The browser version you are using is not recommended for this site.Please consider upgrading to the latest version of your browser by clicking one of the following links.
We are sorry, This PDF is available in download format only
CERN openlab: Computing with Universal PerformanceCase Study: Intel® Xeon® processor 5500 series Energy Performance CERN openlab shows faster, more efficient analysis of physics data with Intel® Xeon® processor 5500 series The European Organization for Nuclear Research – CERN – is one of the largest and most respected scientific institutions in the world. Founded in 1954 as one of Europe’s first joint science ventures, it is established on the Swiss-French border near Geneva. CERN has 20 Member States from Europe, while other nations from around the globe also contribute to and participate in its research programme. It is carrying out research into fundamental physics and uses some of the most complex scientific instruments to study the basic constituents of matter and the Universe. Challenges: • Improve performance. CERN needs to ensure its computing platform has the highest possible throughput to process the 15 Petabytes of data per year expected from the Large Hadron Collider (LHC) experiments and to distribute the data to be analysed worldwide • Optimise energy consumption. As the present CERN data centre is limited to 2.9 MW electrical power (not counting the power for cooling and ventilation), CERN IT needs to ensure an optimal balance of performance and power consumption TESTED Solutions: • Different flavours. Intel® Xeon® processor 5500 series was evaluated in three flavours of varying power needs and performance levels against a series of benchmark tests Impact: • Increased efficiency. Tests showed that the new generation processor delivers a 36 per cent energy efficiency improvement over the previous generation for CERN’s environment • Lower power use. By enabling Intel Xeon processor 5500 series’ Simultaneous Multi- Threading feature, efficiency of the new platform can be boosted by up to 20 per centRead the full CERN openlab Case Study.
Citrix partners with Intel for cloud interoperability and cloud on-boarding proof of concept.
Parallels works with Intel to provide security monitoring and service catalogs to deploy virtual machines.
Canonical discusses building a cloud with Ubuntu*
What are public, private, and hybrid clouds?
Intel® AES-NI offers new instructions that speed up enterprise encryption and offer better performance, security, and more.
Fujitsu discusses how to build a cloud.