Development of high-level synthesis tools such as OpenCL SDK for FPGAs enables us to design accelerators for scientific applications that can take advantage of flexibility and efficiency of FPGAs. However, the available OpenCL SDKs only support the standard floating-point (FP) formats. In this paper, we present the performance evaluation of high precision FP operations, which are currently not supported in OpenCL, on recent FPGAs. By using a mechanism to call a custom design from an OpenCL kernel, we evaluate the performance of a sample application in high precision FP format binary128. We found that the sustained performance of our design in binary128 on Intel Arria10 and Stratix10 is 19 and 71 Gflops, respectively.

In this paper, we describe the design and performance of GRAPE-8 accelerator processor for gravitational N-body simulations. It is designed to evaluate gravitational interaction with cutoff between particles. The cutoff function is useful for schemes like TreePM or Particle-Particle Particle-Tree, in which gravitational force is divided to short-range and longrange components. A single GRAPE-8 processor chip integrates 48 pipeline processors. The effective number of floating-point operations per interaction is around 40. Thus the peak performance of a single GRAPE-8 processor chip is 480 Gflops. A GRAPE-8 processor card houses two GRAPE-8 chips and one FPGA chip for PCI-Express interface. The total power consumption of the board is 46W. Thus, theoretical peak performance per watt is 20.5 Gflops/W. The effective performance of the total system, including the host computer, is around 5Gflops/W. This is more than a factor of two higher than the highest number in the current Green500 list.

As an entry for the 2002 Gordon Bell performance prize, we report the performance achieved on the GRAPE-6 system for a simulation of the early evolution of the protoplanet-planetesimal system of the Uranus-Neptune region. GRAPE-6 is a special-purpose computer for astrophysical N-body calculations. The present configuration has 2048 custom pipeline chips, each containing six pipeline processors for the calculation of gravitational interactions between particles. Its theoretical peak performance is 63.4 Tflops. The actual performance obtained was 29.5 Tflops, for a simulation of the early evolution of outer Solar system with 1.8 million planetesimals and two massive protoplanets.