Graphic-Card Cluster for Astrophysics (GraCCA) -- Performance Tests
arXiv:0707.2991 · doi:10.1016/j.newast.2007.12.005
Abstract
In this paper, we describe the architecture and performance of the GraCCA system, a Graphic-Card Cluster for Astrophysics simulations. It consists of 16 nodes, with each node equipped with 2 modern graphic cards, the NVIDIA GeForce 8800 GTX. This computing cluster provides a theoretical performance of 16.2 TFLOPS. To demonstrate its performance in astrophysics computation, we have implemented a parallel direct N-body simulation program with shared time-step algorithm in this system. Our system achieves a measured performance of 7.1 TFLOPS and a parallel efficiency of 90% for simulating a globular cluster of 1024K particles. In comparing with the GRAPE-6A cluster at RIT (Rochester Institute of Technology), the GraCCA system achieves a more than twice higher measured speed and an even higher performance-per-dollar ratio. Moreover, our system can handle up to 320M particles and can serve as a general-purpose computing cluster for a wide range of astrophysics problems.
Accepted for publication in New Astronomy
References in corpus (12)
- High Performance Direct Gravitational N-body Simulations on Graphics Processing Units -- II: An implementation in CUDA
- GRAPE-6: The massively-parallel special-purpose computer for astrophysical particle simulation
- Statistics of N-body Simulations I. Equal Masess Before Core Collapse
- Performance Analysis of Direct N-Body Algorithms on Special-Purpose Supercomputers
- A New Parallel N-body Gravity Solver: TPM
- GRAPE-6A: A single-card GRAPE-6 for parallel PC-GRAPE cluster system
- Post-Collapse evolution of globular clusters
- Particle-Mesh code for cosmological simulations
- Systolic and Hyper-Systolic Algorithms for the Gravitational N-Body Problem, with an Application to Brownian Motion
- N-Body Simulations on GPUs
- An efficient parallel algorithm for O(N^2) direct summation method and its variations on distributed-memory parallel machines
- Performance analysis of direct N-body algorithms for astrophysical simulations on distributed systems
Cited by in corpus (12)
- NBODY6++GPU: Ready for the gravitational million-body problem
- High Performance Direct Gravitational N-body Simulations on Graphics Processing Units -- II: An implementation in CUDA
- GAMER: a GPU-Accelerated Adaptive Mesh Refinement Code for Astrophysics
- Teraflop per second gravitational lensing ray-shooting using graphics processing units
- Soliton Oscillations and Revised Constraints from Eridanus II of Fuzzy Dark Matter
- Astrophysical Supercomputing with GPUs: Critical Decisions for Early Adopters
- Expansion Techniques for Collisionless Stellar Dynamical Simulations
- Accelerating Radio Astronomy Cross-Correlation with Graphics Processing Units
- Magnetohydrodynamics with GAMER
- Directionally Unsplit Hydrodynamic Schemes with Hybrid MPI/OpenMP/GPU Parallelization in AMR
- GAMER with out-of-core computation
- Efficient magnetohydrodynamic simulations on graphics processing units with CUDA