English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Over the last few years the GPGPU (General-Purpose computing on GraphicsProcessing Units) paradigm represented a remarkable development in the world ofcomputing. Computing for High-Energy Physics is no exception: several workshave demonstrated the effectiveness of the integration of GPU-based systems inhigh level trigger of different experiments. On the other hand the use of GPUsin the low level trigger systems, characterized by stringent real-timeconstraints, such as tight time budget and high throughput, poses severalchallenges. In this paper we focus on the low level trigger in the CERN NA62experiment, investigating the use of real-time computing on GPUs in thissynchronous system. Our approach aimed at harvesting the GPU computing power tobuild in real-time refined physics-related trigger primitives for the RICHdetector, as the the knowledge of Cerenkov rings parameters allows to buildstringent conditions for data selection at trigger level. Latencies of allcomponents of the trigger chain have been analyzed, pointing out thatnetworking is the most critical one. To keep the latency of data transfer taskunder control, we devised NaNet, an FPGA-based PCIe Network Interface Card(NIC) with GPUDirect capabilities. For the processing task, we developedspecific multiple ring trigger algorithms to leverage the parallel architectureof GPUs and increase the processing throughput to keep up with the high eventrate. Results obtained during the first months of 2016 NA62 run are presentedand discussed.

GPU-based Real-time Triggering in the NA62 Experiment