Radeon Pro Duo Steps Down Performance and Price

The new Radeon Pro Duo GPU. (Image courtesy of AMD.)

Recently, AMD announced the release of a new Radeon Pro Duo graphics card and, in an interesting turn of strategy, lowered the performance and price of the new GPU.

According to AMD, the new Polaris-based GPU will produce 11.45 teraflops of single-precision point performance, some 4.55 teraflops less than AMD’s latest Pro Duo model. Still, AMD suggests that its new chip is more than capable powering through engineering, 3D modelers, filmmakers and virtual reality (VR) content developers. With its $999 starting price and its 250-watt power rating, the new Pro Duo not only starts out much cheaper, it’ll be less expensive to run as well.

But what exactly is driving the 2017 incarnation of the Pro Duo?

AMD has designed the hulking GPU unit around two Radeon Pro WX 7100 cards, making it two times faster than a sole Pro WX 7100 stuffed into a workstation. With its 32GB of GDDR5 memory, the Pro Duo can handle large data sets, making it possible for designers to work with 8K content, large assemblies and VR workflows.

“Today’s professional workflows continue to increase in complexity, often demanding that creators switch between a wide variety of applications to progress their work,” said Ogi Brkic, general manager of professional graphics at AMD. “We designed the Radeon Pro Duo to eliminate those constraints, empowering professionals to multi-task without compromise, dedicating GPU resources where and how they need them. It’s a continuation of our promise for Radeon Pro: to provide greater choice in how professionals practice their craft, enabling superior multi-tasking, accelerated applications and powerful solutions for advanced workloads like VR.”

Whether every engineer needs all of the power provided by the Pro Duo is debatable, but those working in the aerospace, automotive, oil and gas or simulation industries can certainly benefit from its power. For many of us work-a-day modelers though, an extra $999 on top of an already expensive workstation might represent a bit too much invested for minimal realized gain.