Boosting Event Building Performance using Infiniband FDR for the CMS Upgrade

2 Jun 2014, 16:50
Graanbeurszaal (Beurs van Berlage)


Beurs van Berlage

Oral Data-processing: 3b) Trigger and Data Acquisition Systems III.b Trigger & DAQ


Andrew Kevin Forrest (CERN)


As part of the CMS upgrade during CERN’s shutdown period (LS1), the CMS data acquisition system is incorporating Infiniband FDR technology to boost event building performance for operation from 2015 onwards. Infiniband promises to provide substantial increase in data transmission speeds compared to the older 1GE network used during the 2009-2013 LHC run. Several options exist to end user developers when choosing a foundation for software upgrades, including the uDAPL (DAT Collaborative) and Infiniband verbs libraries (OFED). Due to advances in technology, the CMS data acquisition system will be able to achieve the required throughput of 100 kHz with increased event sizes while downsizing the number of nodes by using a combination of 10GE, 40GE and 56 GB Infiniband FDR. This paper presents the analysis and results of a comparison between GE and Infiniband solutions as well as a look at how they integrate into an event building architecture, while preserving the portability, scalability, efficiency and the deterministic latency expected in a high end data acquisition network.

Primary authors


Andre Georg Holzner (Univ. of California San Diego (US)) Dr Attila Racz (CERN) Aymeric Arnaud Dupont (CERN) Benjamin Stieger (CERN) Carlos Nunez Barranco Fernandez (CERN) Christian Deldicque (CERN) Christoph Paus (Massachusetts Inst. of Technology (US)) Christoph Schwick (CERN) Dominique Gigi (CERN) Emilio Meschi (CERN) Frank Glege (CERN) Frans Meijers (CERN) Georgiana Lavinia Darlea (Massachusetts Inst. of Technology (US)) Guillelmo Gomez Ceballos Retuerto (Massachusetts Inst. of Technology (US)) Hannes Sakulin (CERN) James Gordon Branson (Univ. of California San Diego (US)) Mr Jan Veverka (Massachusetts Inst. of Technology (US)) Dr Jeroen Hegeman (CERN) Konstanty Sumorok (Massachusetts Inst. of Technology (US)) Lorenzo Masetti (CERN) Dr Marc Dobson (CERN) Marco Pieri (Univ. of California San Diego (US)) Olivier Chaze (CERN) Petr Zejdl (CERN) Remi Mommsen (Fermi National Accelerator Lab. (US)) Robert Gomez-Reino Garrido (CERN) Samim Erhan (Univ. of California Los Angeles (US)) Sergio Cittolin (Univ. of California San Diego (US)) Srecko Morovic (CERN) Tomasz Adrian Bawej (CERN) Ulf Behrens (DESY) Vivian O'Dell (Fermi National Accelerator Lab. (US))

Presentation Materials