CERN openlab - Platform

Board of Sponsors meeting launches CERN openlab's next phase

Morag Hickman — Tue, 08 May 2012 08:08:31 +0000

Wednesday, 9 May, 2012

On the 8^th and 9^th of May, the CERN openlab Board of Sponsors gathered at CERN to officially close phase III of the collaboration, and to launch its fourth phase, which will run through 2012 to the end of 2014.

Welcomed by the Head of CERN openlab, Bob Jones, delegates from industry member companies and CERN management joined CERN openlab staff to review the third phase. Various talks highlighted key achievements, and celebrated the positive impact on the development of Grid and computing services which underpin the LHC. They also looked forward to future plans for development.

The fourth phase of CERN openlab will address topics critical to the continued growth of the CERN scientific programme, such as cloud computing, business analytics, the next generation of hardware, and security for myriads of network devices. The industry investment over the three years of the fourth phase represents more than eight million Swiss Francs.

Rolf Heuer, CERN Director General chaired a Round-Table discussion at the end of the day with the heads of delegations from the openlab partner companies, HP, Intel, Oracle, Intel, and Huawei as a contributor for a year, and thanked all CERN openlab partners and contributors for their continued support. He emphasized that the fourth phase of CERN openlab will be instrumental in addressing the growing computing challenges posed by increases in LHC luminosity and energy in future.

The second day brought an opportunity to widen the scope of the meeting, showcasing the scientific diversity of CERN, future needs of the experiments, and exploring how CERN openlab fits into the broader picture.

CERN Research Director Sergio Bertolluci spoke on the scientific programme of CERN, Pierre Vande Vyvre, Project Leader of the ALICE Data Acquisition Project, gave an experiment’s-eye-view of CERN’s computing needs and how they will change as the LHC’s energy and luminosity increase. A key development in processing data from the LHC and its experiments will be the creation of the CERN' s remote data centre, plans for which were outlined in a talk by Wayne Salter, Computing Facilities Group Leader in the CERN IT Department.

Bernd Panzer-Steindel, CTO and resource manager in the CERN computer centre, turned the focus towards strategic direction outilining how CERN is moving towards an agile infrastructure making sure of reasoned virtualisation. This presentation was followed-up by a discussion and wrap-up session. Bob Jones concluded: “CERN openlab has established itself as a reference thanks to the excellent relationship and on-going commitment of all partners and contributors during the past 11 years. The combined knowledge and dedication of the engineers from CERN and the companies have produced remarkable results. The launch of this fourth phase is an exciting time for CERN openlab and I am confident that we will be equally successful in the future.”

The press release is available to you, as well as a video presenting the CERN openlab activities and the group picture taken at the occasion of this first CERN openlab IV annual Board of Sponsors meeting, in the presence of the CERN Director-General, the partners, and the openlab team members.

Details of the event are available to delegates on Indico.

Niko Neufeld

Petya Georgieva — Mon, 26 Oct 2015 08:34:47 +0000

Biography:

Niko Neufeld holds a degree in engineering physics from the University of Technology in Vienna, Austria, and a PhD in particle physics. Since 2000 he has been working in the field of high-speed data acquisition and embedded processing. He co-designed the data-acquisition system of the LHCb experiment, which sifts through almost 70 gigabytes of data per second. Niko is now in charge of the upgrade of the LHCb data-acquisition system, which will increase the data-rate by almost a factor 50. He is a staff scientist in the physics department at CERN, and has published on numerous topics related to high-speed networking, physics data-processing, and embedded systems.

Photo:

Role(s):

PH-LBC

Active person:

Active person

First Name(s):

Niko

Last Name(s):

Neufeld

Years working at openlab-related job:

October, 2015

The Grid, CERN's Global Supercomputer - Computerphile

Melissa Gaillard — Tue, 01 Sep 2015 08:55:16 +0000

Date Published:

Tuesday, 15 October, 2013

CERN developed their 'Grid' before the world wide web took off. Maria and Andrzej explain how it does a lot more than just share the reams of data the Large Hadron Collider collects.

The Grid, CERN's Global Supercomputer - Computerphile

Petya Georgieva — Tue, 01 Sep 2015 07:59:22 +0000

Date Published:

Tuesday, 15 October, 2013

CERN developed their 'Grid' before the world wide web took off. Maria and Andrzej explain how it does a lot more than just share the reams of data the Large Hadron Collider collects.

CERN Upgrades Data Center and Restarts Large Hadron Collider

Melissa Gaillard — Tue, 11 Aug 2015 13:09:43 +0000

Intel

Link:

CERN Upgrades Data Center and Restarts Large Hadron Collider

Monday, 10 August, 2015

With upgraded hardware and capabilities, CERN pushes physics into new realms In April 2015, the most powerful particle accelerator ever built—the Large Hadron Collider (LHC) at CERN, the European Organization for Nuclear Research—was fired up for its second big series of runs, this time smashing things together at nearly twice the energy of its famous first run.

CERNUpgradesDataCenter&RestartsLargeHadronCollider.pdf

Phase:

openlab phase V

Competence center:

Platform

Evaluation of Selected C++11 Features with GCC, ICC and Clang

Mary Touranakou — Fri, 06 Mar 2015 14:24:26 +0000

Date published:

Monday, 1 September, 2014

Document type:

Summer student report

Author(s):

S. Wang

Project Specification: The project concerns various C++11 features - their performance and reliability. The report summarizes the tesults from four micro-benchmarks designed for this project and run with three different compilers (GCC, ICC, Clang) and tries to make an evaluation based on the results. Abstract: As C++11 gained almost full support by compilers, it is interesting to see whether we can leverage some of the features to improve performance and reliability of C++ code. This work is focused on four selected problems: time measurement techniques, for-loops efficiency, asychronuous tasks and parallel mode of STL algorithms. For each of them a micro-benchmark is made. All the benchmarks are fully automatized to generate results from running binaries compiled by three compilers: GCC, ICC and Clang with -O2, -O3 and -Ofast options. In order to evaluate vectorization and multithreading, profiling tools such as perf and Intel Vtune are used.

Report on ZENODO:

Document on ZENODO

The Evolving Marriage of Hardware and Software

Mary Touranakou — Thu, 05 Mar 2015 12:58:28 +0000

Date Published:

Friday, 21 February, 2014

This talk will give an overview of the activities of the openlab Platform Competence Center, collaborating with Intel.

Open Innovation 2.0 - Interview with Bob Jones, Head of CERN’s openlab project

Mary Touranakou — Tue, 10 Feb 2015 15:30:27 +0000

Date Published:

Tuesday, 21 May, 2013

CERN’s Bob Jones covers the openlab project to enable data-intensive solutions for the Large Hadron Collider

A glimpse of the CERN openlab summer student programme 2014

Mary Touranakou — Fri, 09 Jan 2015 10:51:19 +0000

Date Published:

Friday, 9 January, 2015

The 2014 students present the CERN openlab summer student programme.

Evaluation of selected C++11 features with GCC, ICC and Clang

Mary Touranakou — Fri, 05 Dec 2014 14:31:22 +0000

Date published:

Monday, 1 September, 2014

Document type:

Summer student report

Author(s):

S. Wang

Report on ZENODO:

Document on ZENODO

CERN/Intel Big Data Workshop

Mary Touranakou — Wed, 12 Nov 2014 16:16:51 +0000

Date:

Tuesday, 9 July, 2013 - 12:00 to Wednesday, 10 July, 2013 - 12:25

Location:

CERN IT Auditorium

CERN has been discussing with Intel to establish a big data lab at CERN. A number of meetings have already taken place promoted by a paper presented to Intel executives last year. As a follow-up we are organising a workshop at CERN on 9-10 July. The idea is that Intel will present their technologies and CERN will present the requirements for the LHC experiments' online systems. The material about the new technologies to be presented by Intel is subject to a Non-disclosure agreement which limits participants only to Intel and CERN personnel.

A key question forguding discussion during the workshop is "What would be the scientific value of having a large enough memory/processing capacity to be able to relax the triggers and still keep up with the data flow”?

The expected output of the workshop is a revised vision document and a concrete project plan for the big data lab.

Indico or other event webpage:

For more information

Calendar

High Core Count and Low Power Systems Evaluation

Mary Touranakou — Tue, 14 Oct 2014 12:25:23 +0000

Date published:

Wednesday, 7 May, 2014

Document type:

Poster

Author(s):

P. Szostek

A. Nowak

G. Bitzes

Event published at:

CERN openlab Board of Sponsors 2014 - Poster Session

CERN openlab Board of Sponsors 2014 (registered users only)

Technical document file:

poster_Intel.pdf

How can HEP Applications benefit from Vectorization?

Mary Touranakou — Tue, 14 Oct 2014 12:16:25 +0000

Date published:

Wednesday, 7 May, 2014

Document type:

Poster

Author(s):

G. Bitzes

Event published at:

CERN openlab Board of Sponsors 2014 - Poster Session

CERN openlab Board of Sponsors 2014 (registered users only)

Technical document file:

Intel-poster-final.pdf

Vectorization Studies of Random Number Generators on Intel’s Haswell Architecture

Mary Touranakou — Mon, 13 Oct 2014 08:49:13 +0000

Date published:

Monday, 1 September, 2014

Document type:

Summer student report

Author(s):

Y. Demirag

Project Specification: This project concerns the field of vectorization for Computing in High Energy Physics at CERN,Geneva. This paper summarises the results and progress of vectorizing two newly proposed counter based random number generators on Intel’s Haswell Architecture. Abstract: This project studies SIMD optimizing two different newly proposed random number generators on Intel’s Haswell architecture with AVX2 instruction sets. AVX2 instruction set is necessary since many random number generators rely on 64-bit integer multiplication. In first phase, mathematical algorithms behind the random number generators are studied and the places where they can be vectorized are identified. Then all internal data structures of random number generators are transformed from Array of Struct to Struct of Array for better auto-vectorization. To achieve better results intrinsics are used via a high-level C++ wrapping library. In second phase we performed benchmarks and studied the speed up obtained up to 1.57 times for Threefry CBRNG due to vectorization on Haswell.

Report on ZENODO:

Document on ZENODO

Fifth International Workshop for Future Challenges in Tracking and Trigger Concepts, Frankfurt, Germany

Mary Touranakou — Thu, 09 Oct 2014 11:39:24 +0000

Date:

Monday, 12 May, 2014 (All day) to Wednesday, 14 May, 2014 (All day)

Location:

Frankfurt, Germany

Indico or other event webpage:

More information about the event

Calendar