Parallel computing in experimental mechanics and optical measurement: A review (II)

Wang, Tianyi; Kemao, Qian

doi:10.1016/j.optlaseng.2017.06.002

Cited by 37 publications

(21 citation statements)

References 135 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The proposed new algorithms for global (or FE) DIC may prove useful particularly (i) for evolution problems, where one operator is assembled and factorized once for all Gauss‐Newton iterations and for each time step, and (ii) for stereo DIC, where projector gradients may evolve during iterations. To go even further in algorithmic efficiency, these solvers could be coupled with high‐performance computing tools …”

Section: Resultsmentioning

confidence: 99%

Classic and inverse compositional Gauss‐Newton in global DIC

Passieux

Bouclier

2019

Numerical Meth Engineering

View full text Add to dashboard Cite

Summary Today, effective implementations of digital image correlation (DIC) are based on iterative algorithms with constant linear operators. A relevant idea of the classic finite element (or, more generally, global) DIC solver consists in replacing the gradient of the deformed state image with that of the reference image, so as to obtain a constant operator. Different arguments (small strains, small deformations, equality of the two gradients close to the solution, etc) have been given in the literature to justify this approximation, but none of them are fully accurate. Indeed, the convergence of the optimization algorithm has to be investigated from its ability to produce descent directions. Through such a study, this paper attempts to explain why this approximation works and what is its domain of validity. Then, an inverse compositional Gauss‐Newton implementation of finite element DIC is proposed as a cost‐effective and mathematically sound alternative to this approximation.

show abstract

Section: Resultsmentioning

confidence: 99%

Classic and inverse compositional Gauss‐Newton in global DIC

Passieux

Bouclier

2019

Numerical Meth Engineering

View full text Add to dashboard Cite

show abstract

“…The proposed framework is developed using NVIDIA Tesla K20C card that exhibits a generic, scalable architecture and is portable onto other GPU variants offered by NVIDIA. The heterogeneous realization of 2D‐DIC is already demonstrated by Huang et al and Wang and Kemao . However, the method of deploying CPU‐GPU for computations in this paper is different.…”

Section: Introductionmentioning

confidence: 83%

“…Due to high execution time, this measurement technique is primarily used as a post‐processing image analysis tool. Recent works in literature focus on DIC's performance improvement using graphics processing unit (GPU) (which comprises multiple in‐built processor cores [of the order of thousands] within a single IC). While a computation exhibiting high level of parallelism is expected to achieve good speedup on a GPU, parallelizing two‐dimensional DIC (2D‐DIC) on GPUs is not straightforward.…”

Section: Introductionmentioning

confidence: 99%

High‐speed, two‐dimensional digital image correlation algorithm using heterogeneous (CPU‐GPU) framework

Thiagu

Subramanian²,

Nasre

2020

Strain

View full text Add to dashboard Cite

Two-dimensional digital image correlation (2D-DIC) is an experimental technique used to measure in-plane displacement of a test specimen. Real-time measurement of full-field displacement data is challenging due to enormous computational load of the algorithm. In order to improve the computational speed, the focus of recent research works has been on the approach of parallelization across subsets within image pairs using graphics processing unit (GPU). But alternate GPU-based parallelization approaches to improve the performance of this algorithm as per the order of data processing have not been explored.To address this research gap, our method utilizes parallelism within a subset as well as across subsets for each computation step in an iteration cycle. A heterogeneous (CPU-GPU) framework in combination with a pyramid-based initial values estimation for subsets (in parallel) is proposed in this work. The precompute steps of the proposed framework are implemented using CPU, whereas the main iterative steps are realized using GPU. It is demonstrated that the overall computational speed of the proposed heterogeneous framework improves by ≈ 9× compared to a sequential CPU-based implementation for a pair of gray-scale images with a resolution of 588 × 2, 048 pixels. As an important milestone, feasibility to measure deformations in real time (≤1 s) is manifested in this study.

show abstract

“…Por otra parte, la medición experimental óptica y mecánica requiere de procesar grandes cantidades de datos y a alta velocidad, con el propósito de obtener una respuesta en tiempo real. Qian Kemao et al (Wang and Kemao, 2018) cubren en su revisión de literatura varias plataformas y técnicas utilizadas en el cómputo paralelo que se emplean en medición experimental, entre las que destacan el uso de CPUs, GPUs, FPGAs. En esta revisión se expondrán los trabajos más significativos en el área del procesamiento digital de señales implementados en procesadores multinúcleo, con las diferentes técnicas de programación, se cubrirá la implementación en GPUs y sistemas heterogéneos de GPU-CPU-FPGA y finalmente se mostrara los trabajos más recientes en la computadora de placa única Parallella, computadora que unifica tres diferentes tecnologías a baja potencia (Olofsson, Nordström and Ul-Abdin, 2015).…”

Section: Adaptación De La Implementación De Algoritmos De Pds En La Eunclassified

Implementación de Algoritmos de Procesamiento Digital de Señales en Hardware Paralelo: Artículo de revisión

Martínez

Aceves

Argüelles

et al. 2018

CULCyT

View full text Add to dashboard Cite

show abstract

Parallel computing in experimental mechanics and optical measurement: A review (II)

Cited by 37 publications

References 135 publications

Classic and inverse compositional Gauss‐Newton in global DIC

Classic and inverse compositional Gauss‐Newton in global DIC

High‐speed, two‐dimensional digital image correlation algorithm using heterogeneous (CPU‐GPU) framework

Implementación de Algoritmos de Procesamiento Digital de Señales en Hardware Paralelo: Artículo de revisión

Contact Info

Product

Resources

About