Aggressively Parallel Algorithms of Collision and Nearest Neighbor Detection for GPU Planetesimal Disk Simulation

Details Aggressively Parallel Algorithms of Collision and Nearest Neighbor Detection for GPU Planetesimal Disk Simulation Aggressively Parallel Algorithms of Collision and Nearest Neighbor Detection for GPU Planetesimal Disk Simulation

Sep 2008

adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=2008dps....40.1105q&link_type=abstract

American Astronomical Society, DPS meeting #40, #11.05; Bulletin of the American Astronomical Society, Vol. 40, p.402

Statistics

Computation

Scientific paper

Planetesimal and dust dynamical simulations require collision and nearest neighbor detection. A brute force implementation for sorting interparticle distances requires O(N2) computations for N particles, limiting the numbers of particles that have been simulated. Parallel algorithms recently developed for the GPU (graphics processing unit), such as the radix sort, can run as fast as O(N) and sort distances between a million particles in a few hundred milliseconds. We introduce improvements in collision and nearest neighbor detection algorithms and how we have incorporated them into our efficient parallel 2nd order democratic heliocentric method symplectic integrator written in NVIDIA's CUDA for the GPU.

Affiliated with

Also associated with

No associations

Rating

Aggressively Parallel Algorithms of Collision and Nearest Neighbor Detection for GPU Planetesimal Disk Simulation does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Aggressively Parallel Algorithms of Collision and Nearest Neighbor Detection for GPU Planetesimal Disk Simulation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Aggressively Parallel Algorithms of Collision and Nearest Neighbor Detection for GPU Planetesimal Disk Simulation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-1436547