Efficiency of linked cell algorithms

Welling, Ulrich; Germano, Guido

doi:10.1016/j.cpc.2010.11.002

Cited by 44 publications

(31 citation statements)

References 31 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Periodic boundary conditions are enforced by applying the minimum-image convention on s. Welling and Germano [18] have claimed that using such shift vectors is less efficient than using ghost cells to resolve periodicity, albeit without demonstrating this experimentally. In the current implementation, when computing the sorted interactions or traversing a pairwise Verlet list, the shift vector is added to the particle positions outside the main loop, incurring only a negligible overhead.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Pairwise verlet lists: Combining cell lists and verlet lists to improve memory locality and parallelism

Gonnet

2011

J Comput Chem

View full text Add to dashboard Cite

Verlet lists, which are commonly used in many particle-based simulations, are not suited for modern, shared-memory parallel multicore architectures. In this article, we introduce pairwise Verlet lists: local Verlet lists containing only interacting particle pairs between a pair of neighboring computational cells. We show that these pairwise Verlet lists are more efficient and scale much better than the traditional global Verlet list, both on a single processor as well as on multiple shared-memory cores. The improved performance on a single core makes them an interesting option for distributed-memory simulations as well.

show abstract

Section: Resultsmentioning

confidence: 99%

“…[17]), which was shown by Welling and Germano [18] and Fomin [14] to be advantageous in conjunction with the sorted interaction described in Ref. [11], yet goes a step Computational cells (squares left) and particle data (rectangles right) in a) traditional cell lists as described in Ref.…”

Section: Introductionmentioning

confidence: 92%

Pairwise verlet lists: Combining cell lists and verlet lists to improve memory locality and parallelism

Gonnet

2011

J Comput Chem

View full text Add to dashboard Cite

show abstract

“…This makes the search far more efficient than a particlepair based search. Another implication of the much lower number of (now cluster-) pairs, is that advanced search algorithms, such as interaction sorting [18,19], will not help and a simple search algorithm performs well. Finally, the cost of interaction calculation is proportional to the total number of pair interactions calculated.…”

Section: Computational Costmentioning

confidence: 99%

A flexible algorithm for calculating pair interactions on SIMD architectures

Páll

Hess

2013

Computer Physics Communications

574

400

View full text Add to dashboard Cite

Calculating interactions or correlations between pairs of particles is typically the most time-consuming task in particle simulation or correlation analysis. Straightforward implementations using a double loop over particle pairs have traditionally worked well, especially since compilers usually do a good job of unrolling the inner loop. In order to reach high performance on modern CPU and accelerator architectures, singleinstruction multiple-data (SIMD) parallelization has become essential. Avoiding memory bottlenecks is also increasingly important and requires reducing the ratio of memory to arithmetic operations. Moreover, when pairs only interact within a certain cut-off distance, good SIMD utilization can only be achieved by reordering input and output data, which quickly becomes a limiting factor. Here we present an algorithm for SIMD parallelization based on grouping a fixed number of particles, e.g. 2, 4, or 8, into spatial clusters. Calculating all interactions between particles in a pair of such clusters improves data reuse compared to the traditional scheme and results in a more efficient SIMD parallelization. Adjusting the cluster size allows the algorithm to map to SIMD units of various widths. This flexibility not only enables fast and efficient implementation on current CPUs and accelerator architectures like GPUs or Intel MIC, but it also makes the algorithm future-proof. We present the algorithm with an application to molecular dynamics simulations, where we can also make use of the effective buffering the method introduces.

show abstract

“…The number of distance checks performed by an algorithm is a good predictor of its performance [21]. Table I shows the average number of distance checks performed using each method, with N3 on and off, as well as the SIMD inefficiency for AVX2 and KNC intrinsic implementations (i.e.…”

Section: Projection Sorting Vs Verlet Listsmentioning

confidence: 99%