A few short years ago, the LEGO Group—makers of the iconic locking building-block toys so many parents have stepped on in the middle of the night—was plagued by uncontrolled technology sprawl.

Various business units within LEGO were purchasing redundant licenses for the same technologies, with each team using the technologies for different purposes. Many business units had even established their own computing platforms. The result was unnecessary costs and added complexity.

Michael Schøler, part of a team from Danish consultancy Hinnerup Net, was brought in by LEGO (also based in Denmark) to help sort through the confusion. During a GTC 2012 session Tuesday, he said it was clear at the time that the company needed a unified technology platform that could do everything: facilitate high-end and low-end games, support mobile applications, power the LEGO.com website — you name it.

Henrik Høj Madsen (left) and Michael Schøler (right)
lead the GTC 2012 session

So LEGO turned to NVIDIA. Zeroing in on the CUDA computing platform, the company wanted not only fast rendering of 3D imagery, but also aspired to leverage CUDA to manage critical business functions. Now, three years later, LEGO is running much of its business on the platform.

“We have a proven system that’s working well,” Schøler said during an interview following his session.

CUDA also helped LEGO solve a very specific—and performance-draining—problem. Some 95 percent of the little circular knobs that enable LEGO pieces to interlock are invisible in a finished model, yet a massive amount of the company’s compute power was being sucked up to render those polygons. With Hinnerup Net’s help, LEGO tapped CUDA to purge the invisible polygons in its rendering systems, freeing up computing resources.

Interestingly, one asset LEGO has not yet ported to the CUDA platform is the company’s high-end 3D rendering system, but Schøler said his team is working on that. They’ve developed a proof of concept, and it’s performed well so far. All that’s left is to convince the affected project groups at LEGO to give the green light to make a change.

“We’re trying to convince the business that this is the way to go,” said Schøler. “We’re doing the marketing for NVIDIA.”

  • http://www.facebook.com/michael.schoeler Michael Schøler

    Michael Schøler here: I’d like to add credits where credits are most certainly due; As stated in the presentation, the CUDA work and OptiX optimizations were done by a team from the Alexandra Institute, and tech engineers from NVIDIA. We (Henrik and I who did the presentation) have helped implementing the distributed and scalable system architecture around the existing and emerging in-house optimization technologies.

  • Will Park

    Thanks for chiming in, Michael. Great to hear it straight from the (expert) horse’s mouth, as it were! :)

  • http://twitter.com/jturato John Turato

    It’s ironic that the very example I typically use to describe why a Service Oriented Architecture makes sense (the Lego as a reusable component that can be assembled into multiple end products) is the very company that needed a unified technology platform that could do everything.

  • http://www.facebook.com/gmsgolan גולן מוצלאוי

     was looking for locksmith and went to  www.immediate-locksmith.com   The technician arrived quickly and was professional in his work and courteous service was excellent the price was fair