Multi-GPU-based Swendsen–Wang multi-cluster algorithm with reduced data traffic

Komura, Yukihiro

doi:10.1016/j.cpc.2015.04.025

Cited by 3 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several directions that we did not explore in this study. First, we did not explore the cluster algorithms [48][49][50]. The strange behavior of the PRNGs in critical Ising systems is discovered in the process of our investigation of dynamic processes of critical Ising systems, where the Metropolis algorithm is a must.…”

Section: Discussionmentioning

confidence: 99%

“…The strange behavior of the PRNGs in critical Ising systems is discovered in the process of our investigation of dynamic processes of critical Ising systems, where the Metropolis algorithm is a must. In the future, PRNGs in critical Ising systems simulated by cluser algorithms, either Swendsen-Wang type [48,49], or Wolff type [50], will be investigated. It would be interesting to know whether PRNGs behave similarly or differently on large critical Ising lattices simulated with cluster algorithms other than with the Metropolis algorithm.…”

Section: Discussionmentioning

confidence: 99%

“…However, programs run on CPU are very flexible and easy to develop, so many alternative algorithms to Metropolis, e.g. cluster algorithms [48][49][50], have been developed to combat the speed problem. Cluster algorithms may be used in addition to Metropolis algorithm in the future (more on this in the next paragraph).…”

Section: J Stat Mech (2023) 073203 To Misbehave In Critical Ising Sys...mentioning

confidence: 99%

See 2 more Smart Citations

Critical Ising system testing of high-quality random number generators

et al. 2023

View full text Add to dashboard Cite

Specialized hardware implemented on field programmable gate array (FPGA) is used to simulate critical 2D Ising lattices up to 40962. Four mainstream, high-quality pseudorandom number generators (PRNGs) including Xorshift, Mersenne Twister, Xorwow, and ALFG are tested on this system, and three of them are found to misbehave with different degree of confidence levels. It is observed that PRNGs with quality issues tend to misbehave in critical Ising systems and the ones with bigger issues start to misbehave in smaller critical Ising systems and vice versa. The size at which a PRNG misbehaves is proposed as a measure of a PRNG’s quality.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: J Stat Mech (2023) 073203 To Misbehave In Critical Ising Sys...mentioning

confidence: 99%

See 1 more Smart Citation

Critical Ising system testing of high-quality random number generators

et al. 2023

View full text Add to dashboard Cite

show abstract

“…However, we can renumber the cluster labels to sequence labels by using the method shown in Fig. 4 in [14], for example.…”

Section: Generalized Gpu-based Cluster Labeling Algorithmmentioning

confidence: 99%

A generalized GPU-based connected component labeling algorithm

Komura¹

2016

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a generalized GPU-based connected component labeling (CCL) algorithm that can be applied to both various lattices and to non-lattice environments in a uniform fashion. We extend our recent GPU-based CCL algorithm without the use of conventional iteration to the generalized method. As an application of this algorithm, we deal with the bond percolation problem. We investigate bond percolation on the honeycomb and triangle lattices to confirm the correctness of this algorithm. Moreover, we deal with bond percolation on the Bethe lattice as a substitute for a network structure, and demonstrate the performance of this algorithm on those lattices.

show abstract