NVIDIA introduces advanced visualization hardware, toolkit
Computer graphics card developer NVIDIA is launching a 4-gigabyte (GB) graphics card, the Quadro FX 5800 and the Quadro Plex 2200 S4 VCS 3D accelerator, designed for the diagnostic medical imaging advanced visualization market.
The Quadro FX 5800 features interactive 4D modeling with time-lapse capabilities, a massive memory bandwidth of up to 102 GB per second, fill rates that exceed 52 billion texels per second and geometry performance of 300 million triangles per second, as well as support for next-generation OpenGL and Microsoft DirectX 10 applications.
The Quadro Plex 2200 S4 VCS contains four Quadro FX 5800 graphic processing units (GPUs) for large-scale server deployment in a distributed 3D visualization environment. The 3D accelerator system offers parallel computing processor architecture with 960 Compute Unified Device Architecture (CUDA) parallel processing cores exposed through a C-language environment and tool suite.
In concert with the hardware offerings, the company has released its NVScale 1.0 SDK, a toolset which allows developers to span all the GPUs seen by host system and scale application performance for large model rendering. The NVScale combined with the multi-GPU visualization on the four Quadro FX 5800 GPUs of the Quadro Plex 2200 S4, allows models to be accelerated up to 16-times faster, processing 1.2 giga triangles per second.
The Quadro FX 5800 features interactive 4D modeling with time-lapse capabilities, a massive memory bandwidth of up to 102 GB per second, fill rates that exceed 52 billion texels per second and geometry performance of 300 million triangles per second, as well as support for next-generation OpenGL and Microsoft DirectX 10 applications.
The Quadro Plex 2200 S4 VCS contains four Quadro FX 5800 graphic processing units (GPUs) for large-scale server deployment in a distributed 3D visualization environment. The 3D accelerator system offers parallel computing processor architecture with 960 Compute Unified Device Architecture (CUDA) parallel processing cores exposed through a C-language environment and tool suite.
In concert with the hardware offerings, the company has released its NVScale 1.0 SDK, a toolset which allows developers to span all the GPUs seen by host system and scale application performance for large model rendering. The NVScale combined with the multi-GPU visualization on the four Quadro FX 5800 GPUs of the Quadro Plex 2200 S4, allows models to be accelerated up to 16-times faster, processing 1.2 giga triangles per second.