Speaker
Wesley Ketchum
(University of Chicago)
Description
Graphical Processing Units (GPUs) have evolved into highly parallel, multi-threaded, multicore powerful processors with high memory bandwidth, driven by the high demand of 3-D graphics. As such, GPUs are used in a variety of intensive computing applications. The combination of highly parallel architecture and high memory bandwidth makes GPUs a potentially promising technology for effective real-time processing for High Energy Physics (HEP) experiments. However, not much is known for their performance in real-time applications that require low latency, such as the trigger for HEP experiments. We will describe our R&D project with the goal to study the timing performance of GPU technology for possible low latency applications, performing basic operations as well as some more advanced HEP trigger algorithms (such as fast tracking or calorimetric clustering). We will present some preliminary results on timing measurements, comparing the performance of a CPU versus a GPU using NVIDIA's CUDA general purpose parallel computing architecture, carried out at CDF's Level-2 trigger test stand. These studies will provide performance benchmarks for future studies to investigate the potential and limitations of GPUs for future real-time applications in HEP experiments.
Authors
Denis Bastieri
(University of Padova and INFN)
Donatella Lucchesi
(University of Padova and INFN)
Giorgio Urso
(ORMA Software)
Kristian Hahn
(FNAL)
Matteo Bauce
(University of Padova and INFN)
Pierluigi Catastini
(FNAL)
Silvia Amerio
(INFN Padova)
Tiehui Liu
(FNAL)
Wesley Ketchum
(University of Chicago)
Young-Kee Kim
(University of Chicago, FNAL)