high performance computing on graphics processing units: hgpu.org

In this paper we describe a single-node, double precision FPGA implementation of the Conjugate Gradient algorithm in the context of Lattice Quantum Chromodynamics. As a benchmark of our proposal we invert numerically the Dirac-Wilson operator on a 4-dimensional grid on a Xilinx Zynq Ultrascale+ evaluation board. In our implementation we separate software/hardware parts in such a way that the entire multiplication by the Dirac operator is performed in hardware, and the rest of the algorithm runs on an ARM core. We find out that the FPGA implementation offers a comparable performance with that obtained using current CPU or Intel’s many core Xeon Phi accelerators. A possible multiple node FPGA-based system is discussed and we argue that power-efficient HPC systems can be implemented using FPGA devices only.