thermal management
always applied clearly and consistently. To address these inconsistencies, industry leaders met in early 2010 to agree on data centre energy effi ciency measurements, metrics and reporting conventions. Organisations represented were the 7x24 Exchange, ASHRAE, The Green Grid, Silicon Valley Leadership Group, the U.S. Department of Energy’s Save Energy Now and Federal Energy Management Programs, the U.S. Environmental Protection Agency’s Energy Star Program, the U.S. Green Building Council, and the Uptime Institute. Among the guiding principles they agreed is that power usage effectiveness (PUE) using source energy consumption is the preferred energy effi ciency metric for data centres. PUE is a measurement of the total energy of the data centre divided by the IT energy consumption. In more and more new facilities, energy
from the data centre is being reused in other parts of the facility or campus with benefi cial results. PUE doesn’t consider these alternate uses for waste energy. To account for these, The Green Grid has proposed and defi ned a new metric: energy reuse effectiveness (ERE). Yet other new metrics it has proposed are data centre compute effi ciency (DCcE) and its underlying sub- metric, server compute effi ciency (ScE). Using these, operators can continually refi ne and increase the effi ciency of their compute
discuss comments on the draft specifi cation. Furthermore, the EPA has launched the development process for the Version 2.0 specifi cation for Energy Star Computer Server Specifi cation Development. Additionally, the SNIA’s Green Storage
Modular data centres such as this from SGI offer a fl exible alternative to brick and mortar data facilities
resources in the same way that they use PUE to improve data centre infrastructure. The group is also introducing the CUE
(carbon usage effectiveness) metric, addressing data centre-specifi c carbon emissions, which is emerging as an important factor in the design, location, and operation of facilities. CUE, combined with PUE, enables operators to quickly assess the relative sustainability of their data centres, compare results, and determine if any energy effi ciency and/or sustainable energy improvements need to be made. Providing a metric at an even lower level, the SNIA (Storage Networking Industry Association) has engaged with the Energy Star program to develop an Energy Star Data Centre Storage Specifi cation. The EPA has hosted a stakeholder meeting to
Initiative is sponsoring, operating and promoting SNIA Emerald, a program scheduled to be fully operational in a few months. Its purpose is to provide a fair and equitable measurement of storage system power usage and effi ciency through use of a well-defi ned testing procedure. The SNIA Emerald Power Effi ciency Measurement Specifi cation is maintained under the guidance of the Green Storage Initiative. Use of the specifi cation will lead to the posting of results to the SNIA Emerald central repository and obtaining a SNIA Emerald trademark and logo license.
Inter-departmental synergies A good wrap-up to the topic of energy effi ciency comes from SGI’s McCann, who says that people are starting to address cross- departmental issues. Previously, he notes, the IT department would select and purchase the equipment, then the facilities people would have to deal with it. Now there are synergies among such departments, the barriers are dropping and the overall costs are being examined.
NVIDIA®
TESLA® REVOLUTIONISING HIGH PERFORMANCE COMPUTING
NVIDIA® Tesla™ 20-series is designed from the ground up for high performance computing (HPC). When compared to the latest quad-core CPU, Tesla 20-series GPU computing processors deliver equivalent performance at 1/20th the power consumption and 1/10th the cost. NVIDIA® Tesla scales to solve the world’s most important computing challenges – more quickly and accurately.
Contact your NVIDIA Tesla Preferred Partner to learn more:
© NVIDIA 2011
01923 225550
sales@armari.co.uk
0800 180 4801
sales@wksmail.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44