The Terabit/s Super-Fragment Builder and Trigger Throttling System for the Compact Muon Solenoid Experiment at CERN

Abstract

The Data Acquisition System of the Compact Muon Solenoid experiment at the Large Hadron Collider reads out event fragments of an average size of 2 kilobytes from around 650 detector front-ends at a rate of up to 100 kHz. The first stage of event-building is performed by the Super-Fragment Builder employing custom-built electronics and a Myrinet optical network. It reduces the number of fragments by one order of magnitude, thereby greatly decreasing the requirements for the subsequent event-assembly stage. By providing fast feedback from any of the front-ends to the trigger, the Trigger Throttling System prevents buffer overflows in the front-end electronics due to variations in the size and rate of events or due to back-pressure from the down-stream event-building and processing. This paper reports on new performance measurements and on the recent successful integration of a scaled-down setup of the described system with the trigger and with front-ends of all major sub-detectors. The on-going commissioning of the full-scale system is discussed. It reduces the number of fragments by one order of magnitude, thereby greatly decreasing the requirements for the subsequent event-assembly stage. By providing fast feedback from any of the front-ends to the trigger, the Trigger Throttling System prevents buffer overflows in the front-end electronics due to variations in the size and rate of events or due to back-pressure from the down-stream event-building and processing. This paper reports on new performance measurements and on the recent successful integration of a scaled-down setup of the described system with the trigger and with front-ends of all major subdetectors. The on-going commissioning of the full-scale system is discussed.

The CMS experiment at the CERN LHC

“…For random traffic the network efficiency is approximately 60%, due to head-of-line blocking. An event building throughput of about 300 MBbyte/s per node is achieved for variable sized fragments with a nominal average of 2 kBytes by using two rails [210]. Hence, the sustained aggregate throughput through the FED-builder stage is ≈1.4 Tbit/s, satisfying the CMS DAQ requirements.…”

Soft error recovery during operation of the compact muon solenoid experiment

“…As a result, a major effort went into quantifying the effects expected at the Large Hadron Collider (LHC) [3], and extreme care was taken in the design of the experiments to minimize the impact of SEEs on their operation. At the Compact Muon Solenoid (CMS) experiment, one of the techniques used to mitigate the effects of SEEs was to incorporate an explicit recovery procedure into its operational state machine [4].…”

“…As described before, CMS was expecting to experience SEEs. Signals were built into the hardware design to reset these electronics [4] and algorithms were implemented to look for soft errors [11] that could result from SEEs. During 2011, however, it became clear that both the detection and reset methods needed to be revisited and expanded to be able to fix all recoverable errors seen by all subsystems in the CMS detector.…”

The central trigger control system of the CMS experiment at CERN

“…7 below) from the detector and DAQ partitions or, in cases where this is not feasible because of time constraints, from electronic emulators. Status signals from the many parts of the CMS detector are grouped into one signal per detector partition in special electronic modules by taking the most severe condition found at its inputs and passing it on to its output ("Fast Merging Modules", FMM [14]). The receiving unit first waits until a new signal state becomes steady for 75 ns, in order to suppress spurious pulses.…”