The Paderborn Center for Parallel Computing (PC²) has been selected by Intel to host a computer cluster that uses Intel’s Xeon processor with its Arria 10 FPGA software development platform.
The German university of Paderborn based in the city of the same name will use this cluster to further research into Field-Programmable Gate Arrays (FPGA) and Manycore architectures.
The Paderborn Center for Parallel Computing (PC²), one of the university’s scientific institutes, will house the cluster. The centre focuses its research efforts on advancing ‘interdisciplinary research in parallel and distributed computing with innovative computer systems. In addition to research into these architectures the centre operates several high-performance cluster systems with up to 10'000 cores to support researchers at Paderborn University and North Rhine-Westfalia with HPC services.
These new Intel server clusters connect Intel Xeon processors with an in-package field-programmable gate array (FPGA) via the platform’s high-speed QuickPath interconnect. The Intel FPGA can be programmed to serve as a workload-optimised accelerator offering substantial performance, and energy-efficiency advantages.
This is a key research area for the computational scientists at PC2as the centre focuses on computing systems research for energy-efficient high-performance computing with an emphasis on heterogeneous and accelerated computing with Field-Programmable Gate Arrays (FPGAs) and Manycore architectures.
While there has been previous research into the use of FPGAs as accelerators for HPC research, this new server from Intel fuses the technology from the acquisition of Altera from December 2015 with Intel Xeon processors.
This solution is suitable for a number of application domains, such as machine learning, data encryption, compression, image processing and video-stream processing. The platform also an ideal experimentation platform for innovative operating system or computing systems research, that focuses on novel approaches to integrating CPUs with accelerators at the software and hardware level.
‘We are very happy to have been selected by Intel as one of only two academic sites worldwide to host a cluster based on Intel Xeon processors and Intel Arria 10 FPGAs . Our computing centre has a strong research background in accelerating demanding applications with FPGAs. The availability of these systems allows us to further expand our leadership in this area and – as a next step – bring Intel FPGA accelerators from the lab to HPC production systems,’ commented Professor Christian Plessl, director of the Paderborn Center for Parallel Computing.
Currently, the Paderborn Center is working on accelerating applications including theoretical physics, material sciences and machine learning with FPGAs. This work is in collaboration with scientists from the application areas. In addition, novel domain-specific programming approaches for FPGAs are being developed to simplify the use of FPGAs for developers without a hardware design background.
While the use of FPGAs has yet to see widespread adoption across cluster computing Intel is hoping to generate more interest in the technology through the Intel Hardware Accelerator Research Program. Through this program researchers both in Germany and across the world can get access to the cluster to perform their own research.
‘We are looking forward to collaborate with Intel and other members of the Hardware Accelerator Research Program on using FPGA acceleration for emerging HPC and data center workloads. By provisioning access to the system to a large number of researchers, we are also gathering experience in how to manage systems with FPGA accelerators in a multi-user setting and for handling parallel applications that use multiple servers with FPGAs. This experience is crucial for deploying systems with FPGAs at scale,’ explains Dr Tobias Kenter, senior researcher and FPGA expert at the Paderborn Center for Parallel Computing.
