Dynamic Strip Partitioning Method Oriented Parallel Computing for Construction of Delaunay Triangulation

Qi, Lin; Shen, Jie; Guo, Lishuai; Zhou, Tong

doi:10.3724/sp.j.1047.2012.00055

Cited by 2 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Armstrong et al [7] carried on interpolation by the dividing method column by column. Based on the method of regular band division in the traditional D-TIN parallel algorithm, Qi et al [8] proposed a balanced and efficient partitioning method of the cluster distribution points-set by using the method of the dynamic stripe. Qian et al [9] presented a strip data equalization method according to the computational overhead considering the complexity of interpolation algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Data Partitioning Method for Parallel Digital Terrain Analysis

Dou

Miao

2015

Journal of Algorithms & Computational Technology

View full text Add to dashboard Cite

Parallel computing of the intensive data is one of the effective methods to improve high-performance computation of massive data. The purpose of this paper is to study the method of data partitioning and scheduling which is geared to the strategy of parallel computation facing to the distribution of data in sequence. According to the features of the intensive data computation, this paper puts forward the concept of data granularity, return granularity and saturation. The parallel computing and scheduling model facing to the distribution of data in sequence is given based on these concepts. Considering that the startup and shutdown of data distribution has some overhead, the distribution of a data block in sequence and the calculation of another data block can be done at the same time. While the total time of the calculation is not decreasing with the increase of the number of data blocks divided, there exists an optimal value. Through analyzing the slope algorithm of Digital Terrain Analysis (DTA), the optimal solution of data partitioning and the best number of computing nodes is presented in this paper. The results of the experiment show that the theoretical analysis and the results of the experiment are basically consistent.

show abstract

Section: Introductionmentioning

confidence: 99%

“…By the formula (8), the speedup also has to do with the data granularity and return granularity of a task, the data distribution time, and the overhead of starting processes.…”

mentioning

confidence: 99%

A Data Partitioning Method for Parallel Digital Terrain Analysis

Dou

Miao

2015

Journal of Algorithms & Computational Technology

View full text Add to dashboard Cite

show abstract

“…Load balancing is one of the most important parts of parallel programming and can affect the performance of the whole algorithm [26]. Most existing algorithms use the static scheduling strategy, which partitions the LiDAR dataset and assigns them to computation units before the algorithm running [13,27,28]. This is useful when the shape of the LiDAR dataset is regular.…”

Section: Problemsmentioning

confidence: 99%

A Hybrid Process/Thread Parallel Algorithm for Generating DEM from LiDAR Points

Ren

Chen

et al. 2017

IJGI

View full text Add to dashboard Cite

Airborne Light Detection and Ranging (LiDAR) is widely used in digital elevation model (DEM) generation. However, the very large volume of LiDAR datasets brings a great challenge for the traditional serial algorithm. Using parallel computing to accelerate the efficiency of DEM generation from LiDAR points has been a hot topic in parallel geo-computing. Generally, most of the existing parallel algorithms running on high-performance clusters (HPC) were in process-paralleling mode, with a static scheduling strategy. The static strategy would not respond dynamically according to the computation progress, leading to load unbalancing. Additionally, because each process has independent memory space, the cost of dealing with boundary problems increases obviously with the increase in the number of processes. Actually, these two problems can have a significant influence on the efficiency of DEM generation for larger datasets, especially for those of irregular shapes. Thus, to solve these problems, we combined the advantages of process-paralleling with the advantages of thread-paralleling, forming a new idea: using process-paralleling to achieve a flexible schedule and scalable computation, using thread-paralleling inside the process to reduce boundary problems. Therefore, we proposed a hybrid process/thread parallel algorithm for generating DEM from LiDAR points. Firstly, at the process level, we designed a parallel method (PPDB) to accelerate the partitioning of LiDAR points. We also proposed a new dynamic scheduling strategy to achieve better load balancing. Secondly, at the thread level, we designed an asynchronous parallel strategy to hide the cost of LiDAR points' reading. Lastly, we tested our algorithm with three LiDAR datasets. Experiments showed that our parallel algorithm had no influence on the accuracy of the resultant DEM. At the same time, our algorithm reduced the conversion time from 112,486 s to 2342 s when we used the largest dataset (150 GB). The PPDB was parallelizable and the new dynamic scheduling strategy achieved a better load balancing. Furthermore, the asynchronous parallel strategy reduced the impact of LiDAR points reading. When compared with the traditional process-paralleling algorithm, the hybrid process/thread parallel algorithm improved the conversion efficiency by 30%.

show abstract

Dynamic Strip Partitioning Method Oriented Parallel Computing for Construction of Delaunay Triangulation

Abstract: % &'()+& ,-. & / 0 ) , &(12 0 &)3 4 0 .)4 .

Cited by 2 publications

References 2 publications

A Data Partitioning Method for Parallel Digital Terrain Analysis

A Data Partitioning Method for Parallel Digital Terrain Analysis

A Hybrid Process/Thread Parallel Algorithm for Generating DEM from LiDAR Points

Contact Info

Product

Resources

About

Dynamic Strip Partitioning Method Oriented Parallel Computing for Construction of Delaunay Triangulation

Abstract: % &'()*+& ,-. & / 0 ) , &(1*2 0 &)3 4 0 .)4 .

Cited by 2 publications

References 2 publications

A Data Partitioning Method for Parallel Digital Terrain Analysis

A Data Partitioning Method for Parallel Digital Terrain Analysis

A Hybrid Process/Thread Parallel Algorithm for Generating DEM from LiDAR Points

Contact Info

Product

Resources

About

Abstract: % &'()+& ,-. & / 0 ) , &(12 0 &)3 4 0 .)4 .