The main purpose of the Central processing facility (CEP) is to correlate the station data and deliver a data product which can be further processed by the user.
The Central Processing Facility (CEP) is divided in three sections: an on-line section for processing real-time data streams from the stations, a storage section collecting the processed data streams and making the resulting datasets available to the third section: the off-line processing. The monitoring and control system is responsible to control CEP and allocates resources to particular observations, which can run in parallel with each other.
The on-line processing section consists of 1.5 Blue Gene/P (BG/P) racks, where the data of the stations are correlated and subsequently reduced. Parallel to the BG/P resources, a general purpose cluster is available for auxiliary processing and in particular for real-time analysis, tuning and/or model creation tasks. The results of those tasks are typically used as control data for the processing applications running on the BG/P platform. The resulting data streams from the on-line processing sections are collected in the temporary storage subsystem.
The input section contains the connections to the stations (through the Wide Area Network). The stations sent their data in logical packages, each containing a time-frequency window of a single voltage beam. Each input node will receive data from the stations and run a data handling application that will buffer the input data and synchronise its output stream with the other input nodes based on the timestamps contained in the data.
Large amounts of processing power and internal interconnection bandwidth are provided through the BG/P supercomputer; a peak processing power of 34 TFlops is available for the processing tasks. This processing power in combination with the IO capabilities of BG/P allows for a correlator capable to handle all LOFAR baselines properly.
The storage system provides disk space for the collection of data streams and storage of complete observation datasets for off-line processing. This storage is intended for temporary usage (typically 5 days) until the final data products are generated and archived or the raw data itself is exported or archived. Access to data in the storage system is through storage clients that have access to the metadata and file locations.
Finally a general purpose Linux cluster is used for the off-line processing. The off-line processing section offers general-purpose processing power and high bandwidth interconnections to the off-line processing applications. The largest part of this cluster is a "normal" Linux cluster computer optimised on cost per Flop.
The size of this section will be determined based on the applications performance, especially the self-calibration of imaging data for the EOR and surveys. Additional off-line processing power will be available in GRID networks, thus potentially providing extra processing power from remote sites. GRID networks also provide the basic infrastructure for data access and data export to user groups.
At the end of the pipeline, an archiving system will be available for long term storage or exporting the data.
For the astronomy application the following main observing modes will be supported:
A major advantage of the LOFAR Central Processor is that multiple applications and modes can be run concurrently.
Central Processor facility hardware architecture overview.