An FPGA Platform for Hyperscalers

FPGAs (Field Programmable Gate Arrays) are making their way into data centers (DC). They are used as accelerators to boost the compute power of individual server nodes and to improve the overall power efficiency. Meanwhile, DC infrastructures are being redesigned to pack ever more compute capacity into the same volume and power envelopes. This redesign leads to the disaggregation of the server and its resources into a collection of standalone computing, memory, and storage modules.To embrace this evolution, we developed a platform that decouples the FPGA from the CPU of the server by connecting the FPGA directly to the DC network. This proposal turns the FPGA into a disaggregated standalone computing resource that can be deployed at large scale into emerging hyperscale data centers.This paper describes an infrastructure which integrates 64 FPGAs (Kintex* UltraScale* XCKU060) from Xilinx* in a 19" × 2U chassis, and provides a bi-sectional bandwidth of 640 Gb/s. The platform is designed for cost effectiveness and makes use of hot-water cooling for optimized energy efficiency. As a result, a DC rack can fit 16 platforms, for a total of 1024 FPGAs + 16 TB of DRR4 memory.

[1]  Andreas Herkersdorf,et al.  Enabling FPGAs in Hyperscale Data Centers , 2015, 2015 IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing and 2015 IEEE 12th Intl Conf on Autonomic and Trusted Computing and 2015 IEEE 15th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom).

[2]  Dimitrios Soudris,et al.  A survey on reconfigurable accelerators for cloud computing , 2016, 2016 26th International Conference on Field Programmable Logic and Applications (FPL).

[3]  Hari Angepat,et al.  A cloud-scale acceleration architecture , 2016, 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO).

[4]  Christoph Hagleitner,et al.  Network-attached FPGAs for data center applications , 2016, 2016 International Conference on Field-Programmable Technology (FPT).

[5]  Andreas Herkersdorf,et al.  Disaggregated FPGAs: Network Performance Comparison against Bare-Metal Servers, Virtual Machines and Linux Containers , 2016, 2016 IEEE International Conference on Cloud Computing Technology and Science (CloudCom).

[6]  James R. Larus,et al.  A reconfigurable fabric for accelerating large-scale datacenter services , 2014, 2014 ACM/IEEE 41st International Symposium on Computer Architecture (ISCA).

[7]  Heiner Giefers,et al.  Analyzing the energy-efficiency of dense linear algebra kernels by power-profiling a hybrid CPU/FPGA system , 2014, 2014 IEEE 25th International Conference on Application-Specific Systems, Architectures and Processors.