{"id":3961,"date":"2025-04-11T16:44:29","date_gmt":"2025-04-11T16:44:29","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2025\/04\/11\/beyond-cad-how-ntop-uses-ai-and-accelerated-computing-to-enhance-product-design\/"},"modified":"2025-04-11T16:44:29","modified_gmt":"2025-04-11T16:44:29","slug":"beyond-cad-how-ntop-uses-ai-and-accelerated-computing-to-enhance-product-design","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2025\/04\/11\/beyond-cad-how-ntop-uses-ai-and-accelerated-computing-to-enhance-product-design\/","title":{"rendered":"Beyond CAD: How nTop Uses AI and Accelerated Computing to Enhance Product Design"},"content":{"rendered":"
\n\t\t<\/span> <\/span> <\/span><\/span><\/p>\n

As a teenager, Bradley Rothenberg was obsessed with CAD: computer-aided design software.<\/p>\n

Before he turned 30, Rothenberg channeled that interest into building a startup, nTop<\/a>, which today offers product developers \u2014 across vastly different industries \u2014 fast, highly iterative tools that help them model and create innovative, often deeply unorthodox designs.<\/p>\n

One of Rothenberg\u2019s key insights has been how closely iteration at scale and innovation correlate \u2014 especially in the design space.<\/p>\n

He also realized that by creating engineering software for GPUs, rather than CPUs \u2014 which powered (and still power) virtually every CAD tool \u2014 nTop could tap into parallel processing algorithms and AI to offer designers fast, virtually unlimited iteration for any design project. The result: almost limitless opportunities for innovation.<\/p>\n

Product designers of all stripes took note.<\/p>\n

A decade after its founding, nTop \u2014 a member of the NVIDIA Inception<\/a> program for cutting-edge startups \u2014 now employs more than 100 people, primarily in New York City, where it\u2019s headquartered, as well as in Germany, France and the U.K. \u2014 with plans to grow another 10% by year\u2019s end.<\/p>\n

Its computation design tools autonomously iterate alongside designers, spitballing different virtual shapes and potential materials to arrive at products, or parts of a product, that are highly performant. It\u2019s design trial and error at scale.<\/p>\n

\u201cAs a designer, you frequently have all these competing goals and questions: If I make this change, will my design be too heavy? Will it be too thick?\u201d Rothenberg said. \u201cWhen making a change to the design, you want to see how that impacts performance, and nTop helps evaluate those performance changes in real time.\u201d<\/p>\n

\"\"
Ocado used nTop software to redesign its 600 series robot to be far lighter and sturdier than earlier versions.<\/figcaption><\/figure>\n

U.K.-based supermarket chain Ocado, which builds and deploys autonomous robots, is one of nTop\u2019s biggest customers.<\/p>\n

Ocado differentiates itself from other large European grocery chains through its deep integration of autonomous robots and grocery picking. Its office-chair-sized robots speed around massive warehouses \u2014 approaching the size of eight American football fields \u2014 at around 20 mph, passing within a millimeter of one another as they pick and sort groceries in hive-like structures.<\/p>\n

In early designs, Ocado\u2019s robots often broke down or even caught fire. Their weight also meant Ocado had to build more robust \u2014 and more expensive \u2014 warehouses.<\/p>\n

Using nTop\u2019s software, Ocado\u2019s robotics team quickly redesigned 16 critical parts in its robots, cutting the robot\u2019s overall weight by two-thirds. Critically, the redesign took around a week. Earlier redesigns that didn\u2019t use nTop\u2019s tools took about four months.<\/p>\n

\"\"
Prototypes of the 600 series robot were printed out using 3D printers for fast-turn testing.<\/figcaption><\/figure>\n

\u201cOcado created a more robust version of its robot that was an order of magnitude cheaper and faster,\u201d Rothenberg said. \u201cIts designers went through these rapid design cycles where they could press a button and the entire robot\u2019s structure would be redesigned overnight using nTop, prepping it for testing the next day.\u201d<\/p>\n

The Ocado use case is typical of how designers use nTop\u2019s tools.<\/p>\n

nTop software runs hundreds of simulations analyzing how different conditions might impact a design\u2019s performance. Insights from those simulations are then fed back into the design algorithm, and the entire process restarts. Designers can easily tweak their designs based on the results, until the iterations land on an optimal result.<\/p>\n

nTop has begun integrating AI models into its simulation workloads, along with an nTop customer\u2019s bespoke design data into its iteration process. nTop uses the NVIDIA Modulus<\/a> framework, NVIDIA Omniverse<\/a> platform and NVIDIA CUDA-X libraries<\/a> to train and infer its accelerated computing workloads and AI models.<\/p>\n

\u201cWe have neural networks that can be trained on the geometry and physics of a company\u2019s data,\u201d Rothenberg said. \u201cIf a company has a specific way of engineering the structure of a car, it can construct that car in nTop, train up an AI in nTop and very quickly iterate through different versions of the car\u2019s structure or any future car designs by accessing all the data the model is already trained on.\u201d<\/p>\n

nTop\u2019s tools have wide applicability across industries.<\/p>\n

A Formula 1 design team used nTop to virtually model countless versions of heat sinks before choosing an unorthodox but highly performant sink for its car.<\/p>\n

Traditionally, heat sinks are made of small, uniform pieces of metal aligned side by side to maximize metal-air interaction and, therefore, heat exchange and cooling.<\/p>\n

\"\"
A heat sink designed for a Formula 1 race car offered 3x more surface area and was 25% lighter than previous sinks.<\/figcaption><\/figure>\n

The engineers iterated with nTop on an undulating multilevel sink that maximized air-metal interaction even as it optimized aerodynamics, which is crucial for racing.<\/p>\n

The new heat sink achieved 3x the surface area for heat transfer than earlier models, while cutting weight by 25%, delivering superior cooling performance and enhanced efficiency.<\/p>\n

Going forward, nTop anticipates its implicit modeling tools will drive greater adoption from product designers who want to work with an iterative \u201cpartner\u201d trained on their company\u2019s proprietary data.<\/p>\n

\u201cWe work with many different partners who develop designs, run a bunch of simulations using models and then optimize for the best results,\u201d said Rothenberg. \u201cThe advances they\u2019re making really speak for themselves.\u201d<\/p>\n

Learn more about nTop\u2019s <\/i>product design workflow<\/i><\/a> and work with <\/i>partners<\/i><\/a>.<\/i><\/p>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"

https:\/\/blogs.nvidia.com\/blog\/ntop-computer-aided-design-ai-accelerated-computing\/<\/p>\n","protected":false},"author":0,"featured_media":3962,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[3],"tags":[],"_links":{"self":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/3961"}],"collection":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/comments?post=3961"}],"version-history":[{"count":0,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/3961\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media\/3962"}],"wp:attachment":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media?parent=3961"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/categories?post=3961"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/tags?post=3961"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}