Global Optimization of Surface Warpage for Inverse Design of Ultra-Thin Electronic Packages Using Tensor Train Decomposition

Selvanayagam, Cheryl; Duong, Pham Luu Trung; Wilkerson, Brett; Raghavan, Nagarajan

doi:10.1109/access.2022.3170455

Cited by 4 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors applied this approach to the problem of optimizing the weights of neural networks in the framework of reinforcement learning problems in (Sozykin et al, 2022) and to the QUBO problem in (Nikitin et al, 2022). A similar optimization approach was also considered in (Selvanayagam et al, 2022) with practical applications of the method for optimizing the housings of electronic devices and in (Shetty et al, 2022) for optimizing the movement in space of robotic arms.…”

Section: Tensor Based Optimization Methodsmentioning

confidence: 99%

“…In the last few years, several new discrete optimization algorithms based on the TT-format have been proposed (Sozykin et al, 2022;Selvanayagam et al, 2022;Shetty et al, 2022;Chertkov et al, 2022a). However, the development of new tensor train-based approaches for optimization is possible based on recently proposed methods for working with probability distributions and sampling in the TT-format (Novikov normal font (a, b, c, .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

PROTES: Probabilistic Optimization with Tensor Sampling

Batsheva¹,

Chertkov²,

Ryzhakov³

et al. 2023

Preprint

View full text Add to dashboard Cite

We develop new method PROTES for optimization of the multidimensional arrays and discretized multivariable functions, which is based on a probabilistic sampling from a probability density function given in the low-parametric tensor train format. We tested it on complex multidimensional arrays taken, among other, from real-world applications, including unconstrained binary optimization and optimal control problems, for which the possible number of elements is up to 2 100 elements. In numerical experiments, both on analytic model functions and on complex problems, our algorithm outperform existing popular discrete optimization methods (Particle Swarm Optimization, Covariance Matrix Adaptation, Differential Evolution and others). Moreover, we take the same set of hyperparameters of our algorithm for all numerical applications.

show abstract

Section: Tensor Based Optimization Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

PROTES: Probabilistic Optimization with Tensor Sampling

Batsheva¹,

Chertkov²,

Ryzhakov³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Due to the accurate and fast predictive capabilities of models created based on ML, it has been introduced into the modeling and simulation of integrated packages. For example, Selvanayagam et al [ 40 , 41 ] partitioned an 8-RDLs interposer into 3 × 3 regions, then established surrogate models that linked the copper ratio in each layer within each region to the warpage in TCT condition, ultimately optimizing the global package warpage.…”

Section: Introductionmentioning

confidence: 99%

An RDL Modeling and Thermo-Mechanical Simulation Method of 2.5D/3D Advanced Package Considering the Layout Impact Based on Machine Learning

Wu,

Wang,

et al. 2023

Micromachines

View full text Add to dashboard Cite

The decreasing-width, increasing-aspect-ratio RDL presents significant challenges to the design for reliability (DFR) of an advanced package. Therefore, this paper proposes an ML-based RDL modeling and simulation method. In the method, RDL was divided into blocks and subdivided into pixels of metal percentage, and the RDL was digitalized as tensors. Then, an ANN-based surrogate model was built and trained using a subset of tensors to predict the equivalent material properties of each block. Lastly, all blocks were transformed into elements for simulations. For validation, line bending simulations were conducted on an RDL, with the reaction force as an accuracy indicator. The results show that neglecting layout impact caused critical errors as the substrate thinned. According to the method, the reaction force error was 2.81% and the layout impact could be accurately considered with 200 × 200 elements. For application, the TCT maximum temperature state simulation was conducted on a CPU chip. The simulation indicated that for an advanced package, the maximum stress was more likely to occur in RDL rather than in bumps; both RDL and bumps were critically impacted by layouts, and RDL stress was also impacted by vias/bumps. The proposed method precisely concerned layout impacts with few resources, presenting an opportunity for efficient improvement.

show abstract