ACADEMIA

Enabling accelerated supercomputing through the combination of CPU and GPU technologies across major operating systems Windows, Mac and Linux accessed via standard highlevel programming environments C/C++, Java, C# and matlab etc.

At GPU Systems http://www.gpusystems.com headquarters in 2012, the company has released its latest version of the Libra Platform & SDK with enhanced support for developers to uniformly accelerate software applications across major operating systems, Windows, Mac and Linux.

Libra Compute API for developers offers performance portability and direct uniform hardware access via standard programming environments C/C++, Java, C# and matlab to execute math operations on top of current and future compute architectures, including the latest GPUs, x86/x64 CPUs and with broad support for compute devices compatible with lowlevel specific APIs – OpenCL, CUDA, OpenGL, DirectX and standard x86/x64 compute APIs.

"With this release we show that using the very latest advanced compute technologies are available to develop software applications using standard programming languages & environments. It is now possible to deploy software on both CPUs and GPUs and across major platforms without customization or modification to program code," says GPU Systems founder Marco Hjerpe.

Key Facts

  * Unleash the Teraflop performance of CPUs and GPUs and future compute accelerators to execute software applications across major operating systems Windows, Mac and Linux.

  * Libra API direct compute access via standard programming languages, C/C++, Java, C# and matlab etc.

  * Develop code once, deploy on numerous CPU and GPU devices.

  * More performance with less code compared to hardware specific lowlevel APIs, easier to maintain applications & algorithms and faster time to market – no need to learn new tools or programming languages.