EPJ Web Conf.
Volume 214, 201923rd International Conference on Computing in High Energy and Nuclear Physics (CHEP 2018)
|Number of page(s)||9|
|Section||T5 - Software development|
|Published online||17 September 2019|
The ALICE Analysis Framework for LHC Run 3
European Organization for Nuclear Research (CERN), Genève,
2 Istituto Nazionale di Fisica Nucleare (INFN), Italy
3 Johann-Wolfgang-Goethe University and Frankfurt Institute for Advances Studies (FIAS), Frankfurt, Germany
* e-mail: firstname.lastname@example.org
Published online: 17 September 2019
The ALICE experimentatthe LHC (CERN)iscurrently developinganew software framework designed for Run3: detector and software will havetocope with Pb–Pb collision rates 100 times higher than today, leadingtothe combinationofcore Online-Offline operations intoasingle framework called O2. The analysis code is expectedtorunonafew large Analysis Facilities counting 20k cores and sustaining a 100 GB/s throughput: this requiresaconjoint effort between the definitionofthe data format, the configurationofthe Analysis Facilities and the developmentofthe Analysis Framework. Wepresent the prototypeofanew Analysis Object Data format basedontimeframes and optimized for continuous readout. Such formatisdesigned tobeextensible and transported efficiently over the network. Wealso present the first iterationofthe Analysis Framework, basedonthe O2 Data Processing Layer and leveraging message passing acrossatopologyofprocesses. Wewill also illustrate the implementation and benchmarkingofacompatibility layer designedtomitigate the transition from the current event-oriented analysis modeltothe new time-oriented one. Finally,wewill giveastatus reportonthe integrationofthe Analysis Framework and Analysis Facilities for Run3into the current organized analysis model in ALICE.
© The Authors, published by EDP Sciences, 2019
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.