Feb 18, 2011 14:07 GMT  ·  By

When it was first introduced by Ageia back in 2004, hardware accelerated physics seemed like it had the potential to transform the whole gaming industry, but now, almost seven years thereafter, the whole excitement that surrounded the technology seems to have died down. However, GPU physics could return to the center stage once more as now, AMD too wants to incorporate a similar solution in their Fusion APUs.

Unlike Nvidia, AMD has taken a different approach when establishing their strategy and has opted to build its solution around the Bullet Physics engine which can be programmed using the OpenCL framework as well as some other low-level APIs.

“Today there are already portions of Bullet Physics that are hardware accelerated with OpenCL, and some of the parts are CUDA-accelerated too, so the model we bring will be very friendly to developers – it will be inclusive, they can take some libraries and do some of them in CPU and some in GPU,” said Manju Hegde, who co-founded Aegia and is now working for AMD as corporate vice president in the Fusion Experience Program.

“It'll be up to the developer to use it, so it's not like we'll say this is what you can use for ATI, this is what we've activated and this is what you need to do to use it.”

According to the Bit-Tech website, the Bullet Physics website is able to create impressive rigid body physics and has already been deployed for developing a wide series of Hollywood blockbusters such as 2012, Hancock and The A-Team.

In addition, the physics engine has also been used for developing some high-profile games, including Grand Theft Auto IV, Red Dead Redemption and Toy Story.

Right now, the most important advantage AMD's approach has over Nvidia's PhysX is its flexibility as OpenCL will surely be used in a wide series of hardware platform in the feature and, if this API manages to hit gaming consoles, it will surely mark a turning point for GPU-accelerated physics.