High-Performance Small-Scale Simulation of Star Clusters Evolution on Cray XD1

TL;DR

This paper demonstrates a highly efficient small-scale N-body simulation of star cluster evolution on a Cray XD1 system, achieving over 57% of peak performance with 64k particles, which is significantly higher than previous results.

Contribution

The paper presents a novel high-performance implementation of N-body simulation for small particle counts on a Cray XD1, utilizing a scalable 2D parallelization scheme and low-latency communication.

Findings

Achieved 2.03 Tflops, 57.7% of peak performance.

Surpassed previous efficiency records for small N-body simulations.

Demonstrated the importance of communication network in parallel performance.

Abstract

In this paper, we describe the performance of an $N$-body simulation of star cluster with 64k stars on a Cray XD1 system with 400 dual-core Opteron processors. A number of astrophysical $N$-body simulations were reported in SCxy conferences. All previous entries for Gordon-Bell prizes used at least 700k particles. The reason for this preference of large numbers of particles is the parallel efficiency. It is very difficult to achieve high performance on large parallel machines, if the number of particles is small. However, for many scientifically important problems the calculation cost scales as $O(N^{3.3})$, and it is very important to use large machines for relatively small number of particles. We achieved 2.03 Tflops, or 57.7% of the theoretical peak performance, using a direct $O(N^2)$ calculation with the individual timestep algorithm, on 64k particles. The best efficiency previously reported on similar calculation with 64K or smaller number of particles is 12% (9 Gflops) on Cray T3E-600 with 128 processors. Our implementation is based on highly scalable two-dimensional parallelization scheme, and low-latency communication network of Cray XD1 turned out to be essential to achieve this level of performance.