# physics AI

Published articles for physics AI.

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

## PhysicsNeMo-Mesh: GPU-Native Meshes and Simulation Cases for Physics AI

DevFeed: [PhysicsNeMo-Mesh: GPU-Native Meshes and Simulation Cases for Physics AI](<https://devfeed.tech/articles/physicsnemo-mesh-gpu-native-meshes-and-simulation-cases-for-physics-ai-108765.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.39072>)

Author: Peter D. Sharpe, Corey Adams, Negin Sobhani, Sanjay Choudhry

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

Content type: article

Language: en

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

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [automatic](<https://devfeed.tech/tags/automatic.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [cases](<https://devfeed.tech/tags/cases.md>), [cells](<https://devfeed.tech/tags/cells.md>), [complete](<https://devfeed.tech/tags/complete.md>), [compute](<https://devfeed.tech/tags/compute.md>), [cs-cg](<https://devfeed.tech/tags/cs-cg.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [curation](<https://devfeed.tech/tags/curation.md>), [data](<https://devfeed.tech/tags/data.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [error](<https://devfeed.tech/tags/error.md>), [fast](<https://devfeed.tech/tags/fast.md>), [faster](<https://devfeed.tech/tags/faster.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [mesh](<https://devfeed.tech/tags/mesh.md>), [physics](<https://devfeed.tech/tags/physics.md>), [physics-ai](<https://devfeed.tech/tags/physics-ai.md>), [physics-comp-ph](<https://devfeed.tech/tags/physics-comp-ph.md>), [physicsnemo](<https://devfeed.tech/tags/physicsnemo.md>), [simulation](<https://devfeed.tech/tags/simulation.md>)

### AI overview

PhysicsNeMo-Mesh brings batched GPU mesh processing into PyTorch automatic differentiation while preserving named fields, their locations and shapes, and simulation cases with PDE specifications and boundary values. On one GB200 GPU, the abstract reports mesh operations 6.2-1,068x faster than VTK with 72 threads, and whole-case loading 8.0-88x faster than reading VTK files (8.0x when both read the same fields). With preprocessing overlapped with training, the reported throughput cost is 2.1% for a 127 ms Transolver step. This enables one stored DrivAerML dataset to feed Transolver, GeoTransolver, and GLOBE in a public recipe. In a heat-conduction setting where shapes and wall conditions vary, per-boundary conditions reduced error from 87% to 6-9%.

### Source excerpt

arXiv:2610.39072v1 Announce Type: cross Abstract: PhysicsNeMo-Mesh is the mesh module of the open-source PhysicsNeMo library. It provides mesh processing similar to PyVista, but on the GPU, in batches, and inside PyTorch's automatic differentiation. Like xarray for unstructured meshes, it attaches semantics to data: fields on points, cells, and whole meshes have names and shapes, and a simulation case keeps the complete PDE problem specification, including boundary conditions and their prescribed values. It addresses three problems that plague machine learning for physical simulation. First, GPU utilization is bottlenecked by I/O, because samples are very large relative to the compute per forward pass. Second, because traditional preprocessing is expensive, it is necessarily done once, during curation, rather than differently for each model and workflow at the point of use. Finally, advanced equivariant and mesh-native architectures require information that curation ordinarily discards. Fast GPU mesh processing makes it practical to preprocess at the point of use: on one GB200 GPU, mesh operations run $6.2\text{--}1{,}068\times$ faster than VTK with 72 threads, and loading a whole case is $8.0\text{--}88\times$ faster than reading its VTK files ($8.0\times$ when both read the same fields). Overlapped with training, this preprocessing costs $2.1\%$ of throughput for a $127\,\text{ms}$ Transolver step. So one dataset serves many models and workflows: in PhysicsNeMo's public recipe, one stored DrivAerML dataset feeds Transolver, GeoTransolver, and GLOBE. PhysicsNeMo-Mesh combines the speed of an intermediate array store with the flexibility of an archival format such as VTK. When shapes and wall conditions both vary, per-boundary conditions cut a heat-conduction error from $87\%$ to $6\text{--}9\%$. And by keeping field ranks and named boundaries, it retains the semantic structure that next-generation architectures will need.

## Physics AI pushes chip design beyond traditional simulation

DevFeed: [Physics AI pushes chip design beyond traditional simulation](<https://devfeed.tech/articles/physics-ai-pushes-chip-design-beyond-traditional-simulation-88551.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/16/vinci4d-physics-models-semiconwest/>)

Author: Devony Hof

Published: 2026-10-16T17:47:37Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [Chip design](<https://devfeed.tech/topics/chip-design.md>), [Simulation](<https://devfeed.tech/topics/simulation.md>), [Physics-guided deep learning](<https://devfeed.tech/topics/physics-guided-deep-learning.md>), [Distributed Systems & Parallel Computing](<https://devfeed.tech/topics/distributed-systems-parallel-computing.md>)

Tags: [advanced-packaging](<https://devfeed.tech/tags/advanced-packaging.md>), [aerospace](<https://devfeed.tech/tags/aerospace.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [automotive](<https://devfeed.tech/tags/automotive.md>), [business](<https://devfeed.tech/tags/business.md>), [chip](<https://devfeed.tech/tags/chip.md>), [chip-fabrication](<https://devfeed.tech/tags/chip-fabrication.md>), [company](<https://devfeed.tech/tags/company.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cube-event-coverage](<https://devfeed.tech/tags/cube-event-coverage.md>), [customer](<https://devfeed.tech/tags/customer.md>), [design](<https://devfeed.tech/tags/design.md>), [fab-construction](<https://devfeed.tech/tags/fab-construction.md>), [has](<https://devfeed.tech/tags/has.md>), [heterogeneous-integration](<https://devfeed.tech/tags/heterogeneous-integration.md>), [karthik-aravamudhan](<https://devfeed.tech/tags/karthik-aravamudhan.md>), [manufacturing-automation](<https://devfeed.tech/tags/manufacturing-automation.md>), [news](<https://devfeed.tech/tags/news.md>), [physical-ai](<https://devfeed.tech/tags/physical-ai.md>), [physics](<https://devfeed.tech/tags/physics.md>), [physics-ai](<https://devfeed.tech/tags/physics-ai.md>), [semicon-west-2026](<https://devfeed.tech/tags/semicon-west-2026.md>), [semiconductor](<https://devfeed.tech/tags/semiconductor.md>), [semiconductor-design](<https://devfeed.tech/tags/semiconductor-design.md>), [semiconductor-engineering](<https://devfeed.tech/tags/semiconductor-engineering.md>), [semiconductor-industry](<https://devfeed.tech/tags/semiconductor-industry.md>), [semiconductor-manufacturing](<https://devfeed.tech/tags/semiconductor-manufacturing.md>), [semiconductor-sustainability](<https://devfeed.tech/tags/semiconductor-sustainability.md>), [semiconwest](<https://devfeed.tech/tags/semiconwest.md>), [semiconwest26eventpage](<https://devfeed.tech/tags/semiconwest26eventpage.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [smart-manufacturing](<https://devfeed.tech/tags/smart-manufacturing.md>), [software](<https://devfeed.tech/tags/software.md>), [study](<https://devfeed.tech/tags/study.md>), [supply-chain-resilience](<https://devfeed.tech/tags/supply-chain-resilience.md>), [technology](<https://devfeed.tech/tags/technology.md>), [thecube](<https://devfeed.tech/tags/thecube.md>), [vinci](<https://devfeed.tech/tags/vinci.md>), [vinci4d](<https://devfeed.tech/tags/vinci4d.md>)

### AI overview

Vinci4D provides semiconductor designers with simulation software built on pretrained physics models. The company says the models, trained on physics equations rather than customer data, can analyze multiple physical phenomena at once and may reduce simulation time and cost. Vinci4D recently raised $250 million in a Series B round and plans to expand into automotive and aerospace applications.

### Source excerpt

Vinci4D Inc. is bringing a new approach to semiconductor design grounded in fundamental physics equations. The company provides simulation software for chip designers, offering an alternative to traditional simulation methods, including finite element analysis, a technique engineers use to study the physical behavior of objects. Instead, Vinci4D's technology uses pretrained physics models to accelerate simulations [...] The post Physics AI pushes chip design beyond traditional simulation appeared first on SiliconANGLE.

## Vinci pushes the boundaries of chip design with physics AI

DevFeed: [Vinci pushes the boundaries of chip design with physics AI](<https://devfeed.tech/articles/vinci-pushes-the-boundaries-of-chip-design-with-physics-ai-88550.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/16/vinci-brings-physics-ai-into-chip-design-loop-semiconwest/>)

Author: Victoria Gayton

Published: 2026-10-16T16:29:25Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [Chip design](<https://devfeed.tech/topics/chip-design.md>), [Electrical engineering and computer science (EECS)](<https://devfeed.tech/topics/electrical-engineering-and-computer-science-eecs.md>), [model architecture](<https://devfeed.tech/topics/model-architecture.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [AWS Trainium](<https://devfeed.tech/topics/aws-trainium.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [chip-design](<https://devfeed.tech/tags/chip-design.md>), [christophe-bertrand](<https://devfeed.tech/tags/christophe-bertrand.md>), [continuous-physics-reasoning](<https://devfeed.tech/tags/continuous-physics-reasoning.md>), [cube-event-coverage](<https://devfeed.tech/tags/cube-event-coverage.md>), [dinesh-panneerselvam](<https://devfeed.tech/tags/dinesh-panneerselvam.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineering-simulation](<https://devfeed.tech/tags/engineering-simulation.md>), [infra](<https://devfeed.tech/tags/infra.md>), [news](<https://devfeed.tech/tags/news.md>), [physical-ai](<https://devfeed.tech/tags/physical-ai.md>), [physics-ai](<https://devfeed.tech/tags/physics-ai.md>), [semicon-west-2026](<https://devfeed.tech/tags/semicon-west-2026.md>), [semiconductor-engineering](<https://devfeed.tech/tags/semiconductor-engineering.md>), [semiconwest](<https://devfeed.tech/tags/semiconwest.md>), [thecube](<https://devfeed.tech/tags/thecube.md>), [vinci](<https://devfeed.tech/tags/vinci.md>), [vinci4d](<https://devfeed.tech/tags/vinci4d.md>)

### AI overview

Vinci4D uses a physics foundation model alongside a GPU-native physics kernel to bring simulation into semiconductor design workflows. The company says the approach combines solver-level accuracy with speed and can run behind customers' firewalls while using Vinci's own training data. Vinci is also exploring applications in automotive and aerospace engineering and plans to add electromagnetics and fluid dynamics capabilities.

### Source excerpt

Physics AI is bringing a new approach to semiconductor engineering, where increasingly complex designs make physical behavior harder to predict. Advanced accelerators combine multiple chips, memory and packaging components, creating tightly coupled engineering challenges. Vinci4D Inc. uses physics AI to bring simulation into engineers' everyday design work. Its approach addresses a familiar engineering tradeoff, according [...] The post Vinci pushes the boundaries of chip design with physics AI appeared first on SiliconANGLE.