Archive for March, 2010

Phoenix PhaseC Upgrade Passed Acceptance Test

Wednesday, March 31st, 2010

CSCS is happy to announce that  Phoenix PhaseC Upgrade passed today the acceptance test. Phoenix is a HPC system run by CSCS used by the researchers of the Swiss Institute of Particle Physics CHIPP to analyze the data from the LHC experiment at CERN.

The upgrade has been delivered and installed by Sun and will double the computing and storage capacity provided by the previous system (also from Sun). The main characteristics of the new cluster are:

  • 96 Sun X6275 compute nodes with in total 768 cores running at 2.56 GHz (Intel E5540)
  • 7.6 TFlops peak performance
  • Lustre 115 TB usable space with a 7.6 GB/s write speed used as scratch
  • 10 Thors X4540 with480 TB total space (plus 672 TB Thumper recycled from PhaseB) used to store experiment data
  • Infiniband QDR used as interconnect

In the next days the system administrators at CSCS will migrate the middleware from phase B to C. PhaseC should be fully operational on Montay, April 19th. You can follow the next steps of the upgrade on twitter: http://www.twitter.com/phoenix_cscs

The Acceptance Protocol being signed by Dominik Ulmer (General Manager, CSCS) and Klaus Landl (Account Manager, Sun)

Part of the project team posing in front of the PhaseC system.

Today we also had the handover of the system responsibility from Fotis (right on the next picture) to Pablo. We thank Fotis for all the excellent job made so far. He has helped make Phoenix into a great cluster during these last 18 months, together with Jason and Riccardo, making it challenging for others to achieve the same quality. Pablo has an extensive GRID background and has been working with us for two months, during which time he has learned the daily procedures at CSCS-LCG2 grid site and is ready to succeed Fotis as system lead.

CERN: LHC research programme gets underway

Tuesday, March 30th, 2010

Today has been a special day here at CSCS for the HPC Co-Location Services team: We were following with crossed fingers the first collisions of the LHC collider at CERN. And everything went well! We are very proud with the cluster Phoenix of CHIPP to contribute as Tier 2 to the analysis of the large amount of data that will be produced by CERN.

Here below you may see a screenshot of the live broadcast of this morning.

And here below you may read the press release of CERN.

Geneva 30 March 2010. Beams collided at 7 TeV in the LHC at 13:06 CEST, marking the start of the LHC research programme. Particle physicists around the world are looking forward to a potentially rich harvest of new physics as the LHC begins its first long run at an energy three and a half times higher than previously achieved at a particle accelerator.

“It’s a great day to be a particle physicist,” said CERN Director General Rolf Heuer. “A lot of people have waited a long time for this moment, but their patience and dedication is starting to pay dividends.”

“With these record-shattering collision energies, the LHC experiments are propelled into a vast region to explore, and the hunt begins for dark matter, new forces, new dimensions and the Higgs boson,” said ATLAS collaboration spokesperson, Fabiola Gianotti. “The fact that the experiments have published papers already on the basis of last year’s data bodes very well for this first physics run.”

“We’ve all been impressed with the way the LHC has performed so far,” said Guido Tonelli, spokesperson of the CMS experiment, “and it’s particularly gratifying to see how well our particle detectors are working while our physics teams worldwide are already analysing data. We’ll address soon some of the major puzzles of modern physics like the origin of mass, the grand unification of forces and the presence of abundant dark matter in the universe. I expect very exciting times in front of us.”

“This is the moment we have been waiting and preparing for”, said ALICE spokesperson Jürgen Schukraft. “We’re very much looking forward to the results from proton collisions, and later this year from lead-ion collisions, to give us new insights into the nature of the strong interaction and the evolution of matter in the early Universe.”

“LHCb is ready for physics,” said the experiment’s spokesperson Andrei Golutvin, “we have a great research programme ahead of us exploring the nature of matter-antimatter asymmetry more profoundly than has ever been done before.”

CERN will run the LHC for 18-24 months with the objective of delivering enough data to the experiments to make significant advances across a wide range of physics channels. As soon as they have  “re-discovered” the known Standard Model particles, a necessary precursor to looking for new physics, the LHC experiments will start the systematic search for the Higgs boson. With the amount of data expected, called one inverse femtobarn by physicists, the combined analysis of ATLAS and CMS will be able to explore a wide mass range, and there’s even a chance of discovery if the Higgs has a mass near 160 GeV. If it’s much lighter or very heavy, it will be harder to find in this first LHC run.

For supersymmetry, ATLAS and CMS will each have enough data to double today?s sensitivity to certain new discoveries. Experiments today are sensitive to some supersymmetric particles with masses up to 400 GeV. An inverse femtobarn at the LHC pushes the discovery range up to 800 GeV.

“The LHC has a real chance over the next two years of discovering supersymmetric particles,” explained Heuer, “and possibly giving insights into the composition of about a quarter of the Universe.”

Even at the more exotic end of the LHC?s potential discovery spectrum, this LHC run will extend the current reach by a factor of two. LHC experiments will be sensitive to new massive particles indicating the presence of extra dimensions up to masses of 2 TeV, where today?s reach is around 1 TeV.

“Over 2000 graduate students are eagerly awaiting data from the LHC experiments,” said Heuer.  “They’re a privileged bunch, set to produce the first theses at the new high-energy frontier.”

Following this run, the LHC will shutdown for routine maintenance, and to complete the repairs and consolidation work needed to reach the LHC’s design energy of 14 TeV following the incident of 19 September 2008. Traditionally, CERN has operated its accelerators on an annual cycle, running for seven to eight months with a four to five month shutdown each
year. Being a cryogenic machine operating at very low temperature, the LHC takes about a month to bring up to room temperature and another month to cool down. A four-month shutdown as part of an annual cycle no longer makes sense for such a machine, so CERN has decided to move to a longer cycle with longer periods of operation accompanied by longer shutdown periods when needed.

“Two years of continuous running is a tall order both for the LHC operators and the experiments, but it will be well worth the effort,” said Heuer. “By starting with a long run and concentrating preparations for 14 TeV collisions into a single shutdown, we’re increasing the overall running time over the next three years, making up for lost time and giving
the experiments the chance to make their mark.”

LHC First Physics: Today Live Webcast

Tuesday, March 30th, 2010

Today marks the start of the LHC research programme with the first attempt for collisions at 7 TeV (3.5 TeV per beam).

Webcasts are available until 18:15 (Central European Summer Time – CEST). The main webcast will include live footage from the control room for the LHC accelerator and from the control rooms of the four main LHC experiments: ALICE, ATLAS, CMS and LHCb.

Follow also on twitter http://twitter.com/cern

HPC Advisory Council Announces European HPC Workshop in Conjunction with ISC 2010

Monday, March 29th, 2010

HPC Advisory Council Announces European HPC Workshop in Conjunction with the International Supercomputing Conference.

The HPC Advisory Council today announced that the HPC Advisory Council, in conjunction with ISC’10, will host the HPC Advisory Council European Workshop 2010 in the CCH-Congress Center Hamburg, Hamburg, Germany on May 30, 2010. The workshop will cover advanced topics such as GPU computing, MPI offloads, congestion management, networking optimizations and will feature presenters from Oakridge National Laboratory, Jülich Supercomputing Centre, Simula Research Laboratory, the 451 Group, and HPC Advisory Council professionals as well as technologists from various Independent Software Vendors and OEMs. The workshop will bring together system managers, researchers, developers, computational scientists, students and industry affiliates to discuss recent HPC developments and future advancements.

Pricing for the one-day workshop is 30€. Registration for the workshop is required and is now open through the ISC’10 registration page. The one-day workshop will include coffee breaks, lunch, and dinner courtesy of the HPC Advisory Council. For more information please visit the web page of the workshop.

Third Workshop on Call For Paters: UnConventional High Performance Computing 2010

Sunday, March 28th, 2010

CALL FOR PAPERS

Third Workshop on

UnConventional High Performance Computing 2010

(UCHPC 2010)

August 31st / September 1st, 2010, Ischia – Naples, Italy

held in conjunction with

Euro-Par 2010, August 31st – September 3rd, 2010

Submission deadline: June 14th 2010

As the computing power of various platforms intended for games is increasing rapidly, they attract the interest of professionals in the HPC community. As an example, the modern graphics processing units (GPU) are often used for HPC in the so called field “General-Purpose computing on GPU’s” (GPGPU). Another example is the Playstation3 (PS3) that has a multicore architecture that lends itself for HPC. These platforms are not conventional HPC platforms, nonetheless they are used for HPC purposes and even clusters of such computing resources are being built with great success. Both the raw computing power and the relatively low cost compared to conventional HPC resources make them very interesting. The aim of this workshop is to focus on such unconventional resources for HPC. Only imagination sets the limit for what this kind of devices can be used for in HPC, also by forming clusters.

The word “UnConventional” in the workshop title emphasizes that the focus is on hardware or platforms used for HPC, which were not intended for HPC in the first place. So, in some sense we try to capture things in this workshop that are being done in an unconventional way today but perhaps will be conventional tomorrow. That is why the C in UnConventional is in capital letters.

Link to the conference »