# domain decomposition

Published articles for domain decomposition.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## DrainSinkhorn: Instance-Resident Batched Entropic Optimal Transport on GPUs

DevFeed: [DrainSinkhorn: Instance-Resident Batched Entropic Optimal Transport on GPUs](<https://devfeed.tech/articles/drainsinkhorn-instance-resident-batched-entropic-optimal-transport-on-gpus-136964.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.24741>)

Author: Xinyang Wen

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [GPU optimization](<https://devfeed.tech/topics/gpu-optimization.md>), [Combinatorial optimization](<https://devfeed.tech/topics/combinatorial-optimization.md>)

Tags: [batch](<https://devfeed.tech/tags/batch.md>), [block](<https://devfeed.tech/tags/block.md>), [chip](<https://devfeed.tech/tags/chip.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [detection](<https://devfeed.tech/tags/detection.md>), [domain-decomposition](<https://devfeed.tech/tags/domain-decomposition.md>), [execution](<https://devfeed.tech/tags/execution.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [image](<https://devfeed.tech/tags/image.md>), [iteration](<https://devfeed.tech/tags/iteration.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [launch](<https://devfeed.tech/tags/launch.md>), [launches](<https://devfeed.tech/tags/launches.md>), [layers](<https://devfeed.tech/tags/layers.md>), [learning](<https://devfeed.tech/tags/learning.md>), [map](<https://devfeed.tech/tags/map.md>), [matching](<https://devfeed.tech/tags/matching.md>), [optimal-transport](<https://devfeed.tech/tags/optimal-transport.md>), [transport](<https://devfeed.tech/tags/transport.md>)

### AI overview

DrainSinkhorn speeds up batches of small, independent entropic optimal transport problems by making each problem an execution unit: one GPU thread block solves an instance that fits on chip and stops when it converges, freeing capacity for pending work. With a fixed iteration count, multiple instances share a block; the forward map and exact gradient each take one launch. Larger instances can leave later launches after convergence. The abstract reports 2.73-10.75x speedups over OTT-JAX and 5.3-34x over POT on tracking and domain-decomposition workloads, with the largest gains on calls containing thousands of instances. In training layers, it reports 1.05-2.8x over OTT-JAX and 9.9-24x over OTA and GeoTransformer Sinkhorn modules. The abstract also reports reduced label-assignment time and faster GeoTransformer patch matching; it does not provide broader evaluation details.

### Source excerpt

arXiv:2607.24741v4 Announce Type: replace Abstract: Many learning pipelines call entropic optimal transport (OT) inside a loop, and each call is a batch of small, independent problems: one per image in detection label assignment, per patch pair in point-cloud registration, per frame pair in tracking, and per tile in domain decomposition. General GPU solvers launch every Sinkhorn update over the whole batch and run the batch until its slowest problem stops, so practitioners write a kernel for each shape or drop OT. We present DrainSinkhorn, a batched Sinkhorn solver that makes each problem of the batch, an instance, the unit of GPU execution. Wherever an instance fits on chip, one GPU thread block solves it from start to finish and exits as soon as the instance converges, freeing its slot for a pending instance. With a fixed iteration count, several instances share a thread block, and the forward map and its exact gradient take one launch each. Larger instances leave later launches once they converge. On tracking and domain-decomposition workloads, DrainSinkhorn is 2.73-10.75x faster than OTT-JAX, the fastest general batched GPU solver in our comparison, and 5.3-34x faster than POT. The gain is largest on calls with thousands of instances. In training layers it is 1.05-2.8x faster than OTT-JAX and 9.9-24x faster than the Sinkhorn modules of OTA and GeoTransformer, cutting label assignment from 16.3% to 4.7% of each GPU's training step and making GeoTransformer's patch matching 10.4x faster in a training step.

## Learning Nonlinear Transient Dynamics in Fluid Flow Networks with the Neural Basis Method

DevFeed: [Learning Nonlinear Transient Dynamics in Fluid Flow Networks with the Neural Basis Method](<https://devfeed.tech/articles/learning-nonlinear-transient-dynamics-in-fluid-flow-networks-with-the-neural-basis-method-132879.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14534>)

Author: Aijaz Nazir, Yuhe Wang, S. K. Rasel, Min Wang

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Computational Fluid Dynamics (CFD)](<https://devfeed.tech/topics/cfd.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [boundary](<https://devfeed.tech/tags/boundary.md>), [cs-ce](<https://devfeed.tech/tags/cs-ce.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [domain-decomposition](<https://devfeed.tech/tags/domain-decomposition.md>), [edge](<https://devfeed.tech/tags/edge.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [error](<https://devfeed.tech/tags/error.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [flow](<https://devfeed.tech/tags/flow.md>), [fluid](<https://devfeed.tech/tags/fluid.md>), [flux](<https://devfeed.tech/tags/flux.md>), [framework](<https://devfeed.tech/tags/framework.md>), [laws](<https://devfeed.tech/tags/laws.md>), [learning](<https://devfeed.tech/tags/learning.md>), [map](<https://devfeed.tech/tags/map.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [network](<https://devfeed.tech/tags/network.md>), [networks](<https://devfeed.tech/tags/networks.md>), [neural](<https://devfeed.tech/tags/neural.md>), [physics-flu-dyn](<https://devfeed.tech/tags/physics-flu-dyn.md>), [transient-dynamics](<https://devfeed.tech/tags/transient-dynamics.md>)

### AI overview

The neural basis method combines fixed neural bases on each network edge with projection of discretized equations to determine expansion coefficients, preserving a conservative formulation. Non-overlapping domain decomposition couples edge subdomains, and a neural operator learns the parametric map to those coefficients. On looped and branching networks, reported relative L² errors are below 0.02%; the physics-informed neural network baseline fails. For unseen boundary conditions, including interpolation and extrapolation, mean pressure errors stay below 1% and mean flux errors below 3.3%, compared with 8-18% pressure and 85-95% flux errors for the physics-informed DeepONet baseline. The results suggest potential for rapid repeated evaluation in monitoring, design exploration and uncertainty quantification.

### Source excerpt

arXiv:2611.14534v1 Announce Type: cross Abstract: Fluid flow networks, from pipeline infrastructure to biological vasculature, are governed by nonlinear edgewise hyperbolic laws coupled through continuity and conservation at junctions. Many-query tasks require rapid evaluation across unseen parametric settings, but conventional methods re-solve the system for each query at prohibitive cost. Existing physics-informed neural approaches impose the governing equations through penalty losses over generic neural approximators; these losses act only as optimization surrogates, with no guarantee that their reduction reduces solution error, and the resulting optimization is prone to ill-conditioning, particularly for hyperbolic systems. Building on the "representation-then-projection" principle of the neural basis method, we introduce a new approach for modeling fluid flow networks. Fixed neural bases define the representation space on each edge, while projection of the discretized equations determines the expansion coefficients, embedding edgewise laws into a conservative formulation. Edge subdomains are coupled through non-overlapping domain decomposition, and a neural operator learns, directly in this reduced space, the parametric map to the expansion coefficients. On looped and branching network topologies, we reproduce references with relative $L^2$ errors below 0.02%, whereas the physics-informed neural network baseline fails. Across unseen boundary conditions in both interpolation and extrapolation, we maintain mean pressure errors below 1% and mean flux errors below 3.3%, while the physics-informed DeepONet baseline reaches 8-18% pressure errors and 85-95% flux errors. These results highlight the framework's potential for real-time monitoring, design exploration, and uncertainty quantification of fluid flow networks.

## Block-Sparse Gauss-Newton Optimization of Finite Basis Physics-Informed Neural Networks: Sparse Automatic Differentiation Approach

DevFeed: [Block-Sparse Gauss-Newton Optimization of Finite Basis Physics-Informed Neural Networks: Sparse Automatic Differentiation Approach](<https://devfeed.tech/articles/block-sparse-gauss-newton-optimization-of-finite-basis-physics-informed-neural-networks-sparse-automatic-differentiation-approach-128678.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.13231>)

Author: Denis Korolev, Adrian Hill, Jeeeun Lee

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Physics-guided deep learning](<https://devfeed.tech/topics/physics-guided-deep-learning.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Operations research and optimization](<https://devfeed.tech/topics/operations-research-and-optimization.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [automatic](<https://devfeed.tech/tags/automatic.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-na](<https://devfeed.tech/tags/cs-na.md>), [domain-decomposition](<https://devfeed.tech/tags/domain-decomposition.md>), [graph-coloring](<https://devfeed.tech/tags/graph-coloring.md>), [linear-algebra](<https://devfeed.tech/tags/linear-algebra.md>), [math-na](<https://devfeed.tech/tags/math-na.md>), [neural-networks](<https://devfeed.tech/tags/neural-networks.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [physics-informed](<https://devfeed.tech/tags/physics-informed.md>), [sparsity](<https://devfeed.tech/tags/sparsity.md>)

### AI overview

The paper uses FBPINN overlapping domain decomposition to exploit block sparsity in the residual Jacobian and Gauss-Newton matrix. Graph coloring groups structurally orthogonal Jacobian columns or rows for sparse automatic differentiation, reducing differentiation cost and memory while retaining structurally nonzero derivatives. The compressed Jacobian is assembled directly in block-sparse form, allowing sparse direct solvers or preconditioned iterative methods. In reported multiscale PDE experiments, the method achieves high accuracy and substantially faster optimization than first-order baselines, while remaining tractable at large problem sizes.

### Source excerpt

arXiv:2611.13231v1 Announce Type: cross Abstract: In this work, we develop an efficient Gauss-Newton optimization approach for finite basis physics-informed neural networks (FBPINNs). The key ingredient is the overlapping domain decomposition architecture of FBPINNs, which localizes the influence of each subnetwork and induces block sparsity in both the residual Jacobian and the corresponding Gauss-Newton matrix. We characterize this structure and exploit it through sparse automatic differentiation, using graph coloring to partition structurally orthogonal Jacobian columns or rows. This reduces differentiation costs and memory requirements while preserving all structurally nonzero derivative information. The resulting compressed Jacobian representations allow us to assemble the Gauss-Newton system directly in block-sparse form, enabling the use of sparse direct solvers and preconditioned iterative methods. In this way, the otherwise expensive second-order optimization problem is reduced to scalable sparse linear algebra. We demonstrate the approach on multiscale PDEs, where accurate approximation requires rich neural network parametrizations and large numbers of collocation points. Numerical experiments show that our block-sparse Gauss-Newton method attains high accuracy and substantially accelerates optimization relative to first-order baselines while remaining computationally tractable for large problem sizes.

## Adaptive hybrid coupling with operator inference, the overlapping Schwarz alternating method and reinforcement learning

DevFeed: [Adaptive hybrid coupling with operator inference, the overlapping Schwarz alternating method and reinforcement learning](<https://devfeed.tech/articles/adaptive-hybrid-coupling-with-operator-inference-the-overlapping-schwarz-alternating-method-and-reinforcement-learning-108535.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.17837>)

Author: Trishit Mondal, Irina Tezaur, Anthony Gruber

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [coupling](<https://devfeed.tech/tags/coupling.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [domain-decomposition](<https://devfeed.tech/tags/domain-decomposition.md>), [elastic](<https://devfeed.tech/tags/elastic.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [inference](<https://devfeed.tech/tags/inference.md>), [math-mp](<https://devfeed.tech/tags/math-mp.md>), [math-ph](<https://devfeed.tech/tags/math-ph.md>), [reduced-order-models](<https://devfeed.tech/tags/reduced-order-models.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [rl](<https://devfeed.tech/tags/rl.md>), [sam](<https://devfeed.tech/tags/sam.md>)

### AI overview

Deep Q-networks can adapt model fidelity during overlapping Schwarz alternating method (O-SAM) simulations, assigning full order models (FOMs) or pre-trained Operator Inference (OpInf) reduced order models (ROMs) to subdomains as features move. Trained offline with a reward balancing accuracy, cost, and switching frequency, policies are deployed on unseen problems without a reference FOM solution. In a 1D moving-front advection-diffusion case, dynamic allocation outperformed static assignments; allowing the agent to adapt the decomposition brought no further benefit. In 3D elastic wave propagation, policies for two- and three-subdomain decompositions assigned FOMs where the wave was present and ROMs elsewhere. The abstract presents this as a demonstrated potential for predictive online fidelity adaptation in Schwarz-based hybrid simulations.

### Source excerpt

arXiv:2609.17837v2 Announce Type: replace Abstract: Hybrid domain decomposition methods provide a flexible framework for coupling full order models (FOMs) and reduced order models (ROMs), but typically assume the model assigned to each subdomain is fixed throughout a simulation. This is limiting for transient problems in which localized features propagate through the domain and the regions requiring high-fidelity resolution change over time. We introduce a reinforcement learning (RL)-based approach for online adaptation of FOM-ROM models coupled via the overlapping Schwarz alternating method (O-SAM), an iterative domain decomposition method that solves subdomain-local problems while exchanging solution information through transmission boundary conditions on overlapping interfaces. Deep Q-networks (DQNs) are trained offline to select among subdomain-local FOMs and pre-trained Operator Inference (OpInf) ROMs using a reward balancing accuracy, cost, and model-switching frequency. Once trained, the policies are deployed predictively on problem instances not seen during training, without requiring a reference FOM solution. We demonstrate the approach on two examples: a 1D advection-diffusion problem with a moving front, and a 3D linear elastic wave propagation problem implemented in the Norma.jl solid mechanics code. For the advection-diffusion benchmark, the learned policy dynamically allocates high-fidelity resolution as the front propagates and outperforms static FOM/ROM assignments; letting the agent also adapt the domain decomposition provides no further benefit. For the elastic wave benchmark, learned policies for two and three subdomain decompositions track the propagating wave by assigning FOMs to subdomains containing the wave and ROMs elsewhere, as expected. Our results demonstrate the potential of RL to enable predictive online adaptation of model fidelity within Schwarz-based hybrid simulations.

## A Composable Thermal Solver For Heterogeneous 2.5D/3D-IC Packages (Cadence, Notre Dame)

DevFeed: [A Composable Thermal Solver For Heterogeneous 2.5D/3D-IC Packages (Cadence, Notre Dame)](<https://devfeed.tech/articles/a-composable-thermal-solver-for-heterogeneous-2-5d-3d-ic-packages-cadence-notre-dame-89818.md>)

Original publisher: [Read original article](<https://semiengineering.com/a-composable-thermal-solver-for-heterogeneous-2-5d-3d-ic-packages-cadence-notre-dame/>)

Author: Technical Paper Link

Published: 2026-10-18T22:51:32Z

Content type: article

Language: en

Sources: [Semiconductor Engineering](<https://devfeed.tech/sources/semiconductor-engineering.md>)

Topics: [Finite Element Method (FEM)](<https://devfeed.tech/topics/finite-element-method.md>), [Chip design](<https://devfeed.tech/topics/chip-design.md>)

Tags: [2-5d](<https://devfeed.tech/tags/2-5d.md>), [3d](<https://devfeed.tech/tags/3d.md>), [3d-ic](<https://devfeed.tech/tags/3d-ic.md>), [advanced-packaging](<https://devfeed.tech/tags/advanced-packaging.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-ml-dl](<https://devfeed.tech/tags/ai-ml-dl.md>), [cadence](<https://devfeed.tech/tags/cadence.md>), [chiplet](<https://devfeed.tech/tags/chiplet.md>), [chiplets](<https://devfeed.tech/tags/chiplets.md>), [coupling](<https://devfeed.tech/tags/coupling.md>), [design-verification](<https://devfeed.tech/tags/design-verification.md>), [domain-decomposition](<https://devfeed.tech/tags/domain-decomposition.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [flux](<https://devfeed.tech/tags/flux.md>), [heat-flux](<https://devfeed.tech/tags/heat-flux.md>), [iteration](<https://devfeed.tech/tags/iteration.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [models](<https://devfeed.tech/tags/models.md>), [notre-dame](<https://devfeed.tech/tags/notre-dame.md>), [operator-learning](<https://devfeed.tech/tags/operator-learning.md>), [packaging](<https://devfeed.tech/tags/packaging.md>), [semiconductor](<https://devfeed.tech/tags/semiconductor.md>), [semiconductor-engineering](<https://devfeed.tech/tags/semiconductor-engineering.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [technical-papers](<https://devfeed.tech/tags/technical-papers.md>), [thermal-analysis](<https://devfeed.tech/tags/thermal-analysis.md>), [thermal-modeling](<https://devfeed.tech/tags/thermal-modeling.md>), [thermal-simulation](<https://devfeed.tech/tags/thermal-simulation.md>), [topology](<https://devfeed.tech/tags/topology.md>), [university-of-notre-dame](<https://devfeed.tech/tags/university-of-notre-dame.md>)

### AI overview

Researchers from Cadence Design Systems and the University of Notre Dame propose DAIST, a composable AI-accelerated solver for thermal analysis of heterogeneous 2.5D and 3D IC packages. It divides package simulations into block-level subdomains, uses neural operators for those subdomains, and couples them through iterative exchanges of temperature and heat flux. The paper reports reuse across unseen package topologies and speedups of up to 178x, with reported mean temperature errors of 0.068% and 0.323% on two evaluated systems.

### Source excerpt

Researchers at Cadence Design Systems and the University of Notre Dame published "A Composable AI-Accelerated Iterative Solver for 3D-IC Thermal Modeling." Abstract: "Accurate thermal analysis of heterogeneous 2.5D/3D-IC packages is essential yet computationally prohibitive. A single full-package FEM simulation can take hours, while AI-based surrogates treat the entire stack as a monolithic prediction target and... " read more The post A Composable Thermal Solver For Heterogeneous 2.5D/3D-IC Packages (Cadence, Notre Dame) appeared first on Semiconductor Engineering.