GPU acceleration for evolutionary topology optimization of continuum structures using isosurfaces

Martnez-Frutos, Jess; Herrero-Prez, David

doi:10.1016/j.compstruc.2016.10.018

Cited by 45 publications

(21 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent works on similar problems [7] indicate that the true potential of element-wise solution approaches lies in the additional computational efficiency gains by parallel implementations for modern HPC hardware architectures. Recent works on similar problems [7] indicate that the true potential of element-wise solution approaches lies in the additional computational efficiency gains by parallel implementations for modern HPC hardware architectures.…”

Section: Discussion and Outlookmentioning

confidence: 99%

“…For a serial implementation, the combination of element-wise residual assembly with EBE-based preconditioners significantly reduces the computational memory requirements at a trade-off of additional computation cost. Recent works on similar problems [7] indicate that the true potential of element-wise solution approaches lies in the additional computational efficiency gains by parallel implementations for modern HPC hardware architectures. For large scale problems the additional work can be compensated by memory savings and better relative parallelization speedup rates than for conventional factorization approaches.…”

Section: Discussion and Outlookmentioning

confidence: 99%

“…Due to the ongoing trend of the exponentially increasing gap between CPU and memory performance [1,2], and modern parallel computing architectures, Element-by-Element (EBE) solution techniques [3] could become competing approaches to solve systems of linear equations in large scale simulations [4]. Regular finite element grids that frequently occur in topology optimization problems [5,6] seem particularly suitable for element-wise solution approaches [7].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Topology optimization combined with element‐by‐element solution techniques

Sala

Kuhn

Sator

et al. 2019

Proc Appl Math and Mech

View full text Add to dashboard Cite

Topology optimization approaches are commonly used for design problems involving physical phenomena related to solid mechanics, acoustics, electromagnetism, fluid mechanics, and combinations thereof. In computational models of these physical phenomena, the field variables are commonly approximated using spatial discretizations within the domain using the Finite Element Method. Even for topology design problems in which the field variables must only satisfy linear state equations, the storage and solution of the resulting global system of equations can become a computational bottleneck. In this contribution, we investigate a topology optimization approach in which the Solid Isotropic Material with Penalization (SIMP) method is combined with element-wise solution approaches, in order to reduce computational memory requirements.

show abstract

Section: Discussion and Outlookmentioning

confidence: 99%

Section: Discussion and Outlookmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Topology optimization combined with element‐by‐element solution techniques

Sala

Kuhn

Sator

et al. 2019

Proc Appl Math and Mech

View full text Add to dashboard Cite

show abstract

“…The use of GPUs for nongraphical applications is growing rapidly because of the high computing capacity of these graphic cards for massive parallel processing (also known as data-level parallelism) at a reasonable cost. 41 The GPU follows the single instruction and multiple data programming model. For efficiency, GPU uses a single program called kernel to process multiple data items in parallel.…”

Section: Gpu Computingmentioning

confidence: 99%

A parallel computational approach for similarity search using Bloom filters

Chauhan

Batra

2018

Computational Intelligence

View full text Add to dashboard Cite

Finding similar items in a large and unstructured dataset is a challenging task in many applications of data science, such as searching, indexing, and retrieval. With the increasing data volume and demand for real time responses, similarity search has gained much consideration. In this paper, a parallel computational approach for similarity search using Bloom filters (PCASSB) has been proposed, which uses Bloom filter for the representation of features of document and comparison with user's query. Query features are stored in integer query array (IQA), an array of integer. The PCASSB, an approximate similarity search technique, has been implemented on graphics processing unit with compute unified device architecture as the programming platform. To compute the similarity score between query and reference dataset, Dice coefficient has been used as a baseline method. The accuracy of the results generated by PCASSB is compared with the baseline method and other state‐of‐the‐art methods. The experimental results show that the proposed technique is quite effective in processing large number of text documents as it takes less computational time.

show abstract

“…Discrete methods, such as Evolutionary Structural Optimization (ESO) (Xie and Steven (1993)) and Level-Set (LS) (Osher and Sethian (1988)), do not relax the problem and hence restrict the design variables to the boundaries of the range {0, 1}. While some effort using SIMP and LS methods have been solved with GPU architectures (Aissa et al (2014)), only one recent study exists with ESO methods (Martinez-Frutos and Herrero-Perez (2017)) and only with structural optimization.…”

Section: Introductionmentioning

confidence: 99%

Multi-physics bi-directional evolutionary topology optimization on GPU-architecture

Munk

Kipouros

Vio

2018

Engineering with Computers

View full text Add to dashboard Cite

Topology optimization has proven to be viable for use in the preliminary phases of real world design problems. Ultimately, the restricting factor is the computational expense since a multitude of designs need to be considered. This is especially imperative in such fields as aerospace, automotive and biomedical, where the problems involve multiple physical models, typically fluids and structures, requiring excessive computational calculations. One possible solution to this is to implement codes on massively parallel computer architectures, such as Graphics Processing Units (GPUs). The present work investigates the feasibility of a GPU-implemented Lattice Boltzmann method for multi-physics topology optimization for the first time. Noticeable differences between the GPU implementation and a Central Processing Unit (CPU) version of the code are observed and the challenges associated with finding feasible solutions in a computational efficient manner are discussed and solved here, for the first time on a multi-physics topology optimization problem. The main goal of this paper is to speed up the topology optimization process for multi-physics problems without restricting the design domain, or sacrificing considerable performance in the objectives. Examples are compared with both standard CPU and various levels of numerical precision GPU codes to better illustrate the advantages and disadvantages of this implementation. A structural and fluid objective topology optimization problem is solved to vary the dependence of the algorithm on the GPU, extending on the previous literature that has only considered structural objectives of non-design dependent load problems. The results of this work indicate some discrepancies between GPU and CPU implementations that have not been seen before in the literature and are imperative to the speed-up of multi-physics topology optimization algorithms using GPUs.

show abstract

GPU acceleration for evolutionary topology optimization of continuum structures using isosurfaces

Cited by 45 publications

References 55 publications

Topology optimization combined with element‐by‐element solution techniques

Topology optimization combined with element‐by‐element solution techniques

A parallel computational approach for similarity search using Bloom filters

Multi-physics bi-directional evolutionary topology optimization on GPU-architecture

Contact Info

Product

Resources

About