Michele Michelotto
(Universita e INFN (IT))
14/10/2014, 13:30
Computing & Batch Services
The traditional architecture for High Energy Physics is x86-64 but in the community there is interest in processor more efficient in term of computing power per Watt. I'll show my
measurement on ARM and Avoton processor.
I'll conclude with some measurements on candidate for fast benchmark that are requested by the physics community, mostyl to measure the performance of machine in cloud.
Jerome Belleman
(CERN)
14/10/2014, 14:00
Computing & Batch Services
The CERN Batch System comprises 4000 worker nodes, 60 queues and offers
a service for various types of large user communities. In light of the
developments driven by the Agile Infrastructure and the more demanding
processing requirements, it will be faced with increasingly challenging
scalability and flexibility needs.
Last HEPiX, we presented the results of our evaluation of SLURM,...
Samir Cury Siqueira
(California Institute of Technology (US))
14/10/2014, 14:30
Computing & Batch Services
Hardware benchmarks are often relative to the target application. In CMS sites, new technologies, mostly processors, need to be evaluated on an yearly basis. A framework was developed at the Caltech CMS Tier-2 to benchmark compute nodes with one of the most CPU-intensive CMS workflows - The Tier-0 Reconstruction.
The benchmark is a CMS job that reports the results to a central database...
Todd Tannenbaum
(Univ of Wisconsin-Madison, Wisconsin, USA)
14/10/2014, 15:00
Computing & Batch Services
The goal of the HTCondor team is to to develop, implement, deploy, and evaluate mechanisms and policies that support High Throughput Computing (HTC) on large collections of distributively owned computing resources. Increasingly, the work performed by the HTCondor developers is being driven by its partnership with the High Energy Physics (HEP) community. This presentation will provide an...
Brian Paul Bockelman
(University of Nebraska (US))
14/10/2014, 15:20
Computing & Batch Services
One of the most critical components delivered by the Open Science Grid (OSG) software team is the compute element, or the OSG-CE. At the core of the CE itself is the gatekeeper software for translating grid pilot jobs into local batch system jobs. OSG is in the process of migrating from the Globus gatekeeper to the HTCondor-CE, supported by the HTCondor team.
The HTCondor-CE provides an...
James Frey
14/10/2014, 16:10
Computing & Batch Services
An important use of HTCondor is as a scalable, reliable interface for
jobs destined for other scheduling systems.
These include Grid intefaces to batch systems (Globus, CREAM, ARC) and
Cloud services (EC2, OpenStack, GCE).
The High Energy Physics community has been a major user of this
functionality and has driven its development.
This talk will provide an overview of HTCondor's Grid...
