A conflict-free, path-level parallelization approach for sequential simulation algorithms

Rasera, Luiz Gustavo; Machado, Péricles Lopes; Costa, João Felipe Coimbra Leite

doi:10.1016/j.cageo.2015.03.016

Cited by 12 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In comparison with other reported parallelization strategies, particularly Rasera et al (2015), the efficiency obtained is comparable only in the larger cases of SISIM with 64 or 128 maximum neighbours. However, the results reported must not be compared directly, since different base codes and parameters were used.…”

Section: Discussionmentioning

confidence: 72%

“…Path-level parallelization is based on the partition of the domain into zones that can be handled by different processes or threads. Rasera et al (2015), based on the strategy proposed by Vargas et al (2007), developed a novel path-level conflict-free parallelization for the SGS method with promising future results in the SIS context. In the same context, Mariethoz (2010) and posteriorly Tahmasebi et al (2012) developed a master-slave strategy that distributes the grid nodes among several processors, using a multi-core cluster or a graphical unit processor (GPU).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A path-level exact parallelization strategy for sequential simulation

Peredo¹,

Baeza

Ortíz

et al. 2018

Computers & Geosciences

View full text Add to dashboard Cite

Sequential Simulation is a well known method in geostatistical modelling. Following the Bayesian approach for simulation of conditionally dependent random events, Sequential Indicator Simulation (SIS) method draws simulated values for K categories (categorical case) or classes defined by K different thresholds (continuous case). Similarly, Sequential Gaussian Simulation (SGS) method draws simulated values from a multivariate Gaussian field. In this work, a path-level approach to parallelize SIS and SGS methods is presented. A first stage of rearrangement of the simulation path is performed, followed by a second stage of parallel simulation for non-conflicting nodes. A key advantage of the proposed parallelization method is to generate identical realizations as with the original non-parallelized methods. Case studies are presented using two sequential simulation codes from GSLIB: SISIM and SGSIM. Execution time and speedup results are shown for large-scale domains, with many categories and maximum kriging neighbours in each case, achieving high speedup results in the best scenarios using 16 threads of execution in a single machine.

show abstract

Section: Discussionmentioning

confidence: 72%

Section: Introductionmentioning

confidence: 99%

A path-level exact parallelization strategy for sequential simulation

Peredo¹,

Baeza

Ortíz

et al. 2018

Computers & Geosciences

View full text Add to dashboard Cite

show abstract

“…In a similar fashion, the multiple point statistical methods have also used the effect of iterations on removing the artifacts (Pourfard et al 2017;. It should be noted that the sequential algorithms can be parallel using different strategies which are not discussed in this review chapter (Rasera et al 2015;Tahmasebi et al 2012b).…”

Section: Simulated Annealingmentioning

confidence: 99%

Multiple Point Statistics: A Review

Tahmasebi

2018

Handbook of Mathematical Geosciences

View full text Add to dashboard Cite

Geostatistical modeling is one of the most important tools for building an ensemble of probable realizations in earth science. Among them, multiple-point statistics (MPS) has recently gone under a remarkable progress in handling complex and more realistic phenomenon that can produce large amount of the expected uncertainty and variability. Such progresses are mostly due to the recent increase in more advanced computational techniques/power. In this review chapter, the recent important developments in MPS are thoroughly reviewed. Furthermore, the advantages and disadvantages of each method are discussed as well. Finally, this chapter provides a brief review on the current challenges and paths that might be considered as future research.

show abstract

“…We choose to parallelize at realization level because it introduces minimal modifications in the code, which is one of our main objectives. Although the node level is the finest-grained scheme, we leave this task as a future work to explore with other technologies (accelerators and co-processors), nested-parallelism with threads or task-based parallelism [20]. The parallel pragma is added in the loop of line 2 from Algorithm 5.…”

Section: (V23)mentioning

confidence: 99%

Acceleration of the Geostatistical Software Library (GSLIB) by code optimization and hybrid parallel programming

Peredo

Ortíz

Herrero

2015

Computers & Geosciences

View full text Add to dashboard Cite

The Geostatistical Software Library (GSLIB) has been used in the geostatistical community for more than thirty years. It was designed as a bundle of sequential Fortran codes, and today it is still in use by many practitioners and researchers. Despite its widespread use, few attempts have been reported in order to bring this package to the multi-core era. Using all CPU resources, GSLIB algorithms can handle large datasets and grids, where tasks are compute and memory intensive. In this work, a methodology is presented to accelerate GSLIB applications using code optimization and hybrid parallel processing, specifically for compute-intensive applications. Minimal code modifications are added decreasing as much as possible the elapsed time of execution of the studied routines. If multi-core processing is available, the user can activate OpenMP directives to speed up the execution using all resources of the CPU. If multi-node processing is available, the execution is enhanced using MPI messages between the compute nodes. Four case studies are presented: experimental variogram calculation, kriging estimation, sequential gaussian and indicator simulation. For each application, three scenarios (small, large and extra large) are tested using a desktop environment with 4 CPU-cores and a multi-node server with 128 CPU-nodes. Elapsed times, speedup and efficiency results are shown.

show abstract

A conflict-free, path-level parallelization approach for sequential simulation algorithms

Cited by 12 publications

References 23 publications

A path-level exact parallelization strategy for sequential simulation

A path-level exact parallelization strategy for sequential simulation

Multiple Point Statistics: A Review

Acceleration of the Geostatistical Software Library (GSLIB) by code optimization and hybrid parallel programming

Contact Info

Product

Resources

About