale Computing (BDEC), a group of international HPC heavyweights including Jack Dongarra (University of Tennessee), Satoshi Matsuoka (Tokyo Institute of Technology), Read more…

By John Russell

Researchers Measure Impact of ‘Meltdown’ and ‘Spectre’ Patches on HPC Workloads

January 17, 2018

Computer scientists from the Center for Computational Research, State University of New York (SUNY), University at Buffalo have examined the effect of Meltdown and Spectre security updates on the performance of popular H Read more…

By Tiffany Trader

HPE Extreme Performance Solutions

HPE and NREL Take Steps to Create a Sustainable, Energy-Efficient Data Center with an H2 Fuel Cell

As enterprises attempt to manage rising volumes of data, unplanned data center outages are becoming more common and more expensive. As the cost of downtime rises, enterprises lose out on productivity and valuable competitive advantage without access to their critical data. Read more…

Fostering Lustre Advancement Through Development and Contributions

January 17, 2018

Six months after organizational changes at Intel's High Performance Data (HPDD) division, most in the Lustre community have shed any initial apprehension around the potential changes that could affect or disrupt Lustre Read more…

By Carlos Aoki Thomaz

UCSD, AIST Forge Tighter Alliance with AI-Focused MOU

January 18, 2018

The rich history of collaboration between UC San Diego and AIST in Japan is getting richer. The organizations entered into a five-year memorandum of understandi Read more…

By Tiffany Trader

New Blueprint for Converging HPC, Big Data

January 18, 2018

After five annual workshops on Big Data and Extreme-Scale Computing (BDEC), a group of international HPC heavyweights including Jack Dongarra (University of Te Read more…

By John Russell

Researchers Measure Impact of ‘Meltdown’ and ‘Spectre’ Patches on HPC Workloads

January 17, 2018

Computer scientists from the Center for Computational Research, State University of New York (SUNY), University at Buffalo have examined the effect of Meltdown Read more…

By Tiffany Trader

Fostering Lustre Advancement Through Development and Contributions

January 17, 2018

Six months after organizational changes at Intel's High Performance Data (HPDD) division, most in the Lustre community have shed any initial apprehension aroun Read more…

By Carlos Aoki Thomaz

When the Chips Are Down

January 11, 2018

In the last article, "The High Stakes Semiconductor Game that Drives HPC Diversity," I alluded to the challenges facing the semiconductor industry and how that may impact the evolution of HPC systems over the next few years. I thought I’d lift the covers a little and look at some of the commercial challenges that impact the component technology we use in HPC. Read more…

By Dairsie Latimer

How Meltdown and Spectre Patches Will Affect HPC Workloads

January 10, 2018

There have been claims that the fixes for the Meltdown and Spectre security vulnerabilities, named the KPTI (aka KAISER) patches, are going to affect applicatio Read more…

By Rosemary Francis

Momentum Builds for US Exascale

January 9, 2018

2018 looks to be a great year for the U.S. exascale program. The last several months of 2017 revealed a number of important developments that help put the U.S. Read more…

By Alex R. Larzelere

ANL’s Rick Stevens on CANDLE, ARM, Quantum, and More

January 8, 2018

Late last year HPCwire caught up with Rick Stevens, associate laboratory director for computing, environment and life Sciences at Argonne National Laboratory, f Read more…

By John Russell

Inventor Claims to Have Solved Floating Point Error Problem

January 17, 2018

"The decades-old floating point error problem has been solved," proclaims a press release from inventor Alan Jorgensen. The computer scientist has filed for and Read more…

By Tiffany Trader

US Coalesces Plans for First Exascale Supercomputer: Aurora in 2021

September 27, 2017

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, in Arlington, Va., yesterday (Sept. 26), it was revealed that the "Aurora" supercompute Read more…

By Tiffany Trader

Japan Unveils Quantum Neural Network

November 22, 2017

The U.S. and China are leading the race toward productive quantum computing, but it's early enough that ultimate leadership is still something of an open questi Read more…

By Tiffany Trader

AMD Showcases Growing Portfolio of EPYC and Radeon-based Systems at SC17

November 13, 2017

AMD’s charge back into HPC and the datacenter is on full display at SC17. Having launched the EPYC processor line in June along with its MI25 GPU the focus he Read more…

By John Russell

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

IBM Begins Power9 Rollout with Backing from DOE, Google

December 6, 2017

After over a year of buildup, IBM is unveiling its first Power9 system based on the same architecture as the Department of Energy CORAL supercomputers, Summit a Read more…

By Tiffany Trader

Fast Forward: Five HPC Predictions for 2018

December 21, 2017

What’s on your list of high (and low) lights for 2017? Volta 100’s arrival on the heels of the P100? Appearance, albeit late in the year, of IBM’s Power9? Read more…

By John Russell

GlobalFoundries Puts Wind in AMD’s Sails with 12nm FinFET

September 24, 2017

From its annual tech conference last week (Sept. 20), where GlobalFoundries welcomed more than 600 semiconductor professionals (reaching the Santa Clara venue Read more…

By Tiffany Trader

Leading Solution Providers

Chip Flaws ‘Meltdown’ and ‘Spectre’ Loom Large

January 4, 2018

The HPC and wider tech community have been abuzz this week over the discovery of critical design flaws that impact virtually all contemporary microprocessors. T Read more…

By Tiffany Trader

Perspective: What Really Happened at SC17?

November 22, 2017

SC is over. Now comes the myriad of follow-ups. Inboxes are filled with templated emails from vendors and other exhibitors hoping to win a place in the post-SC thinking of booth visitors. Attendees of tutorials, workshops and other technical sessions will be inundated with requests for feedback. Read more…

By Andrew Jones

Tensors Come of Age: Why the AI Revolution Will Help HPC

November 13, 2017

Thirty years ago, parallel computing was coming of age. A bitter battle began between stalwart vector computing supporters and advocates of various approaches to parallel computing. IBM skeptic Alan Karp, reacting to announcements of nCUBE’s 1024-microprocessor system and Thinking Machines’ 65,536-element array, made a public $100 wager that no one could get a parallel speedup of over 200 on real HPC workloads. Read more…

By John Gustafson & Lenore Mullin

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

Flipping the Flops and Reading the Top500 Tea Leaves

November 13, 2017

The 50th edition of the Top500 list, the biannual publication of the world’s fastest supercomputers based on public Linpack benchmarking results, was released Read more…

By Tiffany Trader

GlobalFoundries, Ayar Labs Team Up to Commercialize Optical I/O

December 4, 2017

GlobalFoundries (GF) and Ayar Labs, a startup focused on using light, instead of electricity, to transfer data between chips, today announced they've entered in Read more…

By Tiffany Trader

How Meltdown and Spectre Patches Will Affect HPC Workloads

January 10, 2018

There have been claims that the fixes for the Meltdown and Spectre security vulnerabilities, named the KPTI (aka KAISER) patches, are going to affect applicatio Read more…

By Rosemary Francis

HPC Chips – A Veritable Smorgasbord?

October 10, 2017

For the first time since AMD's ill-fated launch of Bulldozer the answer to the question, 'Which CPU will be in my next HPC system?' doesn't have to be 'Whichever variety of Intel Xeon E5 they are selling when we procure'. Read more…

By Dairsie Latimer

  • arrow
  • Click Here for More Headlines
  • arrow
Share This