Microsoft’s DirectCompute API for GPU Computing is supported on NVIDIA’s DX10 and DX11 class GPUs under Windows VISTA and later versions of Windows. Simply install the latest drivers from www.nvidia.com/drivers and applications that rely on DirectCompute will immediately have access to the massive parallel computing power of NVIDIA GPUs to create compelling experiences in consumer and professional applications.
As part of the DirectCompute presentation at the Game Developer Conference (GDC) in March 2009 in San Francisco CA, NVIDIA presented three demonstrations running on an NVIDIA GeForce GTX 280 GPU.
As a processor company, NVIDIA enthusiastically supports language solutions that enable developers to access the parallel processing power of the GPU. In addition to DirectCompute and NVIDIA’s CUDA C/C++, there are solutions for C#, Fortran, Java, MATLAB, OpenCL™, Python and other languages.
NVIDIA has a long history of embracing and supporting a wide variety of programming languages that improve the number and scope of applications that can exploit parallel computing on the GPU. NVIDIA is the only processor company to offer this breadth of development environments for the GPU.
- DirectCompute presentations
- NVIDIA developer forum
- NVIDIA's DirectCompute GPU ocean demo
- NVIDIA's DirectCompute GPU n-body demo
- NVIDIA's DirectCompute GPU particle simulation demo
- Microsoft's DirectX Developer Center