A Fast Scalable Implicit Solver for Nonlinear Time-Evolution Earthquake City Problem on Low-Ordered Unstructured Finite Elements with Artificial Intelligence and Transprecision Computing

Ichimura, Tsuyoshi; Fujita, Kohei; Yamaguchi, Takuma; Naruse, Akira; Wells, Jack; Schulthess, T. C.; Straatsma, Tjerk P.; Zimmer, Christopher; Martinasso, Maxime; Nakajima, Kengo; Hori, Muneo; Wijerathne, Lalith

doi:10.1109/sc.2018.00052

Cited by 38 publications

(25 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, we conduct a numerical experiment on an internal structure optimization problem using image-based wave propagation modeling. Instead of using the proposed method, conventional optimization approaches using large number of nodes in parallel (e.g., using our SC18 Gordon Bell Prize Finalist wave propagation solver [2] scalable up to full Summit [3]) can be used; however, the developed optimization method can extract prior information efficiently using deep learning and thus is capable of acquiring the optimized solution more robustly in a shorter time. For example, in the application problem in Section 3, a very good solution is estimated in very short time using only 2048 samples out of the prior knowledge data base of 470775 samples with two-step sampling (sampling rate of 0.00435(=2048/470775)).…”

Section: Providing Past Information and Archiving Of Resultsmentioning

confidence: 99%

“…3b). Thus, although it is possible to reduce time of the optimization computation using fast wave propagation methods using large number of compute nodes in parallel (e.g., SC18 Gordon Bell Prize Finalist solver [2] scalable up to full Summit [3]), it is difficult to obtain reasonable solutions for difficult optimization problems such as the problem targeted in this study when using conventional optimization methods. Furthermore, the problem sizes are often too small for efficient computation on very large number of compute nodes, and thus the acceleration is limited even for easier optimization problems.…”

Section: Numerical Experimentsmentioning

confidence: 99%

See 1 more Smart Citation

Fast Multi-Step Optimization with Deep Learning for Data-Centric Supercomputing

Ichimura

Fujita

Yamaguchi

et al. 2020

Proceedings of the 2020 4th International Conference on High Performance Compilation, Computing and Communications

Self Cite

View full text Add to dashboard Cite

Following the improvement in data acquisition technology and in analysis capability, we develop an optimization method for datacentric supercomputing, which can utilize large-scale data. Prior information of the solution of these optimization problems is often available, and the use of such information is expected to improve the efficiency of the optimization process and the accuracy of its solution. Targeting use on supercomputing environments such as Big Data and Extreme-scale Computing (BDEC) resources, we develop a fast parameter optimization method that combines datacentric fast simulation methods and deep learning. This method comprises multiple steps, i.e., an approximate solution is obtained in a short time using prior information on many compute nodes, and the approximate solution is refined using a small number of compute nodes. Thus, optimum solutions can be obtained in a short time based on the required accuracy, even on many compute-node environments without fast interconnects. The developed method is expected to provide useful knowledge for related optimization problems computed on distributed ubiquitous computing resources using large observation data obtained by the Internet of Things (IoT) and fifth-generation (5G) networks.

show abstract

Section: Providing Past Information and Archiving Of Resultsmentioning

confidence: 99%

Section: Numerical Experimentsmentioning

confidence: 99%

Fast Multi-Step Optimization with Deep Learning for Data-Centric Supercomputing

Ichimura

Fujita

Yamaguchi

et al. 2020

Proceedings of the 2020 4th International Conference on High Performance Compilation, Computing and Communications

Self Cite

View full text Add to dashboard Cite

show abstract

“…We used lower precision variable format FP21 27 to overcome this problem. FP21 is a 21‐bit floating point number format and has lower precision and smaller data size compared with double precision variable (64 bit) and single precision variable (32 bit).…”

Section: Methodsmentioning

confidence: 99%

“…Compute unified device architecture (CUDA), a dedicated parallel computing platform for GPU programming, is widely used in the development of GPU applications. There are some researches on accelerating seismic response analysis using GPU computing with CUDA implementation (e.g., for the FDM, 24 the discontinuous Galerkin method, 25 the spectral element method, 26 and the FEM 27 ). In these researches, CPU‐based massively parallel computing methods for 3D ground motion simulation were extended so that they are accelerated by fully exploiting GPUs.…”

Section: Introductionmentioning

confidence: 99%

Development of regional simulation of seismic ground‐motion and induced liquefaction enhanced by GPU computing

Kusakabe

Fujita

Ichimura

et al. 2020

Earthq Engng Struct Dyn

Self Cite

View full text Add to dashboard Cite

Much research has been conducted for physics-based ground-motion simulation to reproduce seismic response of soil and structures precisely and to mitigate damages caused by earthquakes. We aimed at enabling physics-based groundmotion simulations of complex three-dimensional (3D) models with multiple materials, such as a digital twin (high-fidelity 3D model of the physical world that is constructed in cyberspace). To perform one case of such simulation requires high computational cost and it is necessary to perform a number of simulations for the estimation of parameters or consideration of the uncertainty of underground soil structure data. To overcome this problem, we proposed a fast simulation method using graphics processing unit computing that enables a simulation with small computational resources. We developed a finite-elementbased method for large-scale 3D seismic response analysis with small programming effort and high maintainability by using OpenACC, a directive-based parallel programming model. A lower precision variable format was introduced to achieve further speeding up of the simulation. For an example usage of the developed method, we applied the developed method to soil liquefaction analysis and conducted two sets of simulations that compared the effect of countermeasures against soil liquefaction: grid-form ground improvement to strengthen the earthquake resistance of existing houses and replacement of liquefiable backfill soil of river wharves for seismic reinforcement of the wharf structure. The developed method accelerates the simulation and enables us to quantitatively estimate the effect of countermeasures using the high-fidelity 3D soil-structure models on a small cluster of computers.

show abstract

“…The major computation-consuming procedure in seismic simulation is solving a large-scale nonlinear equation. MOTHRA [3], an urban seismic problem solver, is proposed in this paper and designed for a situation where both the ground and urban building are targeted. This complex model introduces worse characteristics for computation such as poor convergence.…”

Section: Application Introductionmentioning

confidence: 99%

Research trend of large-scale supercomputers and applications from the TOP500 and Gordon Bell Prize

Zheng

2020

Sci. China Inf. Sci.

View full text Add to dashboard Cite

China is playing an increasingly important role in international supercomputing. In highperformance computing domain, there are two famous awards: The TOP500 list for the fastest 500 supercomputers in the world and the Gordon Bell Prize for the best HPC (high-performance computing) applications. China has been awarded in both TOP500 list and Gordon Bell Prize. In this paper, we review the supercomputers in the latest TOP500 list and seven Gordon Bell Prize applications to show the research trend of the large-scale supercomputers and applications. The first trend we observe is that heterogeneous architectures are widely used in the construction of supercomputing systems. The second trend is that artificial intelligence applications are expected to become one of the main stream applications of supercomputing. The third trend is that applying heterogeneous systems to complex scientific simulation applications will be more difficult.

show abstract

A Fast Scalable Implicit Solver for Nonlinear Time-Evolution Earthquake City Problem on Low-Ordered Unstructured Finite Elements with Artificial Intelligence and Transprecision Computing

Cited by 38 publications

References 11 publications

Fast Multi-Step Optimization with Deep Learning for Data-Centric Supercomputing

Fast Multi-Step Optimization with Deep Learning for Data-Centric Supercomputing

Development of regional simulation of seismic ground‐motion and induced liquefaction enhanced by GPU computing

Research trend of large-scale supercomputers and applications from the TOP500 and Gordon Bell Prize

Contact Info

Product

Resources

About