NVidia has just released their first previews of CUDA5.5 with their usual collection of new bells and whistles, but one big one shows up in this version: Native ARM support for the classis CUDA toolchain.
Nvidia says combining high-performance CUDA-enabled GPU accelerators with low-power ARM-based systems on a chip (SoCs) will enable ARM-based systems to penetrate new markets requiring the highest levels of energy-efficient compute performance. These market segments include: defense systems, automotive, energy exploration, mobile computing, robotics, scientific research, HPC and others.
NVidia has been interested in ARM for a while now, with systems like Tegra and their growing interested in the mobile space. With this release, you can now take advantage of GPU acceleration with familiar CUDA toolsets, without having to rebuild things in other exotic systems.
via GraphicSpeak » Nvidia adds ARM platform support to CUDA GPU programming.
