Filters








180 Hits in 0.86 sec

CMS use of allocation based HPC resources

Dirk Hufnagel
2017 Journal of Physics, Conference Series  
The higher energy and luminosity from the LHC in Run2 has put increased pressure on CMS computing resources. Extrapolating to even higher luminosities (and thus higher event complexities and trigger rates) in Run3 and beyond, it becomes clear the current model of CMS computing alone will not scale accordingly. High Performance Computing (HPC) facilities, widely used in scientific computing outside of HEP, present a (at least so far) largely untapped computing resource for CMS. Even just being
more » ... le use a small fraction of HPC facilities computing resources could significantly increase the overall computing available to CMS. Here we describe the CMS strategy for integrating HPC resources into CMS computing, the unique challenges these facilities present, and how we plan on overcoming these challenges. We also present the current status of ongoing CMS efforts at HPC sites such as NERSC (Cori cluster), SDSC (Comet cluster) and TACC (Stampede cluster).
doi:10.1088/1742-6596/898/9/092050 fatcat:53utbgx5fvdangnfl7jpinicva

CMS Tier-0: Preparing for the future

Dirk Hufnagel
2012 Journal of Physics, Conference Series  
The Tier-0 processing system is the initial stage of the multi-tiered computing system of CMS. It is responsible for the first processing steps of data from the CMS Experiment at CERN. This talk covers the complete overhaul (rewrite) of the system for the 2012 run, to bring it into line with the new CMS Workload Management system, improving scalability and maintainability for the next few years. Abstract. The Tier-0 processing system is the initial stage of the multi-tiered computing system of
more » ... MS. It is responsible for the first processing steps of data from the CMS Experiment at CERN. This presentation covers the complete overhaul (rewrite) of the system for the 2012 run, to bring it into line with the new CMS Workload Management system, improving scalability and maintainability for the next few years.
doi:10.1088/1742-6596/396/2/022025 fatcat:zozeqhpzsnhknlzh6qiruwpu4i

The architecture and operation of the CMS Tier-0

Dirk Hufnagel
2011 Journal of Physics, Conference Series  
The Tier-0 processing system is the initial stage of the multi-tiered computing system of CMS. It takes care of the first processing steps of data at the LHC at CERN. The automated workflows running in the Tier-0 contain both low-latency processing chains for time-critical applications and bulk chains to archive the recorded data offsite the host laboratory. It is a mix between an online and offline system, because the data the CMS DAQ writes out initially is of a temporary nature. Most of the
more » ... omplexity in the design of this system comes from this unique combination of online and offline use cases and dependencies. In this talk, we want to present the software design of the CMS Tier-0 system and present an analysis of the 24/7 operation of the system in the 2009/2010 data taking periods. Abstract. The Tier-0 processing system is the initial stage of the multi-tiered computing system of CMS. It takes care of the first processing steps of data at the LHC at CERN. The automated workflows running in the Tier-0 contain both low-latency processing chains for timecritical applications and bulk chains to archive the recorded data offsite the host laboratory. It is a mix between an online and offline system, because the data the CMS DAQ writes out initially is of a temporary nature. Most of the complexity in the design of this system comes from this unique combination of online and offline use cases and dependencies. In this talk, we want to present the software design of the CMS Tier-0 system and present an analysis of the 24/7 operation of the system in the 2009/2010 data taking periods. • Physics stream, about 200Hz • Express stream, about 20Hz, a subset of Physics for fast monitoring/analysis and feedback • Various calibration/monitoring streams, about 20Hz total
doi:10.1088/1742-6596/331/3/032017 fatcat:4o5c7wvhv5cwhd7x7rgmcuaouq

The CMS TierO goes Cloud and Grid for LHC Run 2

Dirk Hufnagel
2015 Journal of Physics, Conference Series  
In 2015, CMS will embark on a new era of collecting LHC collisions at unprecedented rates and complexity. This will put a tremendous stress on our computing systems. Prompt Processing of the raw data by the Tier-0 infrastructure will no longer be constrained to CERN alone due to the significantly increased resource requirements. In LHC Run 2, we will need to operate it as a distributed system utilizing both the CERN Cloud-based Agile Infrastructure and a significant fraction of the CMS Tier-1
more » ... id resources. In another big change for LHC Run 2, we will process all data using the multi-threaded framework to deal with the increased event complexity and to ensure efficient use of the resources. This contribution will cover the evolution of the Tier-0 infrastructure and present scale testing results and experiences from the first data taking in 2015.
doi:10.1088/1742-6596/664/3/032014 fatcat:ro3njqysq5d5xjq5zmwapno4hu

HPC resource integration into CMS Computing via HEPCloud

Dirk Hufnagel, Burt Holzman, David Mason, Parag Mhashilkar, Steven Timm, Anthony Tiradani, Farrukh Aftab Khan, Oliver Gutsche, Kenneth Bloom, A. Forti, L. Betev, M. Litmaath (+2 others)
2019 EPJ Web of Conferences  
The higher energy and luminosity from the LHC in Run 2 have put increased pressure on CMS computing resources. Extrapolating to even higher luminosities (and thus higher event complexities and trigger rates) beyond Run 3, it becomes clear that simply scaling up the the current model of CMS computing alone will become economically unfeasible. High Performance Computing (HPC) facilities, widely used in scientific computing outside of HEP, have the potential to help fill the gap. Here we describe
more » ... he U.S.CMS efforts to integrate US HPC resources into CMS Computing via the HEPCloud project at Fermilab. We present advancements in our ability to use NERSC resources at scale and efforts to integrate other HPC sites as well. We present experience in the elastic use of HPC resources, quickly scaling up use when so required by CMS workflows. We also present performance studies of the CMS multi-threaded framework on both Haswell and KNL HPC resources.
doi:10.1051/epjconf/201921403031 fatcat:4bvpm72zebaxzo2kzpq44lilqe

Opportunistic Resource Usage in CMS

Peter Kreuzer, Dirk Hufnagel, D Dykstra, O Gutsche, M Tadel, I Sfiligoi, J Letts, F Wuerthwein, A McCrea, B Bockelman, E Fajardo, L Linares (+4 others)
2014 Journal of Physics, Conference Series  
CMS computing model evolution C Grandi, D Bonacorsi, D Colling et al. -CMS computing operations during run 1 J Adelman, S Alderweireldt, J Artieda et al. -Abstract. CMS is using a tiered setup of dedicated computing resources provided by sites distributed over the world and organized in WLCG. These sites pledge resources to CMS and are preparing them especially for CMS to run the experiment's applications. But there are more resources available opportunistically both on the GRID and in local
more » ... versity and research clusters which can be used for CMS applications. We will present CMS' strategy to use opportunistic resources and prepare them dynamically to run CMS applications. CMS is able to run its applications on resources that can be reached through the GRID, through EC2 compliant cloud interfaces. Even resources that can be used through ssh login nodes can be harnessed. All of these usage modes are integrated transparently into the GlideIn WMS submission infrastructure, which is the basis of CMS' opportunistic resource usage strategy. Technologies like Parrot to mount the software distribution via CVMFS and xrootd for access to data and simulation samples via the WAN are used and will be described. We will summarize the experience with opportunistic resource usage and give an outlook for the restart of LHC data taking in 2015.
doi:10.1088/1742-6596/513/6/062028 fatcat:hr23b2vmvvc4zfrlyijxdrpqhu

Practice and consensus-based strategies in diagnosing and managing systemic juvenile idiopathic arthritis in Germany

Claas H. Hinze, Dirk Holzinger, Elke Lainka, Johannes-Peter Haas, Fabian Speth, Tilmann Kallinich, Nikolaus Rieber, Markus Hufnagel, Annette F. Jansson, Christian Hedrich, Hanna Winowski, Thomas Berger (+10 others)
2018 Pediatric Rheumatology Online Journal  
Hufnagel has received research support from Novartis and Roche. Dr.  ... 
doi:10.1186/s12969-018-0224-2 pmid:29357887 pmcid:PMC5778670 fatcat:ik3q7lkhgje7bn3asfc4h3y7de

S100 Levels Guided Treatment Options in a Teenage Boy with Relapsing Pericarditis or Atypical Still and #8217;s Disease

Roland Elling, Jochen Grohmann, Dirk Holzinger, Philipp Hufnagel
2012 Annals of the Pediatric Rheumatology (APR)  
those in com sible only w Measu of units (SI u Footno script lowerc 4. Ref Please appear in the in numerica than 6 autho name of the abbreviated For ch chapter auth name, year o The lis accepted for reference lis mitted when the Digital O Refere Journa of new diagn diatr Rheum Abstract Unraveling the etiology of recurrent pericarditis in children is often challenging. Here, we describe the case of a previously healthy, 15-year-old boy who presented with fever, cough and thoracic pain due to
more » ... carditis with a large pericardial effusion. After insertion of a pericardial drainage over 1600 ml of pericardial fluid were collected over a 48-hour period. Laboratory investigations revealed systemic inflammation and negative autoantibodies, but displayed no evidence of an infectious disease. Autoimmune pericarditis was therefore suspected and a combination of glucocorticosteroid and NSAID therapy was initiated. Steroids were able to be gradually tapered. However, the patient suffered a recurrence of pericarditis after six weeks of low-dose steroids and NSAIDs. As with the first episode, arthritis, rash, lymphadenopathy and hepatosplenomegaly were absent. Retrospective analysis of the serum from the initial episode showed significant elevation of S100 protein levels (S100A8/S100A9). As a result, we assumed an atypical presentation of Still´s disease (systemic onset juvenile idiopathic arthritis or SoJIA) and initiated therapy with anakinra, an interleukin-1-receptor antagonist. This treatment led to rapid improvement, and pericardiocentesis was able to be avoided. Four months after the relapse and subsequent initiation of anakinra therapy, no disease reoccurrence has transpired. Treatment with ibuprofen and steroids could be suspended. The patient developed mild arthritic signs during follow-up supporting the diagnosis of SoJIA. A potential differential diagnosis in this case is idiopathic recurrent acute pericarditis (IRAP), a disease of unknown etiology that shows features consistent with an autoinflammatory pathogenesis where recent reports indicated good clinical response to anakinra treatment as well. This case highlights the predictive value of S100 protein levels for the diagnosis of autoinflammatory disorders such as SoJIA -particularly when there is an atypical or oligosymptomatic presentation. Moreover, it illustrates the therapeutic potential of anakinra for autoimmune-mediated pericarditis.
doi:10.5455/apr.112620120045 fatcat:twbsmcflk5dgvibej2noiulmaa

The Diverse use of Clouds by CMS

Anastasios Andronis, Daniela Bauer, Olivier Chaze, David Colling, Marc Dobson, Simon Fayer, Maria Girone, Claudio Grandi, Adam Huffman, Dirk Hufnagel, Farrukh Aftab Khan, Andrew Lahiff (+5 others)
2015 Journal of Physics, Conference Series  
The resources CMS is using are increasingly being offered as clouds. In Run 2 of the LHC the majority of CMS CERN resources, both in Meyrin and at the Wigner Computing Centre, will be presented as cloud resources on which CMS will have to build its own infrastructure. This infrastructure will need to run all of the CMS workflows including: Tier 0, production and user analysis. In addition, the CMS High Level Trigger will provide a compute resource comparable in scale to the total offered by the
more » ... CMS Tier 1 sites, when it is not running as part of the trigger system. During these periods a cloud infrastructure will be overlaid on this resource, making it accessible for general CMS use. Finally, CMS is starting to utilise cloud resources being offered by individual institutes and is gaining experience to facilitate the use of opportunistically available cloud resources. We present a snap shot of this infrastructure and its operation at the time of the CHEP2015 conference.
doi:10.1088/1742-6596/664/2/022012 fatcat:z6hhawosqfg63hdc2ruo6odm7m

CMS Workflow Execution Using Intelligent Job Scheduling and Data Access Strategies

Khawar Hasham, Antonio Delgado Peris, Ashiq Anjum, Dave Evans, Stephen Gowdy, José M. Hernandez, Eduardo Huedo, Dirk Hufnagel, Frank van Lingen, Richard McClatchey, Simon Metson
2011 IEEE Transactions on Nuclear Science  
Complex scientific workflows can process large amounts of data using thousands of tasks. The turnaround times of these workflows are often affected by various latencies such as the resource discovery, scheduling and data access latencies for the individual workflow processes or actors. Minimizing these latencies will improve the overall execution time of a workflow and thus lead to a more efficient and robust processing environment. In this paper, we propose a pilot job based infrastructure
more » ... has intelligent data reuse and job execution strategies to minimize the scheduling, queuing, execution and data access latencies. The results have shown that significant improvements in the overall turnaround time of a workflow can be achieved with this approach. The proposed approach has been evaluated, first using the CMS Tier0 data processing workflow, and then simulating the workflows to evaluate its effectiveness in a controlled environment.
doi:10.1109/tns.2011.2146276 fatcat:sax2bk5jabh77f2bbug73paw34

HEPCloud, a New Paradigm for HEP Facilities: CMS Amazon Web Services Investigation

Burt Holzman, Lothar A. T. Bauerdick, Brian Bockelman, Dave Dykstra, Ian Fisk, Stuart Fuess, Gabriele Garzoglio, Maria Girone, Oliver Gutsche, Dirk Hufnagel, Hyunwoo Kim, Robert Kennedy (+6 others)
2017 Computing and Software for Big Science  
Historically, high energy physics computing has been performed on large purpose-built computing systems. These began as single-site compute facilities, but have evolved into the distributed computing grids used today. Recently, there has been an exponential increase in the capacity and capability of commercial clouds. Cloud resources are highly virtualized and intended to be able to be flexibly deployed for a variety of computing tasks. There is a growing nterest among the cloud providers to
more » ... onstrate the capability to perform large-scale scientific computing. In this paper, we discuss results from the CMS experiment using the Fermilab HEPCloud facility, which utilized both local Fermilab resources and virtual machines in the Amazon Web Services Elastic Compute Cloud. We discuss the planning, technical challenges, and lessons learned involved in performing physics workflows on a large-scale set of virtualized resources. In addition, we will discuss the economics and operational efficiencies when executing workflows both in the cloud and on dedicated resources.
doi:10.1007/s41781-017-0001-9 fatcat:o3ca6mtu5bbdbkck7xy7u6enp4

Titelseiten

2020 Beiträge zur Geschichte der Deutschen Sprache und Literatur  
AA 91 und Cpg 339 113 Jan-Dirk Müller Christian Buhr: Zweifel an der Liebe.  ...  Katharina Böhnert: Sprachgeschichte 107 Christoph Fasbender Nadine Hufnagel: Verwandtschaft im Reinhart Fuchs.  ... 
doi:10.1515/bgsl-2020-frontmatter1 fatcat:fb2myciqxvalffzwinni7ljmeq

SAT0502 LONG-TERM OBSERVATIONAL SAFETY SURVEILLANCE OF GOLIMUMAB TREATMENT FOR POLYARTICULAR JUVENILE IDIOPATHIC ARTHIRTIS—AN INTERIM ANALYSIS

G. Horneff, A. Zimmer, K. Minden, T. Hospach, F. Weller-Heinemann, S. Hansmann, J. Kuemmerle-Deschner, M. Fasshauer, N. Hofmann, H. Koessel, I. Foeldvari, S. Mrusek (+9 others)
2020 Annals of the Rheumatic Diseases  
: None declared, Dirk Foell Grant/research support from: Novartis, Sobi, Pfizer, Speakers bureau: Novartis, Sobi, Normi Brueck: None declared, Prasad Oommen Consultant of: Novartis, Frank Dressler: None  ...  Hofmann: None declared, Hans Koessel: None declared, Ivan Foeldvari Consultant of: Novartis, Sonja Mrusek: None declared, Daniel Windschall Speakers bureau: Abbvie, Nils Onken: None declared, Markus Hufnagel  ...  Ivan Foeldvari Consultant of: Novartis, Sonja Mrusek: None declared, Daniel Windschall Speakers bureau: Abbvie, Nils Onken: None declared, Markus Hufnagel: None declared, Dirk Foell Grant/research support  ... 
doi:10.1136/annrheumdis-2020-eular.3589 fatcat:xe5l7lrgojab3jrwizhhd5hqq4

Inhaltsverzeichnis

2002 Nietzscheforschung  
Zarathustra -Sisyphos Zur Nietzsche-Rezeption Albert Camus' 247 Hans-Gerd von Seggern (Berlin) Allen Tinten-Fischen feind Metaphern der Melancholie in Nietzsches Also sprach Zarathustra 263 Dirk  ...  Carl Ludwig Nietzsche und Friedrich Nietzsche 131 Johann Figi (Wien) "Dionysos und der Gekreuzigte" Nietzsches Identifikation und Konfrontation mit zentralen religiösen ,Figuren' 147 Erwin Hufnagel  ... 
doi:10.1524/nifo.2002.9.jg.5 fatcat:ggwtcuvl4rdvjgyccoomm7v544

Did you know?

1995 Nature Medicine  
Valiathan had worked with Charles Hufnagel, at Georgetown University Medical Center in Washington, DC. Hufnagel (now deceased) is the person who in 1951 developed the first mechanical valve.  ...  This year's prizewinners are Dirk Bootsma and jan H. J. Hoeijmakers, professors at the Erasmus University of Rotterdam, The Netherlands, noted for their studies of the DNA repair system; Peter N.  ... 
doi:10.1038/nm0295-109 fatcat:4okcxn7ye5b3zbsaffr4cpk4pe
« Previous Showing results 1 — 15 out of 180 results