{"id":83111,"title":"DeepSim – AI physics simulations","tagline":"Run complex physics simulations signficantly faster than any commerical tool.","body":"**TLDR:** AI-accelerated 3D physics simulator for engineers\n\n[DeepSim](https://www.deepsim.io/) makes it easy for engineers to run 3D physics simulations fast. This means rapid design iterations for better products and real-world monitoring for better decisions.\n\nWe built a new physics simulation platform that leverages AI physics models for very fast, ultra-scalable physics simulations.\n\n—\n\nHi everyone! We are [Connor,](https://www.linkedin.com/in/connor-j-mcclellan/) [Alex,](https://www.linkedin.com/in/alexgabourie/) and [Chuck,](https://www.linkedin.com/in/ckoroglu/) and we love physics simulations. While working on our PhDs at Stanford, we saw how physics simulators needed a refresh to solve modern problems. That’s why we started [DeepSim.](https://www.deepsim.io/)\n\n## The Problem\n\nRunning 3D physics simulations is **difficult**, **expensive**, and **slow**.\n\n1. **Setup:** Experienced engineers still spend countless hours meshing their designs before even running a single simulation.\n2. **Run:** Many simulations take hours to even weeks on expensive compute systems. Some are even intractable and require highly trained engineers to simplify the problems at a significant cost of accuracy.\n3. **Attention:** Each step requires constant babysitting as simulators are fragile and can fail at any time.\n\n🧑‍🔧️ Engineers hate the tedious simulation setup and wasted time due to failed simulations.\\\n👔 Managers hate that engineers can’t go faster and use tons of cloud credits.\\\n💰 CEOs/VPs hate that engineering delays stall a product launch.\n\n## The Solution\n\nLeverage AI to **simplify**, **speed up**, and **scale up** 3D physics simulations.\n\nWe are building a new AI physics simulation platform, automating away the physics setup and simulating designs 1000X faster with no drop in accuracy.\n\nOur platform uses lightweight, easy-to-train AI models combined with a powerful GPU-accelerated solver to deliver solutions quickly and efficiently. This approach eliminates the bulkiness of traditional finite element method (FEM) tools and overcomes the inflexibility of other AI physics simulators.\n\n![uploaded image](/media/?type=post\u0026id=83111\u0026key=user_uploads/1869533/6218d9cd-39b9-4307-a144-9f346d8d3c65)\n\nAt [DeepSim](https://www.deepsim.io/), we have already worked with semiconductor companies to build the most powerful thermal simulator for circuit design, running thermal simulations with billions of nodes in minutes on a single GPU, which is 1000X more detail than a commercial tool can deliver using 50+ CPU cores in the same amount of time.\n\nWith DeepSim's simulator, we are able to model extremely complex geometries with length scales spanning 6 orders of magnitude, intractable to solve with FEM tools. Below is a thermal simulation of an integrated circuit, complete with a heat sink and airflow, that only took 10 minutes to run. We can resolve hot spots in individual transistors (\\~10 nm in size) within a whole chip (1 cm).\n\n![uploaded image](/media/?type=post\u0026id=83111\u0026key=user_uploads/1869533/26e48815-e3db-4cfa-bdd4-52168c537546)\n\n## Use Cases\n\nThis is a breakthrough in 3D physics simulations that empowers engineers in the same way FEM did 50 years ago. We’re excited to see where engineers take our tool!\n\nSome initial use cases are:\n\n* Speeding up the design of complex systems with faster simulations\n* Utilizing design automation to speed up development\n* Developing digital twins for system operation\n\n## The Team\n\n![uploaded image](/media/?type=post\u0026id=83111\u0026key=user_uploads/1869533/c032c745-4faf-4374-8a43-92de0645a397)\n\nChuck, Alex, and Connor founded DeepSim to solve the frustrating parts of their PhDs.\n\n## The Ask\n\nWe would love to talk with engineers that…\n\n* design and operate battery packs for EVs or grid-scale energy storage\n* design and deploy satellites\n* work on thermal management of semiconductors, from the chip scale to data centers\n* have any complaints about slow or frustrating simulations\n\nContact us at [founders@deepsim.io](mailto:founders@deepsim.io)!","slug":"LcV-deepsim-ai-physics-simulations","created_at":"2024-08-16T04:14:43.665Z","updated_at":"2026-04-22T07:40:03.594Z","total_vote_count":35,"url":"https://www.ycombinator.com/launches/LcV-deepsim-ai-physics-simulations","share_image_url":"https://www.ycombinator.com/media/?type=post\u0026id=83111\u0026key=user_uploads/1869533/c032c745-4faf-4374-8a43-92de0645a397","company":{"id":29672,"name":"DeepSim, Inc.","slug":"deepsim-inc","url":"https://www.deepsim.io","logo":"https://bookface-images.s3.amazonaws.com/small_logos/4d2d742eff5354c7ab2613bb9ba4ba6a64e707b5.png","batch":"Summer 2024","industry":"B2B","tags":["B2B","Semiconductors","AI"],"search_path":"https://bookface.ycombinator.com/company/29672"}}