A Performance Comparison of Different Graphics Processing Units Running Direct N-Body Simulations
arXiv:1304.1966 · doi:10.1016/j.cpc.2013.07.005
Abstract
Hybrid computational architectures based on the joint power of Central Processing Units and Graphic Processing Units (GPUs) are becoming popular and powerful hardware tools for a wide range of simulations in biology, chemistry, engineering, physics, etc.. In this paper we present a comparison of performance of various GPUs available on market when applied to the numerical integration of the classic, gravitational, N-body problem. To do this, we developed an OpenCL version of the parallel code (HiGPUs) to use for these tests, because this version is the only apt to work on GPUs of different makes. The main general result is that we confirm the reliability, speed and cheapness of GPUs when applied to the examined kind of problems (i.e. when the forces to evaluate are dependent on the mutual distances, as it happens in gravitational physics and molecular dynamics). More specifically, we find that also the cheap GPUs built to be employed just for gaming applications are very performant in terms of computing speed also in scientific applications and, although with some limitations in central memory and in bandwidth, can be a good choice to implement a machine for scientific use at a very good performance to cost ratio.
arXiv commentThis paper has been submitted for publication to Computer Physics Communications It consists of 26 pages, with 6 tables and 10 figures
References in corpus (19)
- On the variation of the Initial Mass Function
- The cosmological simulation code GADGET-2
- Star cluster ecology IVa: Dissection of an open star cluster---photometry
- Accelerating NBODY6 with Graphics Processing Units
- A Very Fast and Momentum-Conserving Tree Code
- Dissipationless Formation and Evolution of the Milky Way Nuclear Star Cluster
- Mass segregation and fractal substructure in young massive clusters: (I) the McLuster code and method calibration
- Performance Analysis of Direct N-Body Algorithms on Special-Purpose Supercomputers
- N-body simulations of gravitational dynamics
- BRIDGE: A Direct-tree Hybrid N-body Algorithm for Fully Self-consistent Simulations of Star Clusters and their Parent Galaxies
- SAPPORO: A way to turn your graphics cards into a GRAPE-6
- 6th and 8th Order Hermite Integrator for N-body Simulations
- A fully parallel, high precision, N-body code running on hybrid computing platforms
- NBSymple, a double parallel, symplectic N-body code running on Graphic Processing Units
- An efficient parallel tree-code for the simulation of self-gravitating systems
- A comparison between Fast Multipole Algorithm and Tree-Code to evaluate gravitational forces in 3-D
- MYRIAD: A new N-body code for simulations of Star Clusters
- The Dense Stellar Systems Around Galactic Massive Black Holes
- A 3D radiative transfer framework: XIII. OpenCL implementation
Cited by in corpus (11)
- A fully parallel, high precision, N-body code running on hybrid computing platforms
- Dynamical friction in cuspy galaxies
- Compact Binary Coalescences: Astrophysical Processes and Lessons Learned
- GOTHIC: Gravitational oct-tree code accelerated by hierarchical time step controlling
- The secular evolution of the Kuiper belt after a close stellar encounter
- Intermediate mass black holes in globular clusters: effects on jerks and jounces of millisecond pulsars
- Rapid Mass segregation in small stellar clusters
- GraviDy, a GPU modular, parallel direct-summation body integrator: Dynamics with softening
- Direct -body code on low-power embedded ARM GPUs
- Direct N-body application on low-power and energy-efficient parallel architectures
- Sapporo2: A versatile direct -body library